Upload 466 files

.gitattributes

@@ -33,3 +33,38 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/dog.jpg filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example0.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example1.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example2.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example3.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example4.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example5.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example6.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/demo/input_imgs/example8.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/figs/coco_vis_comp.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/figs/points_comp.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/figs/sam_variants_comp.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/figs/sam_vs_hqsam_backbones.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/figs/sam-hf-framework.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/assets/hq-sam2-results.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/demo/input_images/example1.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/demo/input_images/example2.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/demo/input_images/example3.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/notebooks/images/cars.jpg filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/notebooks/images/groceries.jpg filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/notebooks/images/truck.jpg filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/sam-hq2/notebooks/videos/bedroom.mp4 filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/seginw/GroundingDINO/.asset/arch.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/seginw/GroundingDINO/.asset/cats.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/seginw/GroundingDINO/.asset/COCO.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/seginw/GroundingDINO/.asset/GD_GLIGEN.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/seginw/GroundingDINO/.asset/GD_SD.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/seginw/GroundingDINO/.asset/hero_figure.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/seginw/GroundingDINO/.asset/ODinW.png filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/visual_demo/1.gif filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/visual_demo/2.gif filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/visual_demo/3.gif filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/visual_demo/4.gif filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/visual_demo/5.gif filter=lfs diff=lfs merge=lfs -text
+sam2.1HQ/sam-hq-main/visual_demo/6.gif filter=lfs diff=lfs merge=lfs -text

sam2.1HQ/sam-hq-main/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

sam2.1HQ/sam-hq-main/README.md

@@ -0,0 +1,318 @@
+# Segment Anything in High Quality
+
+<a href="https://colab.research.google.com/drive/1QwAbn5hsdqKOD5niuBzuqQX4eLCbNKFL?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+[![Huggingfaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/sam-hq-team/sam-hq)
+[![Open in OpenXLab](https://cdn-static.openxlab.org.cn/app-center/openxlab_app.svg)](https://openxlab.org.cn/apps/detail/keleiwhu/sam-hq)
+[![Downloads](https://static.pepy.tech/badge/segment-anything-hq)](https://pepy.tech/project/segment-anything-hq)
+
+
+> [**Segment Anything in High Quality**](https://arxiv.org/abs/2306.01567)           
+> NeurIPS 2023  
+> ETH Zurich & HKUST 
+
+We propose HQ-SAM to upgrade SAM for high-quality zero-shot segmentation. Refer to our [paper](https://arxiv.org/abs/2306.01567) for more details.
+
+## Latest updates
+
+**2025/06** -- :fire::fire: HQ-SAM is supported in the [Huggingface Transformers](https://github.com/huggingface/transformers) library. Please see the detailed usage instruction [here](https://huggingface.co/docs/transformers/main/model_doc/sam_hq). The pretrained model checkpoints can also be downloaded at [here](https://huggingface.co/syscv-community).
+
+**2024/11/17 -- HQ-SAM 2 is released**
+
+- A new suite of improved model checkpoints (denoted as **HQ-SAM 2**, beta-version) are released. See [Model Description](sam-hq2/README.md) for details. Change working directory by `cd sam-hq2`
+
+![HQ-SAM2 results comparison](sam-hq2/assets/hq-sam2-results.png?raw=true)
+
+Updates
+-----------------
+:fire::fire: **SAM for Video Segmentation**: Interested in intersecting SAM and video? HQ-SAM is supported by [DEVA](https://github.com/hkchengrex/Tracking-Anything-with-DEVA) in its text-prompted mode! Also, check the work [MASA](https://github.com/siyuanliii/masa) and [SAM-PT](https://github.com/SysCV/sam-pt) with SAM.
+
+:fire::fire: **SAM in 3D**: Interested in intersecting SAM and 3D Gaussian Splatting? See our new work [Gaussian Grouping](https://github.com/lkeab/gaussian-grouping)! Also, if you are interested in intersecting SAM and NeRF, please see work [SANeRF-HQ](https://github.com/lyclyc52/SANeRF-HQ)!
+
+More: HQ-SAM is adopted in [Osprey](https://arxiv.org/abs/2312.10032), [CaR](https://torrvision.com/clip_as_rnn/), [SpatialRGPT](https://arxiv.org/abs/2406.01584), [GLaMM](https://arxiv.org/abs/2311.03356), [ENIGMA-51](https://iplab.dmi.unict.it/ENIGMA-51/) to provide fine-grained mask annotations.
+
+
+Platform integration: HQ-SAM is supported in the [OpenMMLab PlayGround](https://github.com/open-mmlab/playground/blob/main/label_anything/readme.md) for annotation with Label-Studio, in [segment-geospatial](https://github.com/opengeos/segment-geospatial) for segmenting geospatial data, and mask annotation tool [ISAT](https://github.com/yatengLG/ISAT_with_segment_anything), and [Supervisely](https://supervisely.com/blog/segment-anything-in-high-quality-HQ-SAM/)!
+
+2023/08/11: Support [python package](#quick-installation-via-pip) for easier **pip installation**. Light HQ-SAM is in [EfficientSAM series](https://github.com/IDEA-Research/Grounded-Segment-Anything/tree/main/EfficientSAM) combining with [Grounded SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything/)!
+
+<!-- 2023/07/21: HQ-SAM is also in OpenXLab apps, thanks their support! -->
+
+:rocket::rocket: 2023/07/17: We released **Light HQ-SAM** using TinyViT as backbone, for both fast and high-quality zero-shot segmentation, which reaches **41.2 FPS**. Refer to [Light HQ-SAM vs. MobileSAM](#light-hq-sam-vs-mobilesam-on-coco) for more details.
+
+:trophy::1st_place_medal: 2023/07/14: Grounded **HQ-SAM** obtains the **first place**:1st_place_medal: in the [Segmentation in the Wild](https://eval.ai/web/challenges/challenge-page/1931/leaderboard/4567) competition on zero-shot track (hosted in [CVPR 2023 workshop](https://computer-vision-in-the-wild.github.io/cvpr-2023/)), outperforming Grounded SAM. Refer to our [SGinW evaluation](#grounded-hq-sam-vs-grounded-sam-on-seginw) for more details.
+
+2023/07/05: We released [SAM tuning instuctions](#hq-sam-tuning-and-hq-seg44k-data) and [HQSeg-44K data](#hq-sam-tuning-and-hq-seg44k-data).
+
+2023/07/04: HQ-SAM is adopted in [SAM-PT](https://github.com/SysCV/sam-pt) to improve the SAM-based zero-shot video segmentation performance. Also, HQ-SAM is used in [Grounded-SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything), [Inpaint Anything](https://github.com/Uminosachi/sd-webui-inpaint-anything) and [HQTrack](https://github.com/jiawen-zhu/HQTrack) (2nd in VOTS 2023).
+
+2023/06/28: We released the [ONNX export script](#onnx-export) and [colab notebook](https://colab.research.google.com/drive/11U2La49c2IxahzJkAV-EzPqEH3cz_5hq?usp=sharing) for exporting and using ONNX model.
+
+2023/06/23: Play with HQ-SAM demo at [![Huggingfaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/sam-hq-team/sam-hq), which supports point, box and text prompts.
+
+2023/06/14: We released the [colab demo](https://colab.research.google.com/drive/1QwAbn5hsdqKOD5niuBzuqQX4eLCbNKFL?usp=sharing) <a href="https://colab.research.google.com/drive/1QwAbn5hsdqKOD5niuBzuqQX4eLCbNKFL?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> and [automatic mask generator notebook](https://colab.research.google.com/drive/1dhRq4eR6Fbl-yl1vbQvU9hqyyeOidQaU?usp=sharing).
+
+2023/06/13: We released the [model checkpoints](#model-checkpoints) and [demo visualization codes](#getting-started).
+
+Visual comparison between SAM and HQ-SAM
+-----------------
+**SAM vs. HQ-SAM**
+<table>
+  <tr>
+    <td><img src="visual_demo/1.gif" width="250"></td>
+    <td><img src="visual_demo/2.gif" width="250"></td>
+    <td><img src="visual_demo/3.gif" width="250"></td>
+  </tr>
+  <tr>
+    <td><img src="visual_demo/4.gif" width="250"></td>
+    <td><img src="visual_demo/5.gif" width="250"></td>
+    <td><img src="visual_demo/6.gif" width="250"></td>
+  </tr>
+</table>
+
+<img width="900" alt="image" src='figs/coco_vis_comp.png'>
+
+Introduction
+-----------------
+The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being trained with 1.1 billion masks, SAM's mask prediction quality falls short in many cases, particularly when dealing with objects that have intricate structures. We propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability. Our careful design reuses and preserves the pre-trained model weights of SAM, while only introducing minimal additional parameters and computation. We design a learnable High-Quality Output Token, which is injected into SAM's mask decoder and is responsible for predicting the high-quality mask. Instead of only applying it on mask-decoder features, we first fuse them with early and final ViT features for improved mask details. To train our introduced learnable parameters, we compose a dataset of 44K fine-grained masks from several sources. HQ-SAM is only trained on the introduced detaset of 44k masks, which takes only 4 hours on 8 GPUs. We show the efficacy of HQ-SAM in a suite of 9 diverse segmentation datasets across different downstream tasks, where 7 out of them are evaluated in a zero-shot transfer protocol. 
+
+<img width="1096" alt="image" src='figs/sam-hf-framework.png'>
+
+Quantitative comparison between SAM and HQ-SAM
+-----------------
+Note: For box-prompting-based evaluation, we feed SAM, MobileSAM and our HQ-SAM with the same image/video bounding boxes and adopt the single mask output mode of SAM. 
+
+We provide comprehensive performance, model size and speed comparison on SAM variants:
+<img width="1096" alt="image" src='figs/sam_variants_comp.png'>
+
+### Various ViT backbones on COCO:
+![backbones](figs/sam_vs_hqsam_backbones.png)
+Note: For the COCO dataset, we use a SOTA detector FocalNet-DINO trained on the COCO dataset as our box prompt generator.
+
+### YTVIS and HQ-YTVIS
+Note:Using ViT-L backbone. We adopt the SOTA detector Mask2Former trained on the YouTubeVIS 2019 dataset as our video boxes prompt generator while reusing its object association prediction.
+![ytvis](figs/ytvis.png)
+
+### DAVIS
+Note: Using ViT-L backbone. We adopt the SOTA model XMem as our video boxes prompt generator while reusing its object association prediction.
+![davis](figs/davis.png)
+
+### **Quick Installation via pip**
+```
+pip install segment-anything-hq
+python
+from segment_anything_hq import sam_model_registry
+model_type = "<model_type>" #"vit_l/vit_b/vit_h/vit_tiny"
+sam_checkpoint = "<path/to/checkpoint>"
+sam = sam_model_registry[model_type](checkpoint=sam_checkpoint)
+```
+
+see specific usage example (such as vit-l) by running belowing command:
+```
+export PYTHONPATH=$(pwd)
+python demo/demo_hqsam_pip_example.py
+```
+
+
+### **Standard Installation**
+The code requires `python>=3.8`, as well as `pytorch>=1.7` and `torchvision>=0.8`. Please follow the instructions [here](https://pytorch.org/get-started/locally/) to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.
+
+Clone the repository locally and install with
+
+```
+git clone https://github.com/SysCV/sam-hq.git
+cd sam-hq; pip install -e .
+```
+
+The following optional dependencies are necessary for mask post-processing, saving masks in COCO format, the example notebooks, and exporting the model in ONNX format. `jupyter` is also required to run the example notebooks.
+
+```
+pip install opencv-python pycocotools matplotlib onnxruntime onnx timm
+```
+
+### Example conda environment setup
+```bash
+conda create --name sam_hq python=3.8 -y
+conda activate sam_hq
+conda install pytorch==1.10.0 torchvision==0.11.0 cudatoolkit=11.1 -c pytorch -c nvidia
+pip install opencv-python pycocotools matplotlib onnxruntime onnx timm
+
+# under your working directory
+git clone https://github.com/SysCV/sam-hq.git
+cd sam-hq
+pip install -e .
+export PYTHONPATH=$(pwd)
+```
+
+### **Model Checkpoints**
+
+Three HQ-SAM model versions of the model are available with different backbone sizes. These models can be instantiated by running
+
+```
+from segment_anything import sam_model_registry
+sam = sam_model_registry["<model_type>"](checkpoint="<path/to/checkpoint>")
+```
+
+Download the provided trained model below and put them into the pretrained_checkpoint folder:
+```
+mkdir pretrained_checkpoint
+``` 
+
+Click the links below to download the checkpoint for the corresponding model type. We also provide **alternative model downloading links** [here](https://github.com/SysCV/sam-hq/issues/5) or at [hugging face](https://huggingface.co/lkeab/hq-sam/tree/main).
+- `vit_b`: [ViT-B HQ-SAM model.](https://drive.google.com/file/d/11yExZLOve38kRZPfRx_MRxfIAKmfMY47/view?usp=sharing)
+- `vit_l`: [ViT-L HQ-SAM model.](https://drive.google.com/file/d/1Uk17tDKX1YAKas5knI4y9ZJCo0lRVL0G/view?usp=sharing)
+- `vit_h`: [ViT-H HQ-SAM model.](https://drive.google.com/file/d/1qobFYrI4eyIANfBSmYcGuWRaSIXfMOQ8/view?usp=sharing)
+- `vit_tiny` (**Light HQ-SAM** for real-time need): [ViT-Tiny HQ-SAM model.](https://huggingface.co/lkeab/hq-sam/resolve/main/sam_hq_vit_tiny.pth)
+
+### **Getting Started**
+
+First download a [model checkpoint](#model-checkpoints). Then the model can be used in just a few lines to get masks from a given prompt:
+
+```
+from segment_anything import SamPredictor, sam_model_registry
+sam = sam_model_registry["<model_type>"](checkpoint="<path/to/checkpoint>")
+predictor = SamPredictor(sam)
+predictor.set_image(<your_image>)
+masks, _, _ = predictor.predict(<input_prompts>)
+```
+
+Additionally, see the usage examples in our [demo](/demo/demo_hqsam.py) , [colab notebook](https://colab.research.google.com/drive/1QwAbn5hsdqKOD5niuBzuqQX4eLCbNKFL?usp=sharing) and [automatic mask generator notebook](https://colab.research.google.com/drive/1dhRq4eR6Fbl-yl1vbQvU9hqyyeOidQaU?usp=sharing).
+
+To obtain HQ-SAM's visual result:
+```
+python demo/demo_hqsam.py
+```
+
+To obtain baseline SAM's visual result. Note that you need to download original SAM checkpoint from [baseline-SAM-L model](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth) and put it into the pretrained_checkpoint folder.
+```
+python demo/demo_sam.py
+```
+
+To obtain Light HQ-SAM's visual result:
+```
+python demo/demo_hqsam_light.py
+```
+
+### **HQ-SAM Tuning and HQ-Seg44k Data**
+We provide detailed training, evaluation, visualization and data downloading instructions in [HQ-SAM training](train/README.md). You can also replace our training data to obtain your own SAM in specific application domain (like medical, OCR and remote sensing).
+
+Please change the current folder path to:
+```
+cd train
+```
+and then refer to detailed [readme instruction](train/README.md).
+
+### **Grounded HQ-SAM vs Grounded SAM on [SegInW](https://eval.ai/web/challenges/challenge-page/1931/overview?ref=blog.roboflow.com)**
+
+Grounded HQ-SAM wins the **first place**:1st_place_medal: on SegInW benchmark (consist of 25 public zero-shot in the wild segmentation datasets), and outpuerforming Grounded SAM using the same grounding-dino detector.
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Model Name</th>
+<th valign="bottom">Encoder</th>
+<th valign="bottom">GroundingDINO</th>
+<th valign="bottom">Mean AP</th>
+<th valign="bottom">Evaluation Script</th>
+<th valign="bottom">Log</th>
+<th valign="bottom">Output Json</th>
+<!-- TABLE BODY -->
+<!-- ROW: maskformer2_R50_bs16_50ep -->
+ <tr><td align="left">Grounded SAM</td>
+<td align="center">vit-h</td>
+<td align="center">swin-b</td>
+<td align="center">48.7</td>
+<td align="center"><a href="seginw/test_seginw.sh">script</a></td>
+<td align="center"><a href="seginw/logs/grounded_sam.log">log</a></td>
+<td align="center"><a href="https://huggingface.co/sam-hq-team/SegInW/resolve/main/result/grounded_sam.zip">result</a></td>
+</tr>
+<!-- ROW: maskformer2_R101_bs16_50ep -->
+ <tr><td align="left">Grounded HQ-SAM</td>
+<td align="center">vit-h</td>
+<td align="center">swin-b</td>
+<td align="center"><b>49.6</b></td>
+<td align="center"><a href="seginw/test_seginw_hq.sh">script</a></td>
+<td align="center"><a href="seginw/logs/grounded_hqsam.log">log</a></td>
+<td align="center"><a href="https://huggingface.co/sam-hq-team/SegInW/resolve/main/result/grounded_hqsam.zip">result</a></td>
+</tr>
+</tbody></table>
+
+Please change the current folder path to:
+```
+cd seginw
+```
+We provide detailed evaluation instructions and metrics on SegInW in [Grounded-HQ-SAM evaluation](seginw/README.md).
+
+### **Light HQ-SAM vs MobileSAM on COCO**
+We propose [Light HQ-SAM](#model-checkpoints) based on the tiny vit image encoder provided by MobileSAM. We provide quantitative comparison on zero-shot COCO performance, speed and memory below. Try Light HQ-SAM at [here](#getting-started).
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Model</th>
+<th valign="bottom">Encoder</th>
+<th valign="bottom">AP</th>
+<th valign="bottom">AP@L</th>
+<th valign="bottom">AP@M</th>
+<th valign="bottom">AP@S</th>
+<th valign="bottom">Model Params (MB)</th>
+<th valign="bottom">FPS</th>
+<th valign="bottom">Memory (GB)</th>
+<!-- TABLE BODY -->
+<!-- ROW: maskformer2_R50_bs16_50ep -->
+ <tr><td align="left">MobileSAM</td>
+<td align="center">TinyViT</td>
+<td align="center">44.3</td>
+<td align="center">61.8</td>
+<td align="center">48.1</td>
+<td align="center">28.8</td>
+<td align="center">38.6</td>
+<td align="center">44.8</td>
+<td align="center">3.7</td>
+</tr>
+<!-- ROW: maskformer2_R101_bs16_50ep -->
+ <tr><td align="left"><b>Light HQ-SAM</b></td>
+ <td align="center">TinyViT</td>
+<td align="center"><b>45.0</b></td>
+<td align="center">62.8</td>
+<td align="center">48.8</td>
+<td align="center">29.2</td>
+<td align="center">40.3</td>
+<td align="center">41.2</td>
+<td align="center">3.7</td>
+</tr>
+</tbody></table>
+
+Note: For the COCO dataset, we use the same SOTA detector FocalNet-DINO trained on the COCO dataset as our and Mobile sam's box prompt generator.
+
+
+### **ONNX export**
+HQ-SAM's lightweight mask decoder can be exported to ONNX format so that it can be run in any environment that supports ONNX runtime. Export the model with
+```
+python scripts/export_onnx_model.py --checkpoint <path/to/checkpoint> --model-type <model_type> --output <path/to/output>
+```
+See the [example notebook](https://colab.research.google.com/drive/11U2La49c2IxahzJkAV-EzPqEH3cz_5hq?usp=sharing) for details on how to combine image preprocessing via HQ-SAM's backbone with mask prediction using the ONNX model. It is recommended to use the latest stable version of PyTorch for ONNX export.
+
+
+Citation
+---------------
+If you find HQ-SAM useful in your research or refer to the provided baseline results, please star :star: this repository and consider citing :pencil::
+```
+@inproceedings{sam_hq,
+    title={Segment Anything in High Quality},
+    author={Ke, Lei and Ye, Mingqiao and Danelljan, Martin and Liu, Yifan and Tai, Yu-Wing and Tang, Chi-Keung and Yu, Fisher},
+    booktitle={NeurIPS},
+    year={2023}
+}  
+```
+Related high-quality instance segmentation work:
+```
+@inproceedings{transfiner,
+    title={Mask Transfiner for High-Quality Instance Segmentation},
+    author={Ke, Lei and Danelljan, Martin and Li, Xia and Tai, Yu-Wing and Tang, Chi-Keung and Yu, Fisher},
+    booktitle={CVPR},
+    year={2022}
+}
+```
+
+## Acknowledgments
+- Thanks [SAM](https://github.com/facebookresearch/segment-anything), [Grounded SAM](https://github.com/IDEA-Research/Grounded-Segment-Anything) and [MobileSAM](https://github.com/ChaoningZhang/MobileSAM) for their public code and released models.

sam2.1HQ/sam-hq-main/build/lib/segment_anything/__init__.py

@@ -0,0 +1,16 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+from .build_sam import (
+    build_sam,
+    build_sam_vit_h,
+    build_sam_vit_l,
+    build_sam_vit_b,
+    sam_model_registry,
+)
+from .build_sam_baseline import sam_model_registry_baseline
+from .predictor import SamPredictor
+from .automatic_mask_generator import SamAutomaticMaskGenerator

sam2.1HQ/sam-hq-main/build/lib/segment_anything/automatic_mask_generator.py

@@ -0,0 +1,374 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import numpy as np
+import torch
+from torchvision.ops.boxes import batched_nms, box_area  # type: ignore
+
+from typing import Any, Dict, List, Optional, Tuple
+
+from .modeling import Sam
+from .predictor import SamPredictor
+from .utils.amg import (
+    MaskData,
+    area_from_rle,
+    batch_iterator,
+    batched_mask_to_box,
+    box_xyxy_to_xywh,
+    build_all_layer_point_grids,
+    calculate_stability_score,
+    coco_encode_rle,
+    generate_crop_boxes,
+    is_box_near_crop_edge,
+    mask_to_rle_pytorch,
+    remove_small_regions,
+    rle_to_mask,
+    uncrop_boxes_xyxy,
+    uncrop_masks,
+    uncrop_points,
+)
+
+
+class SamAutomaticMaskGenerator:
+    def __init__(
+        self,
+        model: Sam,
+        points_per_side: Optional[int] = 32,
+        points_per_batch: int = 64,
+        pred_iou_thresh: float = 0.88,
+        stability_score_thresh: float = 0.95,
+        stability_score_offset: float = 1.0,
+        box_nms_thresh: float = 0.7,
+        crop_n_layers: int = 0,
+        crop_nms_thresh: float = 0.7,
+        crop_overlap_ratio: float = 512 / 1500,
+        crop_n_points_downscale_factor: int = 1,
+        point_grids: Optional[List[np.ndarray]] = None,
+        min_mask_region_area: int = 0,
+        output_mode: str = "binary_mask",
+    ) -> None:
+        """
+        Using a SAM model, generates masks for the entire image.
+        Generates a grid of point prompts over the image, then filters
+        low quality and duplicate masks. The default settings are chosen
+        for SAM with a ViT-H backbone.
+
+        Arguments:
+          model (Sam): The SAM model to use for mask prediction.
+          points_per_side (int or None): The number of points to be sampled
+            along one side of the image. The total number of points is
+            points_per_side**2. If None, 'point_grids' must provide explicit
+            point sampling.
+          points_per_batch (int): Sets the number of points run simultaneously
+            by the model. Higher numbers may be faster but use more GPU memory.
+          pred_iou_thresh (float): A filtering threshold in [0,1], using the
+            model's predicted mask quality.
+          stability_score_thresh (float): A filtering threshold in [0,1], using
+            the stability of the mask under changes to the cutoff used to binarize
+            the model's mask predictions.
+          stability_score_offset (float): The amount to shift the cutoff when
+            calculated the stability score.
+          box_nms_thresh (float): The box IoU cutoff used by non-maximal
+            suppression to filter duplicate masks.
+          crop_n_layers (int): If >0, mask prediction will be run again on
+            crops of the image. Sets the number of layers to run, where each
+            layer has 2**i_layer number of image crops.
+          crop_nms_thresh (float): The box IoU cutoff used by non-maximal
+            suppression to filter duplicate masks between different crops.
+          crop_overlap_ratio (float): Sets the degree to which crops overlap.
+            In the first crop layer, crops will overlap by this fraction of
+            the image length. Later layers with more crops scale down this overlap.
+          crop_n_points_downscale_factor (int): The number of points-per-side
+            sampled in layer n is scaled down by crop_n_points_downscale_factor**n.
+          point_grids (list(np.ndarray) or None): A list over explicit grids
+            of points used for sampling, normalized to [0,1]. The nth grid in the
+            list is used in the nth crop layer. Exclusive with points_per_side.
+          min_mask_region_area (int): If >0, postprocessing will be applied
+            to remove disconnected regions and holes in masks with area smaller
+            than min_mask_region_area. Requires opencv.
+          output_mode (str): The form masks are returned in. Can be 'binary_mask',
+            'uncompressed_rle', or 'coco_rle'. 'coco_rle' requires pycocotools.
+            For large resolutions, 'binary_mask' may consume large amounts of
+            memory.
+        """
+
+        assert (points_per_side is None) != (
+            point_grids is None
+        ), "Exactly one of points_per_side or point_grid must be provided."
+        if points_per_side is not None:
+            self.point_grids = build_all_layer_point_grids(
+                points_per_side,
+                crop_n_layers,
+                crop_n_points_downscale_factor,
+            )
+        elif point_grids is not None:
+            self.point_grids = point_grids
+        else:
+            raise ValueError("Can't have both points_per_side and point_grid be None.")
+
+        assert output_mode in [
+            "binary_mask",
+            "uncompressed_rle",
+            "coco_rle",
+        ], f"Unknown output_mode {output_mode}."
+        if output_mode == "coco_rle":
+            from pycocotools import mask as mask_utils  # type: ignore # noqa: F401
+
+        if min_mask_region_area > 0:
+            import cv2  # type: ignore # noqa: F401
+
+        self.predictor = SamPredictor(model)
+        self.points_per_batch = points_per_batch
+        self.pred_iou_thresh = pred_iou_thresh
+        self.stability_score_thresh = stability_score_thresh
+        self.stability_score_offset = stability_score_offset
+        self.box_nms_thresh = box_nms_thresh
+        self.crop_n_layers = crop_n_layers
+        self.crop_nms_thresh = crop_nms_thresh
+        self.crop_overlap_ratio = crop_overlap_ratio
+        self.crop_n_points_downscale_factor = crop_n_points_downscale_factor
+        self.min_mask_region_area = min_mask_region_area
+        self.output_mode = output_mode
+
+    @torch.no_grad()
+    def generate(self, image: np.ndarray, multimask_output: bool = True) -> List[Dict[str, Any]]:
+        """
+        Generates masks for the given image.
+
+        Arguments:
+          image (np.ndarray): The image to generate masks for, in HWC uint8 format.
+
+        Returns:
+           list(dict(str, any)): A list over records for masks. Each record is
+             a dict containing the following keys:
+               segmentation (dict(str, any) or np.ndarray): The mask. If
+                 output_mode='binary_mask', is an array of shape HW. Otherwise,
+                 is a dictionary containing the RLE.
+               bbox (list(float)): The box around the mask, in XYWH format.
+               area (int): The area in pixels of the mask.
+               predicted_iou (float): The model's own prediction of the mask's
+                 quality. This is filtered by the pred_iou_thresh parameter.
+               point_coords (list(list(float))): The point coordinates input
+                 to the model to generate this mask.
+               stability_score (float): A measure of the mask's quality. This
+                 is filtered on using the stability_score_thresh parameter.
+               crop_box (list(float)): The crop of the image used to generate
+                 the mask, given in XYWH format.
+        """
+
+        # Generate masks
+        mask_data = self._generate_masks(image, multimask_output)
+
+        # Filter small disconnected regions and holes in masks
+        if self.min_mask_region_area > 0:
+            mask_data = self.postprocess_small_regions(
+                mask_data,
+                self.min_mask_region_area,
+                max(self.box_nms_thresh, self.crop_nms_thresh),
+            )
+
+        # Encode masks
+        if self.output_mode == "coco_rle":
+            mask_data["segmentations"] = [coco_encode_rle(rle) for rle in mask_data["rles"]]
+        elif self.output_mode == "binary_mask":
+            mask_data["segmentations"] = [rle_to_mask(rle) for rle in mask_data["rles"]]
+        else:
+            mask_data["segmentations"] = mask_data["rles"]
+
+        # Write mask records
+        curr_anns = []
+        for idx in range(len(mask_data["segmentations"])):
+            ann = {
+                "segmentation": mask_data["segmentations"][idx],
+                "area": area_from_rle(mask_data["rles"][idx]),
+                "bbox": box_xyxy_to_xywh(mask_data["boxes"][idx]).tolist(),
+                "predicted_iou": mask_data["iou_preds"][idx].item(),
+                "point_coords": [mask_data["points"][idx].tolist()],
+                "stability_score": mask_data["stability_score"][idx].item(),
+                "crop_box": box_xyxy_to_xywh(mask_data["crop_boxes"][idx]).tolist(),
+            }
+            curr_anns.append(ann)
+
+        return curr_anns
+
+    def _generate_masks(self, image: np.ndarray, multimask_output: bool = True) -> MaskData:
+        orig_size = image.shape[:2]
+        crop_boxes, layer_idxs = generate_crop_boxes(
+            orig_size, self.crop_n_layers, self.crop_overlap_ratio
+        )
+
+        # Iterate over image crops
+        data = MaskData()
+        for crop_box, layer_idx in zip(crop_boxes, layer_idxs):
+            crop_data = self._process_crop(image, crop_box, layer_idx, orig_size, multimask_output)
+            data.cat(crop_data)
+
+        # Remove duplicate masks between crops
+        if len(crop_boxes) > 1:
+            # Prefer masks from smaller crops
+            scores = 1 / box_area(data["crop_boxes"])
+            scores = scores.to(data["boxes"].device)
+            keep_by_nms = batched_nms(
+                data["boxes"].float(),
+                scores,
+                torch.zeros_like(data["boxes"][:, 0]),  # categories
+                iou_threshold=self.crop_nms_thresh,
+            )
+            data.filter(keep_by_nms)
+
+        data.to_numpy()
+        return data
+
+    def _process_crop(
+        self,
+        image: np.ndarray,
+        crop_box: List[int],
+        crop_layer_idx: int,
+        orig_size: Tuple[int, ...],
+        multimask_output: bool = True,
+    ) -> MaskData:
+        # Crop the image and calculate embeddings
+        x0, y0, x1, y1 = crop_box
+        cropped_im = image[y0:y1, x0:x1, :]
+        cropped_im_size = cropped_im.shape[:2]
+        self.predictor.set_image(cropped_im)
+
+        # Get points for this crop
+        points_scale = np.array(cropped_im_size)[None, ::-1]
+        points_for_image = self.point_grids[crop_layer_idx] * points_scale
+
+        # Generate masks for this crop in batches
+        data = MaskData()
+        for (points,) in batch_iterator(self.points_per_batch, points_for_image):
+            batch_data = self._process_batch(points, cropped_im_size, crop_box, orig_size, multimask_output)
+            data.cat(batch_data)
+            del batch_data
+        self.predictor.reset_image()
+
+        # Remove duplicates within this crop.
+        keep_by_nms = batched_nms(
+            data["boxes"].float(),
+            data["iou_preds"],
+            torch.zeros_like(data["boxes"][:, 0]),  # categories
+            iou_threshold=self.box_nms_thresh,
+        )
+        data.filter(keep_by_nms)
+
+        # Return to the original image frame
+        data["boxes"] = uncrop_boxes_xyxy(data["boxes"], crop_box)
+        data["points"] = uncrop_points(data["points"], crop_box)
+        data["crop_boxes"] = torch.tensor([crop_box for _ in range(len(data["rles"]))])
+
+        return data
+
+    def _process_batch(
+        self,
+        points: np.ndarray,
+        im_size: Tuple[int, ...],
+        crop_box: List[int],
+        orig_size: Tuple[int, ...],
+        multimask_output: bool = True,
+    ) -> MaskData:
+        orig_h, orig_w = orig_size
+
+        # Run model on this batch
+        transformed_points = self.predictor.transform.apply_coords(points, im_size)
+        in_points = torch.as_tensor(transformed_points, device=self.predictor.device)
+        in_labels = torch.ones(in_points.shape[0], dtype=torch.int, device=in_points.device)
+        masks, iou_preds, _ = self.predictor.predict_torch(
+            in_points[:, None, :],
+            in_labels[:, None],
+            multimask_output=multimask_output,
+            return_logits=True,
+        )
+
+        # Serialize predictions and store in MaskData
+        data = MaskData(
+            masks=masks.flatten(0, 1),
+            iou_preds=iou_preds.flatten(0, 1),
+            points=torch.as_tensor(points.repeat(masks.shape[1], axis=0)),
+        )
+        del masks
+
+        # Filter by predicted IoU
+        if self.pred_iou_thresh > 0.0:
+            keep_mask = data["iou_preds"] > self.pred_iou_thresh
+            data.filter(keep_mask)
+
+        # Calculate stability score
+        data["stability_score"] = calculate_stability_score(
+            data["masks"], self.predictor.model.mask_threshold, self.stability_score_offset
+        )
+        if self.stability_score_thresh > 0.0:
+            keep_mask = data["stability_score"] >= self.stability_score_thresh
+            data.filter(keep_mask)
+
+        # Threshold masks and calculate boxes
+        data["masks"] = data["masks"] > self.predictor.model.mask_threshold
+        data["boxes"] = batched_mask_to_box(data["masks"])
+
+        # Filter boxes that touch crop boundaries
+        keep_mask = ~is_box_near_crop_edge(data["boxes"], crop_box, [0, 0, orig_w, orig_h])
+        if not torch.all(keep_mask):
+            data.filter(keep_mask)
+
+        # Compress to RLE
+        data["masks"] = uncrop_masks(data["masks"], crop_box, orig_h, orig_w)
+        data["rles"] = mask_to_rle_pytorch(data["masks"])
+        del data["masks"]
+
+        return data
+
+    @staticmethod
+    def postprocess_small_regions(
+        mask_data: MaskData, min_area: int, nms_thresh: float
+    ) -> MaskData:
+        """
+        Removes small disconnected regions and holes in masks, then reruns
+        box NMS to remove any new duplicates.
+
+        Edits mask_data in place.
+
+        Requires open-cv as a dependency.
+        """
+        if len(mask_data["rles"]) == 0:
+            return mask_data
+
+        # Filter small disconnected regions and holes
+        new_masks = []
+        scores = []
+        for rle in mask_data["rles"]:
+            mask = rle_to_mask(rle)
+
+            mask, changed = remove_small_regions(mask, min_area, mode="holes")
+            unchanged = not changed
+            mask, changed = remove_small_regions(mask, min_area, mode="islands")
+            unchanged = unchanged and not changed
+
+            new_masks.append(torch.as_tensor(mask).unsqueeze(0))
+            # Give score=0 to changed masks and score=1 to unchanged masks
+            # so NMS will prefer ones that didn't need postprocessing
+            scores.append(float(unchanged))
+
+        # Recalculate boxes and remove any new duplicates
+        masks = torch.cat(new_masks, dim=0)
+        boxes = batched_mask_to_box(masks)
+        keep_by_nms = batched_nms(
+            boxes.float(),
+            torch.as_tensor(scores),
+            torch.zeros_like(boxes[:, 0]),  # categories
+            iou_threshold=nms_thresh,
+        )
+
+        # Only recalculate RLEs for masks that have changed
+        for i_mask in keep_by_nms:
+            if scores[i_mask] == 0.0:
+                mask_torch = masks[i_mask].unsqueeze(0)
+                mask_data["rles"][i_mask] = mask_to_rle_pytorch(mask_torch)[0]
+                mask_data["boxes"][i_mask] = boxes[i_mask]  # update res directly
+        mask_data.filter(keep_by_nms)
+
+        return mask_data

sam2.1HQ/sam-hq-main/build/lib/segment_anything/build_sam.py

@@ -0,0 +1,169 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+
+from functools import partial
+
+from .modeling import ImageEncoderViT, MaskDecoderHQ, PromptEncoder, Sam, TwoWayTransformer, TinyViT
+
+
+def build_sam_vit_h(checkpoint=None):
+    return _build_sam(
+        encoder_embed_dim=1280,
+        encoder_depth=32,
+        encoder_num_heads=16,
+        encoder_global_attn_indexes=[7, 15, 23, 31],
+        checkpoint=checkpoint,
+    )
+
+
+build_sam = build_sam_vit_h
+
+
+def build_sam_vit_l(checkpoint=None):
+    return _build_sam(
+        encoder_embed_dim=1024,
+        encoder_depth=24,
+        encoder_num_heads=16,
+        encoder_global_attn_indexes=[5, 11, 17, 23],
+        checkpoint=checkpoint,
+    )
+
+
+def build_sam_vit_b(checkpoint=None):
+    return _build_sam(
+        encoder_embed_dim=768,
+        encoder_depth=12,
+        encoder_num_heads=12,
+        encoder_global_attn_indexes=[2, 5, 8, 11],
+        checkpoint=checkpoint,
+    )
+
+
+def build_sam_vit_t(checkpoint=None):
+    prompt_embed_dim = 256
+    image_size = 1024
+    vit_patch_size = 16
+    image_embedding_size = image_size // vit_patch_size
+    mobile_sam = Sam(
+            image_encoder=TinyViT(img_size=1024, in_chans=3, num_classes=1000,
+                embed_dims=[64, 128, 160, 320],
+                depths=[2, 2, 6, 2],
+                num_heads=[2, 4, 5, 10],
+                window_sizes=[7, 7, 14, 7],
+                mlp_ratio=4.,
+                drop_rate=0.,
+                drop_path_rate=0.0,
+                use_checkpoint=False,
+                mbconv_expand_ratio=4.0,
+                local_conv_size=3,
+                layer_lr_decay=0.8
+            ),
+            prompt_encoder=PromptEncoder(
+            embed_dim=prompt_embed_dim,
+            image_embedding_size=(image_embedding_size, image_embedding_size),
+            input_image_size=(image_size, image_size),
+            mask_in_chans=16,
+            ),
+            mask_decoder=MaskDecoderHQ(
+                    num_multimask_outputs=3,
+                    transformer=TwoWayTransformer(
+                    depth=2,
+                    embedding_dim=prompt_embed_dim,
+                    mlp_dim=2048,
+                    num_heads=8,
+                ),
+                transformer_dim=prompt_embed_dim,
+                iou_head_depth=3,
+                iou_head_hidden_dim=256,
+                vit_dim=160,
+            ),
+            pixel_mean=[123.675, 116.28, 103.53],
+            pixel_std=[58.395, 57.12, 57.375],
+        )
+
+    mobile_sam.eval()
+    if checkpoint is not None:
+        with open(checkpoint, "rb") as f:
+            device = "cuda" if torch.cuda.is_available() else "cpu"
+            state_dict = torch.load(f, map_location=device)
+        info = mobile_sam.load_state_dict(state_dict, strict=False)
+        print(info)
+    for n, p in mobile_sam.named_parameters():
+        if 'hf_token' not in n and 'hf_mlp' not in n and 'compress_vit_feat' not in n and 'embedding_encoder' not in n and 'embedding_maskfeature' not in n:
+            p.requires_grad = False
+    return mobile_sam
+
+sam_model_registry = {
+    "default": build_sam_vit_h,
+    "vit_h": build_sam_vit_h,
+    "vit_l": build_sam_vit_l,
+    "vit_b": build_sam_vit_b,
+    "vit_tiny": build_sam_vit_t
+}
+
+
+def _build_sam(
+    encoder_embed_dim,
+    encoder_depth,
+    encoder_num_heads,
+    encoder_global_attn_indexes,
+    checkpoint=None,
+):
+    prompt_embed_dim = 256
+    image_size = 1024
+    vit_patch_size = 16
+    image_embedding_size = image_size // vit_patch_size
+    sam = Sam(
+        image_encoder=ImageEncoderViT(
+            depth=encoder_depth,
+            embed_dim=encoder_embed_dim,
+            img_size=image_size,
+            mlp_ratio=4,
+            norm_layer=partial(torch.nn.LayerNorm, eps=1e-6),
+            num_heads=encoder_num_heads,
+            patch_size=vit_patch_size,
+            qkv_bias=True,
+            use_rel_pos=True,
+            global_attn_indexes=encoder_global_attn_indexes,
+            window_size=14,
+            out_chans=prompt_embed_dim,
+        ),
+        prompt_encoder=PromptEncoder(
+            embed_dim=prompt_embed_dim,
+            image_embedding_size=(image_embedding_size, image_embedding_size),
+            input_image_size=(image_size, image_size),
+            mask_in_chans=16,
+        ),
+        mask_decoder=MaskDecoderHQ(
+            num_multimask_outputs=3,
+            transformer=TwoWayTransformer(
+                depth=2,
+                embedding_dim=prompt_embed_dim,
+                mlp_dim=2048,
+                num_heads=8,
+            ),
+            transformer_dim=prompt_embed_dim,
+            iou_head_depth=3,
+            iou_head_hidden_dim=256,
+            vit_dim=encoder_embed_dim,
+        ),
+        pixel_mean=[123.675, 116.28, 103.53],
+        pixel_std=[58.395, 57.12, 57.375],
+    )
+    sam.eval()
+    if checkpoint is not None:
+        with open(checkpoint, "rb") as f:
+            device = "cuda" if torch.cuda.is_available() else "cpu"
+            state_dict = torch.load(f, map_location=device)
+        info = sam.load_state_dict(state_dict, strict=False)
+        print(info)
+    for n, p in sam.named_parameters():
+        if 'hf_token' not in n and 'hf_mlp' not in n and 'compress_vit_feat' not in n and 'embedding_encoder' not in n and 'embedding_maskfeature' not in n:
+            p.requires_grad = False
+
+    return sam

sam2.1HQ/sam-hq-main/build/lib/segment_anything/build_sam_baseline.py

@@ -0,0 +1,156 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+
+from functools import partial
+
+from .modeling import ImageEncoderViT, MaskDecoder, PromptEncoder, Sam, TwoWayTransformer, TinyViT
+
+
+def build_sam_vit_h(checkpoint=None):
+    return _build_sam(
+        encoder_embed_dim=1280,
+        encoder_depth=32,
+        encoder_num_heads=16,
+        encoder_global_attn_indexes=[7, 15, 23, 31],
+        checkpoint=checkpoint,
+    )
+
+
+build_sam = build_sam_vit_h
+
+
+def build_sam_vit_l(checkpoint=None):
+    return _build_sam(
+        encoder_embed_dim=1024,
+        encoder_depth=24,
+        encoder_num_heads=16,
+        encoder_global_attn_indexes=[5, 11, 17, 23],
+        checkpoint=checkpoint,
+    )
+
+
+def build_sam_vit_b(checkpoint=None):
+    return _build_sam(
+        encoder_embed_dim=768,
+        encoder_depth=12,
+        encoder_num_heads=12,
+        encoder_global_attn_indexes=[2, 5, 8, 11],
+        checkpoint=checkpoint,
+    )
+
+
+def build_sam_vit_t(checkpoint=None):
+    prompt_embed_dim = 256
+    image_size = 1024
+    vit_patch_size = 16
+    image_embedding_size = image_size // vit_patch_size
+    mobile_sam = Sam(
+            image_encoder=TinyViT(img_size=1024, in_chans=3, num_classes=1000,
+                embed_dims=[64, 128, 160, 320],
+                depths=[2, 2, 6, 2],
+                num_heads=[2, 4, 5, 10],
+                window_sizes=[7, 7, 14, 7],
+                mlp_ratio=4.,
+                drop_rate=0.,
+                drop_path_rate=0.0,
+                use_checkpoint=False,
+                mbconv_expand_ratio=4.0,
+                local_conv_size=3,
+                layer_lr_decay=0.8
+            ),
+            prompt_encoder=PromptEncoder(
+            embed_dim=prompt_embed_dim,
+            image_embedding_size=(image_embedding_size, image_embedding_size),
+            input_image_size=(image_size, image_size),
+            mask_in_chans=16,
+            ),
+            mask_decoder=MaskDecoder(
+                    num_multimask_outputs=3,
+                    transformer=TwoWayTransformer(
+                    depth=2,
+                    embedding_dim=prompt_embed_dim,
+                    mlp_dim=2048,
+                    num_heads=8,
+                ),
+                transformer_dim=prompt_embed_dim,
+                iou_head_depth=3,
+                iou_head_hidden_dim=256,
+            ),
+            pixel_mean=[123.675, 116.28, 103.53],
+            pixel_std=[58.395, 57.12, 57.375],
+        )
+
+    mobile_sam.eval()
+    if checkpoint is not None:
+        with open(checkpoint, "rb") as f:
+            state_dict = torch.load(f)
+        mobile_sam.load_state_dict(state_dict)
+    return mobile_sam
+
+sam_model_registry_baseline = {
+    "default": build_sam_vit_h,
+    "vit_h": build_sam_vit_h,
+    "vit_l": build_sam_vit_l,
+    "vit_b": build_sam_vit_b,
+    "vit_tiny": build_sam_vit_t
+}
+
+
+def _build_sam(
+    encoder_embed_dim,
+    encoder_depth,
+    encoder_num_heads,
+    encoder_global_attn_indexes,
+    checkpoint=None,
+):
+    prompt_embed_dim = 256
+    image_size = 1024
+    vit_patch_size = 16
+    image_embedding_size = image_size // vit_patch_size
+    sam = Sam(
+        image_encoder=ImageEncoderViT(
+            depth=encoder_depth,
+            embed_dim=encoder_embed_dim,
+            img_size=image_size,
+            mlp_ratio=4,
+            norm_layer=partial(torch.nn.LayerNorm, eps=1e-6),
+            num_heads=encoder_num_heads,
+            patch_size=vit_patch_size,
+            qkv_bias=True,
+            use_rel_pos=True,
+            global_attn_indexes=encoder_global_attn_indexes,
+            window_size=14,
+            out_chans=prompt_embed_dim,
+        ),
+        prompt_encoder=PromptEncoder(
+            embed_dim=prompt_embed_dim,
+            image_embedding_size=(image_embedding_size, image_embedding_size),
+            input_image_size=(image_size, image_size),
+            mask_in_chans=16,
+        ),
+        mask_decoder=MaskDecoder(
+            num_multimask_outputs=3,
+            transformer=TwoWayTransformer(
+                depth=2,
+                embedding_dim=prompt_embed_dim,
+                mlp_dim=2048,
+                num_heads=8,
+            ),
+            transformer_dim=prompt_embed_dim,
+            iou_head_depth=3,
+            iou_head_hidden_dim=256,
+        ),
+        pixel_mean=[123.675, 116.28, 103.53],
+        pixel_std=[58.395, 57.12, 57.375],
+    )
+    sam.eval()
+    if checkpoint is not None:
+        with open(checkpoint, "rb") as f:
+            state_dict = torch.load(f)
+        sam.load_state_dict(state_dict)
+    return sam

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/__init__.py

@@ -0,0 +1,13 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+from .sam import Sam
+from .image_encoder import ImageEncoderViT
+from .mask_decoder_hq import MaskDecoderHQ
+from .mask_decoder import MaskDecoder
+from .prompt_encoder import PromptEncoder
+from .transformer import TwoWayTransformer
+from .tiny_vit_sam import TinyViT

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/common.py

@@ -0,0 +1,43 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+import torch.nn as nn
+
+from typing import Type
+
+
+class MLPBlock(nn.Module):
+    def __init__(
+        self,
+        embedding_dim: int,
+        mlp_dim: int,
+        act: Type[nn.Module] = nn.GELU,
+    ) -> None:
+        super().__init__()
+        self.lin1 = nn.Linear(embedding_dim, mlp_dim)
+        self.lin2 = nn.Linear(mlp_dim, embedding_dim)
+        self.act = act()
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.lin2(self.act(self.lin1(x)))
+
+
+# From https://github.com/facebookresearch/detectron2/blob/main/detectron2/layers/batch_norm.py # noqa
+# Itself from https://github.com/facebookresearch/ConvNeXt/blob/d1fa8f6fef0a165b27399986cc2bdacc92777e40/models/convnext.py#L119  # noqa
+class LayerNorm2d(nn.Module):
+    def __init__(self, num_channels: int, eps: float = 1e-6) -> None:
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(num_channels))
+        self.bias = nn.Parameter(torch.zeros(num_channels))
+        self.eps = eps
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        u = x.mean(1, keepdim=True)
+        s = (x - u).pow(2).mean(1, keepdim=True)
+        x = (x - u) / torch.sqrt(s + self.eps)
+        x = self.weight[:, None, None] * x + self.bias[:, None, None]
+        return x

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/image_encoder.py

@@ -0,0 +1,398 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from typing import Optional, Tuple, Type
+
+from .common import LayerNorm2d, MLPBlock
+
+
+# This class and its supporting functions below lightly adapted from the ViTDet backbone available at: https://github.com/facebookresearch/detectron2/blob/main/detectron2/modeling/backbone/vit.py # noqa
+class ImageEncoderViT(nn.Module):
+    def __init__(
+        self,
+        img_size: int = 1024,
+        patch_size: int = 16,
+        in_chans: int = 3,
+        embed_dim: int = 768,
+        depth: int = 12,
+        num_heads: int = 12,
+        mlp_ratio: float = 4.0,
+        out_chans: int = 256,
+        qkv_bias: bool = True,
+        norm_layer: Type[nn.Module] = nn.LayerNorm,
+        act_layer: Type[nn.Module] = nn.GELU,
+        use_abs_pos: bool = True,
+        use_rel_pos: bool = False,
+        rel_pos_zero_init: bool = True,
+        window_size: int = 0,
+        global_attn_indexes: Tuple[int, ...] = (),
+    ) -> None:
+        """
+        Args:
+            img_size (int): Input image size.
+            patch_size (int): Patch size.
+            in_chans (int): Number of input image channels.
+            embed_dim (int): Patch embedding dimension.
+            depth (int): Depth of ViT.
+            num_heads (int): Number of attention heads in each ViT block.
+            mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
+            qkv_bias (bool): If True, add a learnable bias to query, key, value.
+            norm_layer (nn.Module): Normalization layer.
+            act_layer (nn.Module): Activation layer.
+            use_abs_pos (bool): If True, use absolute positional embeddings.
+            use_rel_pos (bool): If True, add relative positional embeddings to the attention map.
+            rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
+            window_size (int): Window size for window attention blocks.
+            global_attn_indexes (list): Indexes for blocks using global attention.
+        """
+        super().__init__()
+        self.img_size = img_size
+
+        self.patch_embed = PatchEmbed(
+            kernel_size=(patch_size, patch_size),
+            stride=(patch_size, patch_size),
+            in_chans=in_chans,
+            embed_dim=embed_dim,
+        )
+
+        self.pos_embed: Optional[nn.Parameter] = None
+        if use_abs_pos:
+            # Initialize absolute positional embedding with pretrain image size.
+            self.pos_embed = nn.Parameter(
+                torch.zeros(1, img_size // patch_size, img_size // patch_size, embed_dim)
+            )
+
+        self.blocks = nn.ModuleList()
+        for i in range(depth):
+            block = Block(
+                dim=embed_dim,
+                num_heads=num_heads,
+                mlp_ratio=mlp_ratio,
+                qkv_bias=qkv_bias,
+                norm_layer=norm_layer,
+                act_layer=act_layer,
+                use_rel_pos=use_rel_pos,
+                rel_pos_zero_init=rel_pos_zero_init,
+                window_size=window_size if i not in global_attn_indexes else 0,
+                input_size=(img_size // patch_size, img_size // patch_size),
+            )
+            self.blocks.append(block)
+
+        self.neck = nn.Sequential(
+            nn.Conv2d(
+                embed_dim,
+                out_chans,
+                kernel_size=1,
+                bias=False,
+            ),
+            LayerNorm2d(out_chans),
+            nn.Conv2d(
+                out_chans,
+                out_chans,
+                kernel_size=3,
+                padding=1,
+                bias=False,
+            ),
+            LayerNorm2d(out_chans),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = self.patch_embed(x)
+        if self.pos_embed is not None:
+            x = x + self.pos_embed
+
+        interm_embeddings=[]
+        for blk in self.blocks:
+            x = blk(x)
+            if blk.window_size == 0:
+                interm_embeddings.append(x)
+
+        x = self.neck(x.permute(0, 3, 1, 2))
+
+        return x, interm_embeddings
+
+
+class Block(nn.Module):
+    """Transformer blocks with support of window attention and residual propagation blocks"""
+
+    def __init__(
+        self,
+        dim: int,
+        num_heads: int,
+        mlp_ratio: float = 4.0,
+        qkv_bias: bool = True,
+        norm_layer: Type[nn.Module] = nn.LayerNorm,
+        act_layer: Type[nn.Module] = nn.GELU,
+        use_rel_pos: bool = False,
+        rel_pos_zero_init: bool = True,
+        window_size: int = 0,
+        input_size: Optional[Tuple[int, int]] = None,
+    ) -> None:
+        """
+        Args:
+            dim (int): Number of input channels.
+            num_heads (int): Number of attention heads in each ViT block.
+            mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
+            qkv_bias (bool): If True, add a learnable bias to query, key, value.
+            norm_layer (nn.Module): Normalization layer.
+            act_layer (nn.Module): Activation layer.
+            use_rel_pos (bool): If True, add relative positional embeddings to the attention map.
+            rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
+            window_size (int): Window size for window attention blocks. If it equals 0, then
+                use global attention.
+            input_size (tuple(int, int) or None): Input resolution for calculating the relative
+                positional parameter size.
+        """
+        super().__init__()
+        self.norm1 = norm_layer(dim)
+        self.attn = Attention(
+            dim,
+            num_heads=num_heads,
+            qkv_bias=qkv_bias,
+            use_rel_pos=use_rel_pos,
+            rel_pos_zero_init=rel_pos_zero_init,
+            input_size=input_size if window_size == 0 else (window_size, window_size),
+        )
+
+        self.norm2 = norm_layer(dim)
+        self.mlp = MLPBlock(embedding_dim=dim, mlp_dim=int(dim * mlp_ratio), act=act_layer)
+
+        self.window_size = window_size
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        shortcut = x
+        x = self.norm1(x)
+        # Window partition
+        if self.window_size > 0:
+            H, W = x.shape[1], x.shape[2]
+            x, pad_hw = window_partition(x, self.window_size)
+
+        x = self.attn(x)
+        # Reverse window partition
+        if self.window_size > 0:
+            x = window_unpartition(x, self.window_size, pad_hw, (H, W))
+
+        x = shortcut + x
+        x = x + self.mlp(self.norm2(x))
+
+        return x
+
+
+class Attention(nn.Module):
+    """Multi-head Attention block with relative position embeddings."""
+
+    def __init__(
+        self,
+        dim: int,
+        num_heads: int = 8,
+        qkv_bias: bool = True,
+        use_rel_pos: bool = False,
+        rel_pos_zero_init: bool = True,
+        input_size: Optional[Tuple[int, int]] = None,
+    ) -> None:
+        """
+        Args:
+            dim (int): Number of input channels.
+            num_heads (int): Number of attention heads.
+            qkv_bias (bool):  If True, add a learnable bias to query, key, value.
+            rel_pos (bool): If True, add relative positional embeddings to the attention map.
+            rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
+            input_size (tuple(int, int) or None): Input resolution for calculating the relative
+                positional parameter size.
+        """
+        super().__init__()
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = head_dim**-0.5
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.proj = nn.Linear(dim, dim)
+
+        self.use_rel_pos = use_rel_pos
+        if self.use_rel_pos:
+            assert (
+                input_size is not None
+            ), "Input size must be provided if using relative positional encoding."
+            # initialize relative positional embeddings
+            self.rel_pos_h = nn.Parameter(torch.zeros(2 * input_size[0] - 1, head_dim))
+            self.rel_pos_w = nn.Parameter(torch.zeros(2 * input_size[1] - 1, head_dim))
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        B, H, W, _ = x.shape
+        # qkv with shape (3, B, nHead, H * W, C)
+        qkv = self.qkv(x).reshape(B, H * W, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4)
+        # q, k, v with shape (B * nHead, H * W, C)
+        q, k, v = qkv.reshape(3, B * self.num_heads, H * W, -1).unbind(0)
+
+        attn = (q * self.scale) @ k.transpose(-2, -1)
+
+        if self.use_rel_pos:
+            attn = add_decomposed_rel_pos(attn, q, self.rel_pos_h, self.rel_pos_w, (H, W), (H, W))
+
+        attn = attn.softmax(dim=-1)
+        x = (attn @ v).view(B, self.num_heads, H, W, -1).permute(0, 2, 3, 1, 4).reshape(B, H, W, -1)
+        x = self.proj(x)
+
+        return x
+
+
+def window_partition(x: torch.Tensor, window_size: int) -> Tuple[torch.Tensor, Tuple[int, int]]:
+    """
+    Partition into non-overlapping windows with padding if needed.
+    Args:
+        x (tensor): input tokens with [B, H, W, C].
+        window_size (int): window size.
+
+    Returns:
+        windows: windows after partition with [B * num_windows, window_size, window_size, C].
+        (Hp, Wp): padded height and width before partition
+    """
+    B, H, W, C = x.shape
+
+    pad_h = (window_size - H % window_size) % window_size
+    pad_w = (window_size - W % window_size) % window_size
+    if pad_h > 0 or pad_w > 0:
+        x = F.pad(x, (0, 0, 0, pad_w, 0, pad_h))
+    Hp, Wp = H + pad_h, W + pad_w
+
+    x = x.view(B, Hp // window_size, window_size, Wp // window_size, window_size, C)
+    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
+    return windows, (Hp, Wp)
+
+
+def window_unpartition(
+    windows: torch.Tensor, window_size: int, pad_hw: Tuple[int, int], hw: Tuple[int, int]
+) -> torch.Tensor:
+    """
+    Window unpartition into original sequences and removing padding.
+    Args:
+        windows (tensor): input tokens with [B * num_windows, window_size, window_size, C].
+        window_size (int): window size.
+        pad_hw (Tuple): padded height and width (Hp, Wp).
+        hw (Tuple): original height and width (H, W) before padding.
+
+    Returns:
+        x: unpartitioned sequences with [B, H, W, C].
+    """
+    Hp, Wp = pad_hw
+    H, W = hw
+    B = windows.shape[0] // (Hp * Wp // window_size // window_size)
+    x = windows.view(B, Hp // window_size, Wp // window_size, window_size, window_size, -1)
+    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, Hp, Wp, -1)
+
+    if Hp > H or Wp > W:
+        x = x[:, :H, :W, :].contiguous()
+    return x
+
+
+def get_rel_pos(q_size: int, k_size: int, rel_pos: torch.Tensor) -> torch.Tensor:
+    """
+    Get relative positional embeddings according to the relative positions of
+        query and key sizes.
+    Args:
+        q_size (int): size of query q.
+        k_size (int): size of key k.
+        rel_pos (Tensor): relative position embeddings (L, C).
+
+    Returns:
+        Extracted positional embeddings according to relative positions.
+    """
+    max_rel_dist = int(2 * max(q_size, k_size) - 1)
+    # Interpolate rel pos if needed.
+    if rel_pos.shape[0] != max_rel_dist:
+        # Interpolate rel pos.
+        rel_pos_resized = F.interpolate(
+            rel_pos.reshape(1, rel_pos.shape[0], -1).permute(0, 2, 1),
+            size=max_rel_dist,
+            mode="linear",
+        )
+        rel_pos_resized = rel_pos_resized.reshape(-1, max_rel_dist).permute(1, 0)
+    else:
+        rel_pos_resized = rel_pos
+
+    # Scale the coords with short length if shapes for q and k are different.
+    q_coords = torch.arange(q_size)[:, None] * max(k_size / q_size, 1.0)
+    k_coords = torch.arange(k_size)[None, :] * max(q_size / k_size, 1.0)
+    relative_coords = (q_coords - k_coords) + (k_size - 1) * max(q_size / k_size, 1.0)
+
+    return rel_pos_resized[relative_coords.long()]
+
+
+def add_decomposed_rel_pos(
+    attn: torch.Tensor,
+    q: torch.Tensor,
+    rel_pos_h: torch.Tensor,
+    rel_pos_w: torch.Tensor,
+    q_size: Tuple[int, int],
+    k_size: Tuple[int, int],
+) -> torch.Tensor:
+    """
+    Calculate decomposed Relative Positional Embeddings from :paper:`mvitv2`.
+    https://github.com/facebookresearch/mvit/blob/19786631e330df9f3622e5402b4a419a263a2c80/mvit/models/attention.py   # noqa B950
+    Args:
+        attn (Tensor): attention map.
+        q (Tensor): query q in the attention layer with shape (B, q_h * q_w, C).
+        rel_pos_h (Tensor): relative position embeddings (Lh, C) for height axis.
+        rel_pos_w (Tensor): relative position embeddings (Lw, C) for width axis.
+        q_size (Tuple): spatial sequence size of query q with (q_h, q_w).
+        k_size (Tuple): spatial sequence size of key k with (k_h, k_w).
+
+    Returns:
+        attn (Tensor): attention map with added relative positional embeddings.
+    """
+    q_h, q_w = q_size
+    k_h, k_w = k_size
+    Rh = get_rel_pos(q_h, k_h, rel_pos_h)
+    Rw = get_rel_pos(q_w, k_w, rel_pos_w)
+
+    B, _, dim = q.shape
+    r_q = q.reshape(B, q_h, q_w, dim)
+    rel_h = torch.einsum("bhwc,hkc->bhwk", r_q, Rh)
+    rel_w = torch.einsum("bhwc,wkc->bhwk", r_q, Rw)
+
+    attn = (
+        attn.view(B, q_h, q_w, k_h, k_w) + rel_h[:, :, :, :, None] + rel_w[:, :, :, None, :]
+    ).view(B, q_h * q_w, k_h * k_w)
+
+    return attn
+
+
+class PatchEmbed(nn.Module):
+    """
+    Image to Patch Embedding.
+    """
+
+    def __init__(
+        self,
+        kernel_size: Tuple[int, int] = (16, 16),
+        stride: Tuple[int, int] = (16, 16),
+        padding: Tuple[int, int] = (0, 0),
+        in_chans: int = 3,
+        embed_dim: int = 768,
+    ) -> None:
+        """
+        Args:
+            kernel_size (Tuple): kernel size of the projection layer.
+            stride (Tuple): stride of the projection layer.
+            padding (Tuple): padding size of the projection layer.
+            in_chans (int): Number of input image channels.
+            embed_dim (int): Patch embedding dimension.
+        """
+        super().__init__()
+
+        self.proj = nn.Conv2d(
+            in_chans, embed_dim, kernel_size=kernel_size, stride=stride, padding=padding
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = self.proj(x)
+        # B C H W -> B H W C
+        x = x.permute(0, 2, 3, 1)
+        return x

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/mask_decoder.py

@@ -0,0 +1,178 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from typing import List, Tuple, Type
+
+from .common import LayerNorm2d
+
+
+class MaskDecoder(nn.Module):
+    def __init__(
+        self,
+        *,
+        transformer_dim: int,
+        transformer: nn.Module,
+        num_multimask_outputs: int = 3,
+        activation: Type[nn.Module] = nn.GELU,
+        iou_head_depth: int = 3,
+        iou_head_hidden_dim: int = 256,
+    ) -> None:
+        """
+        Predicts masks given an image and prompt embeddings, using a
+        transformer architecture.
+
+        Arguments:
+          transformer_dim (int): the channel dimension of the transformer
+          transformer (nn.Module): the transformer used to predict masks
+          num_multimask_outputs (int): the number of masks to predict
+            when disambiguating masks
+          activation (nn.Module): the type of activation to use when
+            upscaling masks
+          iou_head_depth (int): the depth of the MLP used to predict
+            mask quality
+          iou_head_hidden_dim (int): the hidden dimension of the MLP
+            used to predict mask quality
+        """
+        super().__init__()
+        self.transformer_dim = transformer_dim
+        self.transformer = transformer
+
+        self.num_multimask_outputs = num_multimask_outputs
+
+        self.iou_token = nn.Embedding(1, transformer_dim)
+        self.num_mask_tokens = num_multimask_outputs + 1
+        self.mask_tokens = nn.Embedding(self.num_mask_tokens, transformer_dim)
+
+        self.output_upscaling = nn.Sequential(
+            nn.ConvTranspose2d(transformer_dim, transformer_dim // 4, kernel_size=2, stride=2),
+            LayerNorm2d(transformer_dim // 4),
+            activation(),
+            nn.ConvTranspose2d(transformer_dim // 4, transformer_dim // 8, kernel_size=2, stride=2),
+            activation(),
+        )
+        self.output_hypernetworks_mlps = nn.ModuleList(
+            [
+                MLP(transformer_dim, transformer_dim, transformer_dim // 8, 3)
+                for i in range(self.num_mask_tokens)
+            ]
+        )
+
+        self.iou_prediction_head = MLP(
+            transformer_dim, iou_head_hidden_dim, self.num_mask_tokens, iou_head_depth
+        )
+
+    def forward(
+        self,
+        image_embeddings: torch.Tensor,
+        image_pe: torch.Tensor,
+        sparse_prompt_embeddings: torch.Tensor,
+        dense_prompt_embeddings: torch.Tensor,
+        multimask_output: bool,
+        hq_token_only: bool,
+        interm_embeddings: torch.Tensor,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        """
+        Predict masks given image and prompt embeddings.
+
+        Arguments:
+          image_embeddings (torch.Tensor): the embeddings from the image encoder
+          image_pe (torch.Tensor): positional encoding with the shape of image_embeddings
+          sparse_prompt_embeddings (torch.Tensor): the embeddings of the points and boxes
+          dense_prompt_embeddings (torch.Tensor): the embeddings of the mask inputs
+          multimask_output (bool): Whether to return multiple masks or a single
+            mask.
+
+        Returns:
+          torch.Tensor: batched predicted masks
+          torch.Tensor: batched predictions of mask quality
+        """
+        masks, iou_pred = self.predict_masks(
+            image_embeddings=image_embeddings,
+            image_pe=image_pe,
+            sparse_prompt_embeddings=sparse_prompt_embeddings,
+            dense_prompt_embeddings=dense_prompt_embeddings,
+        )
+
+        # Select the correct mask or masks for output
+        if multimask_output:
+            mask_slice = slice(1, None)
+        else:
+            mask_slice = slice(0, 1)
+        masks = masks[:, mask_slice, :, :]
+        iou_pred = iou_pred[:, mask_slice]
+
+        # Prepare output
+        return masks, iou_pred
+
+    def predict_masks(
+        self,
+        image_embeddings: torch.Tensor,
+        image_pe: torch.Tensor,
+        sparse_prompt_embeddings: torch.Tensor,
+        dense_prompt_embeddings: torch.Tensor,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        """Predicts masks. See 'forward' for more details."""
+        # Concatenate output tokens
+        output_tokens = torch.cat([self.iou_token.weight, self.mask_tokens.weight], dim=0)
+        output_tokens = output_tokens.unsqueeze(0).expand(sparse_prompt_embeddings.size(0), -1, -1)
+        tokens = torch.cat((output_tokens, sparse_prompt_embeddings), dim=1)
+
+        # Expand per-image data in batch direction to be per-mask
+        src = torch.repeat_interleave(image_embeddings, tokens.shape[0], dim=0)
+        src = src + dense_prompt_embeddings
+        pos_src = torch.repeat_interleave(image_pe, tokens.shape[0], dim=0)
+        b, c, h, w = src.shape
+
+        # Run the transformer
+        hs, src = self.transformer(src, pos_src, tokens)
+        iou_token_out = hs[:, 0, :]
+        mask_tokens_out = hs[:, 1 : (1 + self.num_mask_tokens), :]
+
+        # Upscale mask embeddings and predict masks using the mask tokens
+        src = src.transpose(1, 2).view(b, c, h, w)
+        upscaled_embedding = self.output_upscaling(src)
+        hyper_in_list: List[torch.Tensor] = []
+        for i in range(self.num_mask_tokens):
+            hyper_in_list.append(self.output_hypernetworks_mlps[i](mask_tokens_out[:, i, :]))
+        hyper_in = torch.stack(hyper_in_list, dim=1)
+        b, c, h, w = upscaled_embedding.shape
+        masks = (hyper_in @ upscaled_embedding.view(b, c, h * w)).view(b, -1, h, w)
+
+        # Generate mask quality predictions
+        iou_pred = self.iou_prediction_head(iou_token_out)
+
+        return masks, iou_pred
+
+
+# Lightly adapted from
+# https://github.com/facebookresearch/MaskFormer/blob/main/mask_former/modeling/transformer/transformer_predictor.py # noqa
+class MLP(nn.Module):
+    def __init__(
+        self,
+        input_dim: int,
+        hidden_dim: int,
+        output_dim: int,
+        num_layers: int,
+        sigmoid_output: bool = False,
+    ) -> None:
+        super().__init__()
+        self.num_layers = num_layers
+        h = [hidden_dim] * (num_layers - 1)
+        self.layers = nn.ModuleList(
+            nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim])
+        )
+        self.sigmoid_output = sigmoid_output
+
+    def forward(self, x):
+        for i, layer in enumerate(self.layers):
+            x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
+        if self.sigmoid_output:
+            x = F.sigmoid(x)
+        return x

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/mask_decoder_hq.py

@@ -0,0 +1,232 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# Modified by HQ-SAM team
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from typing import List, Tuple, Type
+
+from .common import LayerNorm2d
+
+
+class MaskDecoderHQ(nn.Module):
+    def __init__(
+        self,
+        *,
+        transformer_dim: int,
+        transformer: nn.Module,
+        num_multimask_outputs: int = 3,
+        activation: Type[nn.Module] = nn.GELU,
+        iou_head_depth: int = 3,
+        iou_head_hidden_dim: int = 256,
+        vit_dim: int = 1024,
+    ) -> None:
+        """
+        Predicts masks given an image and prompt embeddings, using a
+        transformer architecture.
+
+        Arguments:
+          transformer_dim (int): the channel dimension of the transformer
+          transformer (nn.Module): the transformer used to predict masks
+          num_multimask_outputs (int): the number of masks to predict
+            when disambiguating masks
+          activation (nn.Module): the type of activation to use when
+            upscaling masks
+          iou_head_depth (int): the depth of the MLP used to predict
+            mask quality
+          iou_head_hidden_dim (int): the hidden dimension of the MLP
+            used to predict mask quality
+        """
+        super().__init__()
+        self.transformer_dim = transformer_dim
+        self.transformer = transformer
+
+        self.num_multimask_outputs = num_multimask_outputs
+
+        self.iou_token = nn.Embedding(1, transformer_dim)
+        self.num_mask_tokens = num_multimask_outputs + 1
+        self.mask_tokens = nn.Embedding(self.num_mask_tokens, transformer_dim)
+
+        self.output_upscaling = nn.Sequential(
+            nn.ConvTranspose2d(transformer_dim, transformer_dim // 4, kernel_size=2, stride=2),
+            LayerNorm2d(transformer_dim // 4),
+            activation(),
+            nn.ConvTranspose2d(transformer_dim // 4, transformer_dim // 8, kernel_size=2, stride=2),
+            activation(),
+        )
+        self.output_hypernetworks_mlps = nn.ModuleList(
+            [
+                MLP(transformer_dim, transformer_dim, transformer_dim // 8, 3)
+                for i in range(self.num_mask_tokens)
+            ]
+        )
+
+        self.iou_prediction_head = MLP(
+            transformer_dim, iou_head_hidden_dim, self.num_mask_tokens, iou_head_depth
+        )
+
+        # HQ-SAM parameters
+        self.hf_token = nn.Embedding(1, transformer_dim) # HQ-Ouptput-Token
+        self.hf_mlp = MLP(transformer_dim, transformer_dim, transformer_dim // 8, 3) # corresponding new MLP layer for HQ-Ouptput-Token
+        self.num_mask_tokens = self.num_mask_tokens + 1
+        
+        # three conv fusion layers for obtaining HQ-Feature
+        self.compress_vit_feat = nn.Sequential(
+                                        nn.ConvTranspose2d(vit_dim, transformer_dim, kernel_size=2, stride=2),
+                                        LayerNorm2d(transformer_dim),
+                                        nn.GELU(), 
+                                        nn.ConvTranspose2d(transformer_dim, transformer_dim // 8, kernel_size=2, stride=2))
+        
+        self.embedding_encoder = nn.Sequential(
+                                        nn.ConvTranspose2d(transformer_dim, transformer_dim // 4, kernel_size=2, stride=2),
+                                        LayerNorm2d(transformer_dim // 4),
+                                        nn.GELU(),
+                                        nn.ConvTranspose2d(transformer_dim // 4, transformer_dim // 8, kernel_size=2, stride=2),
+                                    )
+        self.embedding_maskfeature = nn.Sequential(
+                                        nn.Conv2d(transformer_dim // 8, transformer_dim // 4, 3, 1, 1), 
+                                        LayerNorm2d(transformer_dim // 4),
+                                        nn.GELU(),
+                                        nn.Conv2d(transformer_dim // 4, transformer_dim // 8, 3, 1, 1))
+
+
+
+    def forward(
+        self,
+        image_embeddings: torch.Tensor,
+        image_pe: torch.Tensor,
+        sparse_prompt_embeddings: torch.Tensor,
+        dense_prompt_embeddings: torch.Tensor,
+        multimask_output: bool,
+        hq_token_only: bool,
+        interm_embeddings: torch.Tensor,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        """
+        Predict masks given image and prompt embeddings.
+
+        Arguments:
+          image_embeddings (torch.Tensor): the embeddings from the ViT image encoder
+          image_pe (torch.Tensor): positional encoding with the shape of image_embeddings
+          sparse_prompt_embeddings (torch.Tensor): the embeddings of the points and boxes
+          dense_prompt_embeddings (torch.Tensor): the embeddings of the mask inputs
+          multimask_output (bool): Whether to return multiple masks or a single
+            mask.
+
+        Returns:
+          torch.Tensor: batched predicted masks
+          torch.Tensor: batched predictions of mask quality
+        """
+        vit_features = interm_embeddings[0].permute(0, 3, 1, 2) # early-layer ViT feature, after 1st global attention block in ViT
+        hq_features = self.embedding_encoder(image_embeddings) + self.compress_vit_feat(vit_features)
+
+        masks, iou_pred = self.predict_masks(
+            image_embeddings=image_embeddings,
+            image_pe=image_pe,
+            sparse_prompt_embeddings=sparse_prompt_embeddings,
+            dense_prompt_embeddings=dense_prompt_embeddings,
+            hq_features=hq_features,
+        )
+
+        # Select the correct mask or masks for output
+        if multimask_output:
+            # mask with highest score
+            mask_slice = slice(1,self.num_mask_tokens-1)
+            iou_pred = iou_pred[:, mask_slice]
+            iou_pred, max_iou_idx = torch.max(iou_pred,dim=1)
+            iou_pred = iou_pred.unsqueeze(1)
+            masks_multi = masks[:, mask_slice, :, :]
+            masks_sam = masks_multi[torch.arange(masks_multi.size(0)),max_iou_idx].unsqueeze(1)
+        else:
+            # singale mask output, default
+            mask_slice = slice(0, 1)
+            iou_pred = iou_pred[:,mask_slice]
+            masks_sam = masks[:,mask_slice]
+
+        masks_hq = masks[:,slice(self.num_mask_tokens-1, self.num_mask_tokens)]
+        if hq_token_only:
+            masks = masks_hq
+        else:
+            masks = masks_sam + masks_hq
+        # Prepare output
+        return masks, iou_pred
+
+    def predict_masks(
+        self,
+        image_embeddings: torch.Tensor,
+        image_pe: torch.Tensor,
+        sparse_prompt_embeddings: torch.Tensor,
+        dense_prompt_embeddings: torch.Tensor,
+        hq_features: torch.Tensor,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        """Predicts masks. See 'forward' for more details."""
+        # Concatenate output tokens
+        output_tokens = torch.cat([self.iou_token.weight, self.mask_tokens.weight, self.hf_token.weight], dim=0)
+        output_tokens = output_tokens.unsqueeze(0).expand(sparse_prompt_embeddings.size(0), -1, -1)
+        tokens = torch.cat((output_tokens, sparse_prompt_embeddings), dim=1)
+
+        # Expand per-image data in batch direction to be per-mask
+        src = torch.repeat_interleave(image_embeddings, tokens.shape[0], dim=0)
+        src = src + dense_prompt_embeddings
+        pos_src = torch.repeat_interleave(image_pe, tokens.shape[0], dim=0)
+        b, c, h, w = src.shape
+
+        # Run the transformer
+        hs, src = self.transformer(src, pos_src, tokens)
+        iou_token_out = hs[:, 0, :]
+        mask_tokens_out = hs[:, 1 : (1 + self.num_mask_tokens), :]
+
+        # Upscale mask embeddings and predict masks using the mask tokens
+        src = src.transpose(1, 2).view(b, c, h, w)
+
+        upscaled_embedding_sam = self.output_upscaling(src)
+        upscaled_embedding_hq = self.embedding_maskfeature(upscaled_embedding_sam) + hq_features.repeat(b,1,1,1)
+
+        hyper_in_list: List[torch.Tensor] = []
+        for i in range(self.num_mask_tokens):
+            if i < self.num_mask_tokens - 1:
+                hyper_in_list.append(self.output_hypernetworks_mlps[i](mask_tokens_out[:, i, :]))
+            else:
+                hyper_in_list.append(self.hf_mlp(mask_tokens_out[:, i, :]))
+
+        hyper_in = torch.stack(hyper_in_list, dim=1)
+        b, c, h, w = upscaled_embedding_sam.shape
+
+        masks_sam = (hyper_in[:,:self.num_mask_tokens-1] @ upscaled_embedding_sam.view(b, c, h * w)).view(b, -1, h, w)
+        masks_sam_hq = (hyper_in[:,self.num_mask_tokens-1:] @ upscaled_embedding_hq.view(b, c, h * w)).view(b, -1, h, w)
+        masks = torch.cat([masks_sam,masks_sam_hq],dim=1)
+        # Generate mask quality predictions
+        iou_pred = self.iou_prediction_head(iou_token_out)
+
+        return masks, iou_pred
+
+
+# Lightly adapted from
+# https://github.com/facebookresearch/MaskFormer/blob/main/mask_former/modeling/transformer/transformer_predictor.py # noqa
+class MLP(nn.Module):
+    def __init__(
+        self,
+        input_dim: int,
+        hidden_dim: int,
+        output_dim: int,
+        num_layers: int,
+        sigmoid_output: bool = False,
+    ) -> None:
+        super().__init__()
+        self.num_layers = num_layers
+        h = [hidden_dim] * (num_layers - 1)
+        self.layers = nn.ModuleList(
+            nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim])
+        )
+        self.sigmoid_output = sigmoid_output
+
+    def forward(self, x):
+        for i, layer in enumerate(self.layers):
+            x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
+        if self.sigmoid_output:
+            x = F.sigmoid(x)
+        return x

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/prompt_encoder.py

@@ -0,0 +1,214 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import numpy as np
+import torch
+from torch import nn
+
+from typing import Any, Optional, Tuple, Type
+
+from .common import LayerNorm2d
+
+
+class PromptEncoder(nn.Module):
+    def __init__(
+        self,
+        embed_dim: int,
+        image_embedding_size: Tuple[int, int],
+        input_image_size: Tuple[int, int],
+        mask_in_chans: int,
+        activation: Type[nn.Module] = nn.GELU,
+    ) -> None:
+        """
+        Encodes prompts for input to SAM's mask decoder.
+
+        Arguments:
+          embed_dim (int): The prompts' embedding dimension
+          image_embedding_size (tuple(int, int)): The spatial size of the
+            image embedding, as (H, W).
+          input_image_size (int): The padded size of the image as input
+            to the image encoder, as (H, W).
+          mask_in_chans (int): The number of hidden channels used for
+            encoding input masks.
+          activation (nn.Module): The activation to use when encoding
+            input masks.
+        """
+        super().__init__()
+        self.embed_dim = embed_dim
+        self.input_image_size = input_image_size
+        self.image_embedding_size = image_embedding_size
+        self.pe_layer = PositionEmbeddingRandom(embed_dim // 2)
+
+        self.num_point_embeddings: int = 4  # pos/neg point + 2 box corners
+        point_embeddings = [nn.Embedding(1, embed_dim) for i in range(self.num_point_embeddings)]
+        self.point_embeddings = nn.ModuleList(point_embeddings)
+        self.not_a_point_embed = nn.Embedding(1, embed_dim)
+
+        self.mask_input_size = (4 * image_embedding_size[0], 4 * image_embedding_size[1])
+        self.mask_downscaling = nn.Sequential(
+            nn.Conv2d(1, mask_in_chans // 4, kernel_size=2, stride=2),
+            LayerNorm2d(mask_in_chans // 4),
+            activation(),
+            nn.Conv2d(mask_in_chans // 4, mask_in_chans, kernel_size=2, stride=2),
+            LayerNorm2d(mask_in_chans),
+            activation(),
+            nn.Conv2d(mask_in_chans, embed_dim, kernel_size=1),
+        )
+        self.no_mask_embed = nn.Embedding(1, embed_dim)
+
+    def get_dense_pe(self) -> torch.Tensor:
+        """
+        Returns the positional encoding used to encode point prompts,
+        applied to a dense set of points the shape of the image encoding.
+
+        Returns:
+          torch.Tensor: Positional encoding with shape
+            1x(embed_dim)x(embedding_h)x(embedding_w)
+        """
+        return self.pe_layer(self.image_embedding_size).unsqueeze(0)
+
+    def _embed_points(
+        self,
+        points: torch.Tensor,
+        labels: torch.Tensor,
+        pad: bool,
+    ) -> torch.Tensor:
+        """Embeds point prompts."""
+        points = points + 0.5  # Shift to center of pixel
+        if pad:
+            padding_point = torch.zeros((points.shape[0], 1, 2), device=points.device)
+            padding_label = -torch.ones((labels.shape[0], 1), device=labels.device)
+            points = torch.cat([points, padding_point], dim=1)
+            labels = torch.cat([labels, padding_label], dim=1)
+        point_embedding = self.pe_layer.forward_with_coords(points, self.input_image_size)
+        point_embedding[labels == -1] = 0.0
+        point_embedding[labels == -1] += self.not_a_point_embed.weight
+        point_embedding[labels == 0] += self.point_embeddings[0].weight
+        point_embedding[labels == 1] += self.point_embeddings[1].weight
+        return point_embedding
+
+    def _embed_boxes(self, boxes: torch.Tensor) -> torch.Tensor:
+        """Embeds box prompts."""
+        boxes = boxes + 0.5  # Shift to center of pixel
+        coords = boxes.reshape(-1, 2, 2)
+        corner_embedding = self.pe_layer.forward_with_coords(coords, self.input_image_size)
+        corner_embedding[:, 0, :] += self.point_embeddings[2].weight
+        corner_embedding[:, 1, :] += self.point_embeddings[3].weight
+        return corner_embedding
+
+    def _embed_masks(self, masks: torch.Tensor) -> torch.Tensor:
+        """Embeds mask inputs."""
+        mask_embedding = self.mask_downscaling(masks)
+        return mask_embedding
+
+    def _get_batch_size(
+        self,
+        points: Optional[Tuple[torch.Tensor, torch.Tensor]],
+        boxes: Optional[torch.Tensor],
+        masks: Optional[torch.Tensor],
+    ) -> int:
+        """
+        Gets the batch size of the output given the batch size of the input prompts.
+        """
+        if points is not None:
+            return points[0].shape[0]
+        elif boxes is not None:
+            return boxes.shape[0]
+        elif masks is not None:
+            return masks.shape[0]
+        else:
+            return 1
+
+    def _get_device(self) -> torch.device:
+        return self.point_embeddings[0].weight.device
+
+    def forward(
+        self,
+        points: Optional[Tuple[torch.Tensor, torch.Tensor]],
+        boxes: Optional[torch.Tensor],
+        masks: Optional[torch.Tensor],
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        """
+        Embeds different types of prompts, returning both sparse and dense
+        embeddings.
+
+        Arguments:
+          points (tuple(torch.Tensor, torch.Tensor) or none): point coordinates
+            and labels to embed.
+          boxes (torch.Tensor or none): boxes to embed
+          masks (torch.Tensor or none): masks to embed
+
+        Returns:
+          torch.Tensor: sparse embeddings for the points and boxes, with shape
+            BxNx(embed_dim), where N is determined by the number of input points
+            and boxes.
+          torch.Tensor: dense embeddings for the masks, in the shape
+            Bx(embed_dim)x(embed_H)x(embed_W)
+        """
+        bs = self._get_batch_size(points, boxes, masks)
+        sparse_embeddings = torch.empty((bs, 0, self.embed_dim), device=self._get_device())
+        if points is not None:
+            coords, labels = points
+            point_embeddings = self._embed_points(coords, labels, pad=(boxes is None))
+            sparse_embeddings = torch.cat([sparse_embeddings, point_embeddings], dim=1)
+        if boxes is not None:
+            box_embeddings = self._embed_boxes(boxes)
+            sparse_embeddings = torch.cat([sparse_embeddings, box_embeddings], dim=1)
+
+        if masks is not None:
+            dense_embeddings = self._embed_masks(masks)
+        else:
+            dense_embeddings = self.no_mask_embed.weight.reshape(1, -1, 1, 1).expand(
+                bs, -1, self.image_embedding_size[0], self.image_embedding_size[1]
+            )
+
+        return sparse_embeddings, dense_embeddings
+
+
+class PositionEmbeddingRandom(nn.Module):
+    """
+    Positional encoding using random spatial frequencies.
+    """
+
+    def __init__(self, num_pos_feats: int = 64, scale: Optional[float] = None) -> None:
+        super().__init__()
+        if scale is None or scale <= 0.0:
+            scale = 1.0
+        self.register_buffer(
+            "positional_encoding_gaussian_matrix",
+            scale * torch.randn((2, num_pos_feats)),
+        )
+
+    def _pe_encoding(self, coords: torch.Tensor) -> torch.Tensor:
+        """Positionally encode points that are normalized to [0,1]."""
+        # assuming coords are in [0, 1]^2 square and have d_1 x ... x d_n x 2 shape
+        coords = 2 * coords - 1
+        coords = coords @ self.positional_encoding_gaussian_matrix
+        coords = 2 * np.pi * coords
+        # outputs d_1 x ... x d_n x C shape
+        return torch.cat([torch.sin(coords), torch.cos(coords)], dim=-1)
+
+    def forward(self, size: Tuple[int, int]) -> torch.Tensor:
+        """Generate positional encoding for a grid of the specified size."""
+        h, w = size
+        device: Any = self.positional_encoding_gaussian_matrix.device
+        grid = torch.ones((h, w), device=device, dtype=torch.float32)
+        y_embed = grid.cumsum(dim=0) - 0.5
+        x_embed = grid.cumsum(dim=1) - 0.5
+        y_embed = y_embed / h
+        x_embed = x_embed / w
+
+        pe = self._pe_encoding(torch.stack([x_embed, y_embed], dim=-1))
+        return pe.permute(2, 0, 1)  # C x H x W
+
+    def forward_with_coords(
+        self, coords_input: torch.Tensor, image_size: Tuple[int, int]
+    ) -> torch.Tensor:
+        """Positionally encode points that are not normalized to [0,1]."""
+        coords = coords_input.clone()
+        coords[:, :, 0] = coords[:, :, 0] / image_size[1]
+        coords[:, :, 1] = coords[:, :, 1] / image_size[0]
+        return self._pe_encoding(coords.to(torch.float))  # B x N x C

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/sam.py

@@ -0,0 +1,177 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from typing import Any, Dict, List, Tuple
+
+from .image_encoder import ImageEncoderViT
+from .mask_decoder import MaskDecoder
+from .prompt_encoder import PromptEncoder
+
+
+class Sam(nn.Module):
+    mask_threshold: float = 0.0
+    image_format: str = "RGB"
+
+    def __init__(
+        self,
+        image_encoder: ImageEncoderViT,
+        prompt_encoder: PromptEncoder,
+        mask_decoder: MaskDecoder,
+        pixel_mean: List[float] = [123.675, 116.28, 103.53],
+        pixel_std: List[float] = [58.395, 57.12, 57.375],
+    ) -> None:
+        """
+        SAM predicts object masks from an image and input prompts.
+
+        Arguments:
+          image_encoder (ImageEncoderViT): The backbone used to encode the
+            image into image embeddings that allow for efficient mask prediction.
+          prompt_encoder (PromptEncoder): Encodes various types of input prompts.
+          mask_decoder (MaskDecoder): Predicts masks from the image embeddings
+            and encoded prompts.
+          pixel_mean (list(float)): Mean values for normalizing pixels in the input image.
+          pixel_std (list(float)): Std values for normalizing pixels in the input image.
+        """
+        super().__init__()
+        self.image_encoder = image_encoder
+        self.prompt_encoder = prompt_encoder
+        self.mask_decoder = mask_decoder
+        self.register_buffer("pixel_mean", torch.Tensor(pixel_mean).view(-1, 1, 1), False)
+        self.register_buffer("pixel_std", torch.Tensor(pixel_std).view(-1, 1, 1), False)
+
+    @property
+    def device(self) -> Any:
+        return self.pixel_mean.device
+
+    def forward(
+        self,
+        batched_input: List[Dict[str, Any]],
+        multimask_output: bool,
+        hq_token_only: bool =False,
+    ) -> List[Dict[str, torch.Tensor]]:
+        """
+        Predicts masks end-to-end from provided images and prompts.
+        If prompts are not known in advance, using SamPredictor is
+        recommended over calling the model directly.
+
+        Arguments:
+          batched_input (list(dict)): A list over input images, each a
+            dictionary with the following keys. A prompt key can be
+            excluded if it is not present.
+              'image': The image as a torch tensor in 3xHxW format,
+                already transformed for input to the model.
+              'original_size': (tuple(int, int)) The original size of
+                the image before transformation, as (H, W).
+              'point_coords': (torch.Tensor) Batched point prompts for
+                this image, with shape BxNx2. Already transformed to the
+                input frame of the model.
+              'point_labels': (torch.Tensor) Batched labels for point prompts,
+                with shape BxN.
+              'boxes': (torch.Tensor) Batched box inputs, with shape Bx4.
+                Already transformed to the input frame of the model.
+              'mask_inputs': (torch.Tensor) Batched mask inputs to the model,
+                in the form Bx1xHxW.
+          multimask_output (bool): Whether the model should predict multiple
+            disambiguating masks, or return a single mask.
+
+        Returns:
+          (list(dict)): A list over input images, where each element is
+            as dictionary with the following keys.
+              'masks': (torch.Tensor) Batched binary mask predictions,
+                with shape BxCxHxW, where B is the number of input prompts,
+                C is determined by multimask_output, and (H, W) is the
+                original size of the image.
+              'iou_predictions': (torch.Tensor) The model's predictions
+                of mask quality, in shape BxC.
+              'low_res_logits': (torch.Tensor) Low resolution logits with
+                shape BxCxHxW, where H=W=256. Can be passed as mask input
+                to subsequent iterations of prediction.
+        """
+        input_images = torch.stack([self.preprocess(x["image"]) for x in batched_input], dim=0)
+        image_embeddings, interm_embeddings = self.image_encoder(input_images)
+        interm_embeddings = interm_embeddings[0] # early layer
+
+        outputs = []
+        for image_record, curr_embedding, curr_interm in zip(batched_input, image_embeddings, interm_embeddings):
+            if "point_coords" in image_record:
+                points = (image_record["point_coords"], image_record["point_labels"])
+            else:
+                points = None
+            sparse_embeddings, dense_embeddings = self.prompt_encoder(
+                points=points,
+                boxes=image_record.get("boxes", None),
+                masks=image_record.get("mask_inputs", None),
+            )
+            low_res_masks, iou_predictions = self.mask_decoder(
+                image_embeddings=curr_embedding.unsqueeze(0),
+                image_pe=self.prompt_encoder.get_dense_pe(),
+                sparse_prompt_embeddings=sparse_embeddings,
+                dense_prompt_embeddings=dense_embeddings,
+                multimask_output=multimask_output,
+                hq_token_only=hq_token_only,
+                interm_embeddings=curr_interm.unsqueeze(0).unsqueeze(0),
+            )
+            masks = self.postprocess_masks(
+                low_res_masks,
+                input_size=image_record["image"].shape[-2:],
+                original_size=image_record["original_size"],
+            )
+            masks = masks > self.mask_threshold
+            outputs.append(
+                {
+                    "masks": masks,
+                    "iou_predictions": iou_predictions,
+                    "low_res_logits": low_res_masks,
+                }
+            )
+        return outputs
+
+    def postprocess_masks(
+        self,
+        masks: torch.Tensor,
+        input_size: Tuple[int, ...],
+        original_size: Tuple[int, ...],
+    ) -> torch.Tensor:
+        """
+        Remove padding and upscale masks to the original image size.
+
+        Arguments:
+          masks (torch.Tensor): Batched masks from the mask_decoder,
+            in BxCxHxW format.
+          input_size (tuple(int, int)): The size of the image input to the
+            model, in (H, W) format. Used to remove padding.
+          original_size (tuple(int, int)): The original size of the image
+            before resizing for input to the model, in (H, W) format.
+
+        Returns:
+          (torch.Tensor): Batched masks in BxCxHxW format, where (H, W)
+            is given by original_size.
+        """
+        masks = F.interpolate(
+            masks,
+            (self.image_encoder.img_size, self.image_encoder.img_size),
+            mode="bilinear",
+            align_corners=False,
+        )
+        masks = masks[..., : input_size[0], : input_size[1]]
+        masks = F.interpolate(masks, original_size, mode="bilinear", align_corners=False)
+        return masks
+
+    def preprocess(self, x: torch.Tensor) -> torch.Tensor:
+        """Normalize pixel values and pad to a square input."""
+        # Normalize colors
+        x = (x - self.pixel_mean) / self.pixel_std
+
+        # Pad
+        h, w = x.shape[-2:]
+        padh = self.image_encoder.img_size - h
+        padw = self.image_encoder.img_size - w
+        x = F.pad(x, (0, padw, 0, padh))
+        return x

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/tiny_vit_sam.py

@@ -0,0 +1,724 @@
+# --------------------------------------------------------
+# TinyViT Model Architecture
+# Copyright (c) 2022 Microsoft
+# Adapted from LeViT and Swin Transformer
+#   LeViT: (https://github.com/facebookresearch/levit)
+#   Swin: (https://github.com/microsoft/swin-transformer)
+# Build the TinyViT Model
+# --------------------------------------------------------
+
+import itertools
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.utils.checkpoint as checkpoint
+from timm.models.layers import DropPath as TimmDropPath,\
+    to_2tuple, trunc_normal_
+from timm.models.registry import register_model
+from typing import Tuple
+
+
+class Conv2d_BN(torch.nn.Sequential):
+    def __init__(self, a, b, ks=1, stride=1, pad=0, dilation=1,
+                 groups=1, bn_weight_init=1):
+        super().__init__()
+        self.add_module('c', torch.nn.Conv2d(
+            a, b, ks, stride, pad, dilation, groups, bias=False))
+        bn = torch.nn.BatchNorm2d(b)
+        torch.nn.init.constant_(bn.weight, bn_weight_init)
+        torch.nn.init.constant_(bn.bias, 0)
+        self.add_module('bn', bn)
+
+    @torch.no_grad()
+    def fuse(self):
+        c, bn = self._modules.values()
+        w = bn.weight / (bn.running_var + bn.eps)**0.5
+        w = c.weight * w[:, None, None, None]
+        b = bn.bias - bn.running_mean * bn.weight / \
+            (bn.running_var + bn.eps)**0.5
+        m = torch.nn.Conv2d(w.size(1) * self.c.groups, w.size(
+            0), w.shape[2:], stride=self.c.stride, padding=self.c.padding, dilation=self.c.dilation, groups=self.c.groups)
+        m.weight.data.copy_(w)
+        m.bias.data.copy_(b)
+        return m
+
+
+class DropPath(TimmDropPath):
+    def __init__(self, drop_prob=None):
+        super().__init__(drop_prob=drop_prob)
+        self.drop_prob = drop_prob
+
+    def __repr__(self):
+        msg = super().__repr__()
+        msg += f'(drop_prob={self.drop_prob})'
+        return msg
+
+
+class PatchEmbed(nn.Module):
+    def __init__(self, in_chans, embed_dim, resolution, activation):
+        super().__init__()
+        img_size: Tuple[int, int] = to_2tuple(resolution)
+        self.patches_resolution = (img_size[0] // 4, img_size[1] // 4)
+        self.num_patches = self.patches_resolution[0] * \
+            self.patches_resolution[1]
+        self.in_chans = in_chans
+        self.embed_dim = embed_dim
+        n = embed_dim
+        self.seq = nn.Sequential(
+            Conv2d_BN(in_chans, n // 2, 3, 2, 1),
+            activation(),
+            Conv2d_BN(n // 2, n, 3, 2, 1),
+        )
+
+    def forward(self, x):
+        return self.seq(x)
+
+
+class MBConv(nn.Module):
+    def __init__(self, in_chans, out_chans, expand_ratio,
+                 activation, drop_path):
+        super().__init__()
+        self.in_chans = in_chans
+        self.hidden_chans = int(in_chans * expand_ratio)
+        self.out_chans = out_chans
+
+        self.conv1 = Conv2d_BN(in_chans, self.hidden_chans, ks=1)
+        self.act1 = activation()
+
+        self.conv2 = Conv2d_BN(self.hidden_chans, self.hidden_chans,
+                               ks=3, stride=1, pad=1, groups=self.hidden_chans)
+        self.act2 = activation()
+
+        self.conv3 = Conv2d_BN(
+            self.hidden_chans, out_chans, ks=1, bn_weight_init=0.0)
+        self.act3 = activation()
+
+        self.drop_path = DropPath(
+            drop_path) if drop_path > 0. else nn.Identity()
+
+    def forward(self, x):
+        shortcut = x
+
+        x = self.conv1(x)
+        x = self.act1(x)
+
+        x = self.conv2(x)
+        x = self.act2(x)
+
+        x = self.conv3(x)
+
+        x = self.drop_path(x)
+
+        x += shortcut
+        x = self.act3(x)
+
+        return x
+
+
+class PatchMerging(nn.Module):
+    def __init__(self, input_resolution, dim, out_dim, activation):
+        super().__init__()
+
+        self.input_resolution = input_resolution
+        self.dim = dim
+        self.out_dim = out_dim
+        self.act = activation()
+        self.conv1 = Conv2d_BN(dim, out_dim, 1, 1, 0)
+        stride_c=2
+        if(out_dim==320 or out_dim==448 or out_dim==576):
+            stride_c=1
+        self.conv2 = Conv2d_BN(out_dim, out_dim, 3, stride_c, 1, groups=out_dim)
+        self.conv3 = Conv2d_BN(out_dim, out_dim, 1, 1, 0)
+
+    def forward(self, x):
+        if x.ndim == 3:
+            H, W = self.input_resolution
+            B = len(x)
+            # (B, C, H, W)
+            x = x.view(B, H, W, -1).permute(0, 3, 1, 2)
+
+        x = self.conv1(x)
+        x = self.act(x)
+
+        x = self.conv2(x)
+        x = self.act(x)
+        x = self.conv3(x)
+        x = x.flatten(2).transpose(1, 2)
+        return x
+
+
+class ConvLayer(nn.Module):
+    def __init__(self, dim, input_resolution, depth,
+                 activation,
+                 drop_path=0., downsample=None, use_checkpoint=False,
+                 out_dim=None,
+                 conv_expand_ratio=4.,
+                 ):
+
+        super().__init__()
+        self.dim = dim
+        self.input_resolution = input_resolution
+        self.depth = depth
+        self.use_checkpoint = use_checkpoint
+
+        # build blocks
+        self.blocks = nn.ModuleList([
+            MBConv(dim, dim, conv_expand_ratio, activation,
+                   drop_path[i] if isinstance(drop_path, list) else drop_path,
+                   )
+            for i in range(depth)])
+
+        # patch merging layer
+        if downsample is not None:
+            self.downsample = downsample(
+                input_resolution, dim=dim, out_dim=out_dim, activation=activation)
+        else:
+            self.downsample = None
+
+    def forward(self, x):
+        for blk in self.blocks:
+            if self.use_checkpoint:
+                x = checkpoint.checkpoint(blk, x)
+            else:
+                x = blk(x)
+        if self.downsample is not None:
+            x = self.downsample(x)
+        return x
+
+
+class Mlp(nn.Module):
+    def __init__(self, in_features, hidden_features=None,
+                 out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.norm = nn.LayerNorm(in_features)
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.act = act_layer()
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.norm(x)
+
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+class Attention(torch.nn.Module):
+    def __init__(self, dim, key_dim, num_heads=8,
+                 attn_ratio=4,
+                 resolution=(14, 14),
+                 ):
+        super().__init__()
+        # (h, w)
+        assert isinstance(resolution, tuple) and len(resolution) == 2
+        self.num_heads = num_heads
+        self.scale = key_dim ** -0.5
+        self.key_dim = key_dim
+        self.nh_kd = nh_kd = key_dim * num_heads
+        self.d = int(attn_ratio * key_dim)
+        self.dh = int(attn_ratio * key_dim) * num_heads
+        self.attn_ratio = attn_ratio
+        h = self.dh + nh_kd * 2
+
+        self.norm = nn.LayerNorm(dim)
+        self.qkv = nn.Linear(dim, h)
+        self.proj = nn.Linear(self.dh, dim)
+
+        points = list(itertools.product(
+            range(resolution[0]), range(resolution[1])))
+        N = len(points)
+        attention_offsets = {}
+        idxs = []
+        for p1 in points:
+            for p2 in points:
+                offset = (abs(p1[0] - p2[0]), abs(p1[1] - p2[1]))
+                if offset not in attention_offsets:
+                    attention_offsets[offset] = len(attention_offsets)
+                idxs.append(attention_offsets[offset])
+        self.attention_biases = torch.nn.Parameter(
+            torch.zeros(num_heads, len(attention_offsets)))
+        self.register_buffer('attention_bias_idxs',
+                             torch.LongTensor(idxs).view(N, N),
+                             persistent=False)
+
+    @torch.no_grad()
+    def train(self, mode=True):
+        super().train(mode)
+        if mode and hasattr(self, 'ab'):
+            del self.ab
+        else:
+            self.register_buffer('ab',
+                                 self.attention_biases[:, self.attention_bias_idxs],
+                                 persistent=False)
+
+    def forward(self, x):  # x (B,N,C)
+        B, N, _ = x.shape
+
+        # Normalization
+        x = self.norm(x)
+
+        qkv = self.qkv(x)
+        # (B, N, num_heads, d)
+        q, k, v = qkv.view(B, N, self.num_heads, -
+                           1).split([self.key_dim, self.key_dim, self.d], dim=3)
+        # (B, num_heads, N, d)
+        q = q.permute(0, 2, 1, 3)
+        k = k.permute(0, 2, 1, 3)
+        v = v.permute(0, 2, 1, 3)
+
+        attn = (
+            (q @ k.transpose(-2, -1)) * self.scale
+            +
+            (self.attention_biases[:, self.attention_bias_idxs]
+             if self.training else self.ab)
+        )
+        attn = attn.softmax(dim=-1)
+        x = (attn @ v).transpose(1, 2).reshape(B, N, self.dh)
+        x = self.proj(x)
+        return x
+
+
+class TinyViTBlock(nn.Module):
+    r""" TinyViT Block.
+
+    Args:
+        dim (int): Number of input channels.
+        input_resolution (tuple[int, int]): Input resolution.
+        num_heads (int): Number of attention heads.
+        window_size (int): Window size.
+        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
+        drop (float, optional): Dropout rate. Default: 0.0
+        drop_path (float, optional): Stochastic depth rate. Default: 0.0
+        local_conv_size (int): the kernel size of the convolution between
+                               Attention and MLP. Default: 3
+        activation: the activation function. Default: nn.GELU
+    """
+
+    def __init__(self, dim, input_resolution, num_heads, window_size=7,
+                 mlp_ratio=4., drop=0., drop_path=0.,
+                 local_conv_size=3,
+                 activation=nn.GELU,
+                 ):
+        super().__init__()
+        self.dim = dim
+        self.input_resolution = input_resolution
+        self.num_heads = num_heads
+        assert window_size > 0, 'window_size must be greater than 0'
+        self.window_size = window_size
+        self.mlp_ratio = mlp_ratio
+
+        self.drop_path = DropPath(
+            drop_path) if drop_path > 0. else nn.Identity()
+
+        assert dim % num_heads == 0, 'dim must be divisible by num_heads'
+        head_dim = dim // num_heads
+
+        window_resolution = (window_size, window_size)
+        self.attn = Attention(dim, head_dim, num_heads,
+                              attn_ratio=1, resolution=window_resolution)
+
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        mlp_activation = activation
+        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim,
+                       act_layer=mlp_activation, drop=drop)
+
+        pad = local_conv_size // 2
+        self.local_conv = Conv2d_BN(
+            dim, dim, ks=local_conv_size, stride=1, pad=pad, groups=dim)
+
+    def forward(self, x):
+        H, W = self.input_resolution
+        B, L, C = x.shape
+        assert L == H * W, "input feature has wrong size"
+        res_x = x
+        if H == self.window_size and W == self.window_size:
+            x = self.attn(x)
+        else:
+            x = x.view(B, H, W, C)
+            pad_b = (self.window_size - H %
+                     self.window_size) % self.window_size
+            pad_r = (self.window_size - W %
+                     self.window_size) % self.window_size
+            padding = pad_b > 0 or pad_r > 0
+
+            if padding:
+                x = F.pad(x, (0, 0, 0, pad_r, 0, pad_b))
+
+            pH, pW = H + pad_b, W + pad_r
+            nH = pH // self.window_size
+            nW = pW // self.window_size
+            # window partition
+            x = x.view(B, nH, self.window_size, nW, self.window_size, C).transpose(2, 3).reshape(
+                B * nH * nW, self.window_size * self.window_size, C)
+            x = self.attn(x)
+            # window reverse
+            x = x.view(B, nH, nW, self.window_size, self.window_size,
+                       C).transpose(2, 3).reshape(B, pH, pW, C)
+
+            if padding:
+                x = x[:, :H, :W].contiguous()
+
+            x = x.view(B, L, C)
+
+        x = res_x + self.drop_path(x)
+
+        x = x.transpose(1, 2).reshape(B, C, H, W)
+        x = self.local_conv(x)
+        x = x.view(B, C, L).transpose(1, 2)
+
+        x = x + self.drop_path(self.mlp(x))
+        return x
+
+    def extra_repr(self) -> str:
+        return f"dim={self.dim}, input_resolution={self.input_resolution}, num_heads={self.num_heads}, " \
+               f"window_size={self.window_size}, mlp_ratio={self.mlp_ratio}"
+
+
+class BasicLayer(nn.Module):
+    """ A basic TinyViT layer for one stage.
+
+    Args:
+        dim (int): Number of input channels.
+        input_resolution (tuple[int]): Input resolution.
+        depth (int): Number of blocks.
+        num_heads (int): Number of attention heads.
+        window_size (int): Local window size.
+        mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
+        drop (float, optional): Dropout rate. Default: 0.0
+        drop_path (float | tuple[float], optional): Stochastic depth rate. Default: 0.0
+        downsample (nn.Module | None, optional): Downsample layer at the end of the layer. Default: None
+        use_checkpoint (bool): Whether to use checkpointing to save memory. Default: False.
+        local_conv_size: the kernel size of the depthwise convolution between attention and MLP. Default: 3
+        activation: the activation function. Default: nn.GELU
+        out_dim: the output dimension of the layer. Default: dim
+    """
+
+    def __init__(self, dim, input_resolution, depth, num_heads, window_size,
+                 mlp_ratio=4., drop=0.,
+                 drop_path=0., downsample=None, use_checkpoint=False,
+                 local_conv_size=3,
+                 activation=nn.GELU,
+                 out_dim=None,
+                 ):
+
+        super().__init__()
+        self.dim = dim
+        self.input_resolution = input_resolution
+        self.depth = depth
+        self.use_checkpoint = use_checkpoint
+
+        # build blocks
+        self.blocks = nn.ModuleList([
+            TinyViTBlock(dim=dim, input_resolution=input_resolution,
+                         num_heads=num_heads, window_size=window_size,
+                         mlp_ratio=mlp_ratio,
+                         drop=drop,
+                         drop_path=drop_path[i] if isinstance(
+                             drop_path, list) else drop_path,
+                         local_conv_size=local_conv_size,
+                         activation=activation,
+                         )
+            for i in range(depth)])
+
+        # patch merging layer
+        if downsample is not None:
+            self.downsample = downsample(
+                input_resolution, dim=dim, out_dim=out_dim, activation=activation)
+        else:
+            self.downsample = None
+
+    def forward(self, x):
+        for blk in self.blocks:
+            if self.use_checkpoint:
+                x = checkpoint.checkpoint(blk, x)
+            else:
+                x = blk(x)
+        if self.downsample is not None:
+            x = self.downsample(x)
+        return x
+
+    def extra_repr(self) -> str:
+        return f"dim={self.dim}, input_resolution={self.input_resolution}, depth={self.depth}"
+
+class LayerNorm2d(nn.Module):
+    def __init__(self, num_channels: int, eps: float = 1e-6) -> None:
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(num_channels))
+        self.bias = nn.Parameter(torch.zeros(num_channels))
+        self.eps = eps
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        u = x.mean(1, keepdim=True)
+        s = (x - u).pow(2).mean(1, keepdim=True)
+        x = (x - u) / torch.sqrt(s + self.eps)
+        x = self.weight[:, None, None] * x + self.bias[:, None, None]
+        return x
+class TinyViT(nn.Module):
+    def __init__(self, img_size=224, in_chans=3, num_classes=1000,
+                 embed_dims=[96, 192, 384, 768], depths=[2, 2, 6, 2],
+                 num_heads=[3, 6, 12, 24],
+                 window_sizes=[7, 7, 14, 7],
+                 mlp_ratio=4.,
+                 drop_rate=0.,
+                 drop_path_rate=0.1,
+                 use_checkpoint=False,
+                 mbconv_expand_ratio=4.0,
+                 local_conv_size=3,
+                 layer_lr_decay=1.0,
+                 ):
+        super().__init__()
+        self.img_size=img_size
+        self.num_classes = num_classes
+        self.depths = depths
+        self.num_layers = len(depths)
+        self.mlp_ratio = mlp_ratio
+
+        activation = nn.GELU
+
+        self.patch_embed = PatchEmbed(in_chans=in_chans,
+                                      embed_dim=embed_dims[0],
+                                      resolution=img_size,
+                                      activation=activation)
+
+        patches_resolution = self.patch_embed.patches_resolution
+        self.patches_resolution = patches_resolution
+
+        # stochastic depth
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate,
+                                                sum(depths))]  # stochastic depth decay rule
+
+        # build layers
+        self.layers = nn.ModuleList()
+        for i_layer in range(self.num_layers):
+            kwargs = dict(dim=embed_dims[i_layer],
+                        input_resolution=(patches_resolution[0] // (2 ** (i_layer-1 if i_layer == 3 else i_layer)),
+                                patches_resolution[1] // (2 ** (i_layer-1 if i_layer == 3 else i_layer))),
+                        #   input_resolution=(patches_resolution[0] // (2 ** i_layer),
+                        #                     patches_resolution[1] // (2 ** i_layer)),
+                          depth=depths[i_layer],
+                          drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
+                          downsample=PatchMerging if (
+                              i_layer < self.num_layers - 1) else None,
+                          use_checkpoint=use_checkpoint,
+                          out_dim=embed_dims[min(
+                              i_layer + 1, len(embed_dims) - 1)],
+                          activation=activation,
+                          )
+            if i_layer == 0:
+                layer = ConvLayer(
+                    conv_expand_ratio=mbconv_expand_ratio,
+                    **kwargs,
+                )
+            else:
+                layer = BasicLayer(
+                    num_heads=num_heads[i_layer],
+                    window_size=window_sizes[i_layer],
+                    mlp_ratio=self.mlp_ratio,
+                    drop=drop_rate,
+                    local_conv_size=local_conv_size,
+                    **kwargs)
+            self.layers.append(layer)
+
+        # Classifier head
+        self.norm_head = nn.LayerNorm(embed_dims[-1])
+        self.head = nn.Linear(
+            embed_dims[-1], num_classes) if num_classes > 0 else torch.nn.Identity()
+
+        # init weights
+        self.apply(self._init_weights)
+        self.set_layer_lr_decay(layer_lr_decay)
+        self.neck = nn.Sequential(
+            nn.Conv2d(
+                embed_dims[-1],
+                256,
+                kernel_size=1,
+                bias=False,
+            ),
+            LayerNorm2d(256),
+            nn.Conv2d(
+                256,
+                256,
+                kernel_size=3,
+                padding=1,
+                bias=False,
+            ),
+            LayerNorm2d(256),
+        )
+    def set_layer_lr_decay(self, layer_lr_decay):
+        decay_rate = layer_lr_decay
+
+        # layers -> blocks (depth)
+        depth = sum(self.depths)
+        lr_scales = [decay_rate ** (depth - i - 1) for i in range(depth)]
+        #print("LR SCALES:", lr_scales)
+
+        def _set_lr_scale(m, scale):
+            for p in m.parameters():
+                p.lr_scale = scale
+
+        self.patch_embed.apply(lambda x: _set_lr_scale(x, lr_scales[0]))
+        i = 0
+        for layer in self.layers:
+            for block in layer.blocks:
+                block.apply(lambda x: _set_lr_scale(x, lr_scales[i]))
+                i += 1
+            if layer.downsample is not None:
+                layer.downsample.apply(
+                    lambda x: _set_lr_scale(x, lr_scales[i - 1]))
+        assert i == depth
+        for m in [self.norm_head, self.head]:
+            m.apply(lambda x: _set_lr_scale(x, lr_scales[-1]))
+
+        for k, p in self.named_parameters():
+            p.param_name = k
+
+        def _check_lr_scale(m):
+            for p in m.parameters():
+                assert hasattr(p, 'lr_scale'), p.param_name
+
+        self.apply(_check_lr_scale)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+
+    @torch.jit.ignore
+    def no_weight_decay_keywords(self):
+        return {'attention_biases'}
+
+    def forward_features(self, x):
+        # x: (N, C, H, W)
+        x = self.patch_embed(x)
+
+        x = self.layers[0](x)
+        start_i = 1
+
+        interm_embeddings=[]
+        for i in range(start_i, len(self.layers)):
+            layer = self.layers[i]
+            x = layer(x)
+            # print('x shape:', x.shape, '---i:', i)
+            if i == 1:
+                interm_embeddings.append(x.view(x.shape[0], 64, 64, -1))
+
+        B,_,C=x.size()
+        x = x.view(B, 64, 64, C)
+        x=x.permute(0, 3, 1, 2)
+        x=self.neck(x)
+        return x, interm_embeddings
+
+    def forward(self, x):
+        x, interm_embeddings = self.forward_features(x)
+        #x = self.norm_head(x)
+        #x = self.head(x)
+        # print('come to here is correct'* 3)
+        return x, interm_embeddings
+
+
+_checkpoint_url_format = \
+    'https://github.com/wkcn/TinyViT-model-zoo/releases/download/checkpoints/{}.pth'
+_provided_checkpoints = {
+    'tiny_vit_5m_224': 'tiny_vit_5m_22kto1k_distill',
+    'tiny_vit_11m_224': 'tiny_vit_11m_22kto1k_distill',
+    'tiny_vit_21m_224': 'tiny_vit_21m_22kto1k_distill',
+    'tiny_vit_21m_384': 'tiny_vit_21m_22kto1k_384_distill',
+    'tiny_vit_21m_512': 'tiny_vit_21m_22kto1k_512_distill',
+}
+
+
+def register_tiny_vit_model(fn):
+    '''Register a TinyViT model
+    It is a wrapper of `register_model` with loading the pretrained checkpoint.
+    '''
+    def fn_wrapper(pretrained=False, **kwargs):
+        model = fn()
+        if pretrained:
+            model_name = fn.__name__
+            assert model_name in _provided_checkpoints, \
+                f'Sorry that the checkpoint `{model_name}` is not provided yet.'
+            url = _checkpoint_url_format.format(
+                _provided_checkpoints[model_name])
+            checkpoint = torch.hub.load_state_dict_from_url(
+                url=url,
+                map_location='cpu', check_hash=False,
+            )
+            model.load_state_dict(checkpoint['model'])
+
+        return model
+
+    # rename the name of fn_wrapper
+    fn_wrapper.__name__ = fn.__name__
+    return register_model(fn_wrapper)
+
+
+@register_tiny_vit_model
+def tiny_vit_5m_224(pretrained=False, num_classes=1000, drop_path_rate=0.0):
+    return TinyViT(
+        num_classes=num_classes,
+        embed_dims=[64, 128, 160, 320],
+        depths=[2, 2, 6, 2],
+        num_heads=[2, 4, 5, 10],
+        window_sizes=[7, 7, 14, 7],
+        drop_path_rate=drop_path_rate,
+    )
+
+
+@register_tiny_vit_model
+def tiny_vit_11m_224(pretrained=False, num_classes=1000, drop_path_rate=0.1):
+    return TinyViT(
+        num_classes=num_classes,
+        embed_dims=[64, 128, 256, 448],
+        depths=[2, 2, 6, 2],
+        num_heads=[2, 4, 8, 14],
+        window_sizes=[7, 7, 14, 7],
+        drop_path_rate=drop_path_rate,
+    )
+
+
+@register_tiny_vit_model
+def tiny_vit_21m_224(pretrained=False, num_classes=1000, drop_path_rate=0.2):
+    return TinyViT(
+        num_classes=num_classes,
+        embed_dims=[96, 192, 384, 576],
+        depths=[2, 2, 6, 2],
+        num_heads=[3, 6, 12, 18],
+        window_sizes=[7, 7, 14, 7],
+        drop_path_rate=drop_path_rate,
+    )
+
+
+@register_tiny_vit_model
+def tiny_vit_21m_384(pretrained=False, num_classes=1000, drop_path_rate=0.1):
+    return TinyViT(
+        img_size=384,
+        num_classes=num_classes,
+        embed_dims=[96, 192, 384, 576],
+        depths=[2, 2, 6, 2],
+        num_heads=[3, 6, 12, 18],
+        window_sizes=[12, 12, 24, 12],
+        drop_path_rate=drop_path_rate,
+    )
+
+
+@register_tiny_vit_model
+def tiny_vit_21m_512(pretrained=False, num_classes=1000, drop_path_rate=0.1):
+    return TinyViT(
+        img_size=512,
+        num_classes=num_classes,
+        embed_dims=[96, 192, 384, 576],
+        depths=[2, 2, 6, 2],
+        num_heads=[3, 6, 12, 18],
+        window_sizes=[16, 16, 32, 16],
+        drop_path_rate=drop_path_rate,
+    )

sam2.1HQ/sam-hq-main/build/lib/segment_anything/modeling/transformer.py

@@ -0,0 +1,240 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+from torch import Tensor, nn
+
+import math
+from typing import Tuple, Type
+
+from .common import MLPBlock
+
+
+class TwoWayTransformer(nn.Module):
+    def __init__(
+        self,
+        depth: int,
+        embedding_dim: int,
+        num_heads: int,
+        mlp_dim: int,
+        activation: Type[nn.Module] = nn.ReLU,
+        attention_downsample_rate: int = 2,
+    ) -> None:
+        """
+        A transformer decoder that attends to an input image using
+        queries whose positional embedding is supplied.
+
+        Args:
+          depth (int): number of layers in the transformer
+          embedding_dim (int): the channel dimension for the input embeddings
+          num_heads (int): the number of heads for multihead attention. Must
+            divide embedding_dim
+          mlp_dim (int): the channel dimension internal to the MLP block
+          activation (nn.Module): the activation to use in the MLP block
+        """
+        super().__init__()
+        self.depth = depth
+        self.embedding_dim = embedding_dim
+        self.num_heads = num_heads
+        self.mlp_dim = mlp_dim
+        self.layers = nn.ModuleList()
+
+        for i in range(depth):
+            self.layers.append(
+                TwoWayAttentionBlock(
+                    embedding_dim=embedding_dim,
+                    num_heads=num_heads,
+                    mlp_dim=mlp_dim,
+                    activation=activation,
+                    attention_downsample_rate=attention_downsample_rate,
+                    skip_first_layer_pe=(i == 0),
+                )
+            )
+
+        self.final_attn_token_to_image = Attention(
+            embedding_dim, num_heads, downsample_rate=attention_downsample_rate
+        )
+        self.norm_final_attn = nn.LayerNorm(embedding_dim)
+
+    def forward(
+        self,
+        image_embedding: Tensor,
+        image_pe: Tensor,
+        point_embedding: Tensor,
+    ) -> Tuple[Tensor, Tensor]:
+        """
+        Args:
+          image_embedding (torch.Tensor): image to attend to. Should be shape
+            B x embedding_dim x h x w for any h and w.
+          image_pe (torch.Tensor): the positional encoding to add to the image. Must
+            have the same shape as image_embedding.
+          point_embedding (torch.Tensor): the embedding to add to the query points.
+            Must have shape B x N_points x embedding_dim for any N_points.
+
+        Returns:
+          torch.Tensor: the processed point_embedding
+          torch.Tensor: the processed image_embedding
+        """
+        # BxCxHxW -> BxHWxC == B x N_image_tokens x C
+        bs, c, h, w = image_embedding.shape
+        image_embedding = image_embedding.flatten(2).permute(0, 2, 1)
+        image_pe = image_pe.flatten(2).permute(0, 2, 1)
+
+        # Prepare queries
+        queries = point_embedding
+        keys = image_embedding
+
+        # Apply transformer blocks and final layernorm
+        for layer in self.layers:
+            queries, keys = layer(
+                queries=queries,
+                keys=keys,
+                query_pe=point_embedding,
+                key_pe=image_pe,
+            )
+
+        # Apply the final attention layer from the points to the image
+        q = queries + point_embedding
+        k = keys + image_pe
+        attn_out = self.final_attn_token_to_image(q=q, k=k, v=keys)
+        queries = queries + attn_out
+        queries = self.norm_final_attn(queries)
+
+        return queries, keys
+
+
+class TwoWayAttentionBlock(nn.Module):
+    def __init__(
+        self,
+        embedding_dim: int,
+        num_heads: int,
+        mlp_dim: int = 2048,
+        activation: Type[nn.Module] = nn.ReLU,
+        attention_downsample_rate: int = 2,
+        skip_first_layer_pe: bool = False,
+    ) -> None:
+        """
+        A transformer block with four layers: (1) self-attention of sparse
+        inputs, (2) cross attention of sparse inputs to dense inputs, (3) mlp
+        block on sparse inputs, and (4) cross attention of dense inputs to sparse
+        inputs.
+
+        Arguments:
+          embedding_dim (int): the channel dimension of the embeddings
+          num_heads (int): the number of heads in the attention layers
+          mlp_dim (int): the hidden dimension of the mlp block
+          activation (nn.Module): the activation of the mlp block
+          skip_first_layer_pe (bool): skip the PE on the first layer
+        """
+        super().__init__()
+        self.self_attn = Attention(embedding_dim, num_heads)
+        self.norm1 = nn.LayerNorm(embedding_dim)
+
+        self.cross_attn_token_to_image = Attention(
+            embedding_dim, num_heads, downsample_rate=attention_downsample_rate
+        )
+        self.norm2 = nn.LayerNorm(embedding_dim)
+
+        self.mlp = MLPBlock(embedding_dim, mlp_dim, activation)
+        self.norm3 = nn.LayerNorm(embedding_dim)
+
+        self.norm4 = nn.LayerNorm(embedding_dim)
+        self.cross_attn_image_to_token = Attention(
+            embedding_dim, num_heads, downsample_rate=attention_downsample_rate
+        )
+
+        self.skip_first_layer_pe = skip_first_layer_pe
+
+    def forward(
+        self, queries: Tensor, keys: Tensor, query_pe: Tensor, key_pe: Tensor
+    ) -> Tuple[Tensor, Tensor]:
+        # Self attention block
+        if self.skip_first_layer_pe:
+            queries = self.self_attn(q=queries, k=queries, v=queries)
+        else:
+            q = queries + query_pe
+            attn_out = self.self_attn(q=q, k=q, v=queries)
+            queries = queries + attn_out
+        queries = self.norm1(queries)
+
+        # Cross attention block, tokens attending to image embedding
+        q = queries + query_pe
+        k = keys + key_pe
+        attn_out = self.cross_attn_token_to_image(q=q, k=k, v=keys)
+        queries = queries + attn_out
+        queries = self.norm2(queries)
+
+        # MLP block
+        mlp_out = self.mlp(queries)
+        queries = queries + mlp_out
+        queries = self.norm3(queries)
+
+        # Cross attention block, image embedding attending to tokens
+        q = queries + query_pe
+        k = keys + key_pe
+        attn_out = self.cross_attn_image_to_token(q=k, k=q, v=queries)
+        keys = keys + attn_out
+        keys = self.norm4(keys)
+
+        return queries, keys
+
+
+class Attention(nn.Module):
+    """
+    An attention layer that allows for downscaling the size of the embedding
+    after projection to queries, keys, and values.
+    """
+
+    def __init__(
+        self,
+        embedding_dim: int,
+        num_heads: int,
+        downsample_rate: int = 1,
+    ) -> None:
+        super().__init__()
+        self.embedding_dim = embedding_dim
+        self.internal_dim = embedding_dim // downsample_rate
+        self.num_heads = num_heads
+        assert self.internal_dim % num_heads == 0, "num_heads must divide embedding_dim."
+
+        self.q_proj = nn.Linear(embedding_dim, self.internal_dim)
+        self.k_proj = nn.Linear(embedding_dim, self.internal_dim)
+        self.v_proj = nn.Linear(embedding_dim, self.internal_dim)
+        self.out_proj = nn.Linear(self.internal_dim, embedding_dim)
+
+    def _separate_heads(self, x: Tensor, num_heads: int) -> Tensor:
+        b, n, c = x.shape
+        x = x.reshape(b, n, num_heads, c // num_heads)
+        return x.transpose(1, 2)  # B x N_heads x N_tokens x C_per_head
+
+    def _recombine_heads(self, x: Tensor) -> Tensor:
+        b, n_heads, n_tokens, c_per_head = x.shape
+        x = x.transpose(1, 2)
+        return x.reshape(b, n_tokens, n_heads * c_per_head)  # B x N_tokens x C
+
+    def forward(self, q: Tensor, k: Tensor, v: Tensor) -> Tensor:
+        # Input projections
+        q = self.q_proj(q)
+        k = self.k_proj(k)
+        v = self.v_proj(v)
+
+        # Separate into heads
+        q = self._separate_heads(q, self.num_heads)
+        k = self._separate_heads(k, self.num_heads)
+        v = self._separate_heads(v, self.num_heads)
+
+        # Attention
+        _, _, _, c_per_head = q.shape
+        attn = q @ k.permute(0, 1, 3, 2)  # B x N_heads x N_tokens x N_tokens
+        attn = attn / math.sqrt(c_per_head)
+        attn = torch.softmax(attn, dim=-1)
+
+        # Get output
+        out = attn @ v
+        out = self._recombine_heads(out)
+        out = self.out_proj(out)
+
+        return out

sam2.1HQ/sam-hq-main/build/lib/segment_anything/predictor.py

@@ -0,0 +1,276 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import numpy as np
+import torch
+
+from .modeling import Sam
+
+from typing import Optional, Tuple
+
+from .utils.transforms import ResizeLongestSide
+
+
+class SamPredictor:
+    def __init__(
+        self,
+        sam_model: Sam,
+    ) -> None:
+        """
+        Uses SAM to calculate the image embedding for an image, and then
+        allow repeated, efficient mask prediction given prompts.
+
+        Arguments:
+          sam_model (Sam): The model to use for mask prediction.
+        """
+        super().__init__()
+        self.model = sam_model
+        self.transform = ResizeLongestSide(sam_model.image_encoder.img_size)
+        self.reset_image()
+
+    def set_image(
+        self,
+        image: np.ndarray,
+        image_format: str = "RGB",
+    ) -> None:
+        """
+        Calculates the image embeddings for the provided image, allowing
+        masks to be predicted with the 'predict' method.
+
+        Arguments:
+          image (np.ndarray): The image for calculating masks. Expects an
+            image in HWC uint8 format, with pixel values in [0, 255].
+          image_format (str): The color format of the image, in ['RGB', 'BGR'].
+        """
+        assert image_format in [
+            "RGB",
+            "BGR",
+        ], f"image_format must be in ['RGB', 'BGR'], is {image_format}."
+        # import pdb;pdb.set_trace()
+        if image_format != self.model.image_format:
+            image = image[..., ::-1]
+
+        # Transform the image to the form expected by the model
+        # import pdb;pdb.set_trace()
+        input_image = self.transform.apply_image(image)
+        input_image_torch = torch.as_tensor(input_image, device=self.device)
+        input_image_torch = input_image_torch.permute(2, 0, 1).contiguous()[None, :, :, :]
+
+        self.set_torch_image(input_image_torch, image.shape[:2])
+
+    @torch.no_grad()
+    def set_torch_image(
+        self,
+        transformed_image: torch.Tensor,
+        original_image_size: Tuple[int, ...],
+    ) -> None:
+        """
+        Calculates the image embeddings for the provided image, allowing
+        masks to be predicted with the 'predict' method. Expects the input
+        image to be already transformed to the format expected by the model.
+
+        Arguments:
+          transformed_image (torch.Tensor): The input image, with shape
+            1x3xHxW, which has been transformed with ResizeLongestSide.
+          original_image_size (tuple(int, int)): The size of the image
+            before transformation, in (H, W) format.
+        """
+        assert (
+            len(transformed_image.shape) == 4
+            and transformed_image.shape[1] == 3
+            and max(*transformed_image.shape[2:]) == self.model.image_encoder.img_size
+        ), f"set_torch_image input must be BCHW with long side {self.model.image_encoder.img_size}."
+        self.reset_image()
+
+        self.original_size = original_image_size
+        self.input_size = tuple(transformed_image.shape[-2:])
+        input_image = self.model.preprocess(transformed_image)
+        self.features, self.interm_features = self.model.image_encoder(input_image)
+        self.is_image_set = True
+
+    def predict(
+        self,
+        point_coords: Optional[np.ndarray] = None,
+        point_labels: Optional[np.ndarray] = None,
+        box: Optional[np.ndarray] = None,
+        mask_input: Optional[np.ndarray] = None,
+        multimask_output: bool = True,
+        return_logits: bool = False,
+        hq_token_only: bool =False,
+    ) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
+        """
+        Predict masks for the given input prompts, using the currently set image.
+
+        Arguments:
+          point_coords (np.ndarray or None): A Nx2 array of point prompts to the
+            model. Each point is in (X,Y) in pixels.
+          point_labels (np.ndarray or None): A length N array of labels for the
+            point prompts. 1 indicates a foreground point and 0 indicates a
+            background point.
+          box (np.ndarray or None): A length 4 array given a box prompt to the
+            model, in XYXY format.
+          mask_input (np.ndarray): A low resolution mask input to the model, typically
+            coming from a previous prediction iteration. Has form 1xHxW, where
+            for SAM, H=W=256.
+          multimask_output (bool): If true, the model will return three masks.
+            For ambiguous input prompts (such as a single click), this will often
+            produce better masks than a single prediction. If only a single
+            mask is needed, the model's predicted quality score can be used
+            to select the best mask. For non-ambiguous prompts, such as multiple
+            input prompts, multimask_output=False can give better results.
+          return_logits (bool): If true, returns un-thresholded masks logits
+            instead of a binary mask.
+
+        Returns:
+          (np.ndarray): The output masks in CxHxW format, where C is the
+            number of masks, and (H, W) is the original image size.
+          (np.ndarray): An array of length C containing the model's
+            predictions for the quality of each mask.
+          (np.ndarray): An array of shape CxHxW, where C is the number
+            of masks and H=W=256. These low resolution logits can be passed to
+            a subsequent iteration as mask input.
+        """
+        if not self.is_image_set:
+            raise RuntimeError("An image must be set with .set_image(...) before mask prediction.")
+
+        # Transform input prompts
+        coords_torch, labels_torch, box_torch, mask_input_torch = None, None, None, None
+        if point_coords is not None:
+            assert (
+                point_labels is not None
+            ), "point_labels must be supplied if point_coords is supplied."
+            point_coords = self.transform.apply_coords(point_coords, self.original_size)
+            coords_torch = torch.as_tensor(point_coords, dtype=torch.float, device=self.device)
+            labels_torch = torch.as_tensor(point_labels, dtype=torch.int, device=self.device)
+            coords_torch, labels_torch = coords_torch[None, :, :], labels_torch[None, :]
+        if box is not None:
+            box = self.transform.apply_boxes(box, self.original_size)
+            box_torch = torch.as_tensor(box, dtype=torch.float, device=self.device)
+            box_torch = box_torch[None, :]
+        if mask_input is not None:
+            mask_input_torch = torch.as_tensor(mask_input, dtype=torch.float, device=self.device)
+            mask_input_torch = mask_input_torch[None, :, :, :]
+
+        masks, iou_predictions, low_res_masks = self.predict_torch(
+            coords_torch,
+            labels_torch,
+            box_torch,
+            mask_input_torch,
+            multimask_output,
+            return_logits=return_logits,
+            hq_token_only=hq_token_only,
+        )
+
+        masks_np = masks[0].detach().cpu().numpy()
+        iou_predictions_np = iou_predictions[0].detach().cpu().numpy()
+        low_res_masks_np = low_res_masks[0].detach().cpu().numpy()
+        return masks_np, iou_predictions_np, low_res_masks_np
+
+    @torch.no_grad()
+    def predict_torch(
+        self,
+        point_coords: Optional[torch.Tensor],
+        point_labels: Optional[torch.Tensor],
+        boxes: Optional[torch.Tensor] = None,
+        mask_input: Optional[torch.Tensor] = None,
+        multimask_output: bool = True,
+        return_logits: bool = False,
+        hq_token_only: bool =False,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        """
+        Predict masks for the given input prompts, using the currently set image.
+        Input prompts are batched torch tensors and are expected to already be
+        transformed to the input frame using ResizeLongestSide.
+
+        Arguments:
+          point_coords (torch.Tensor or None): A BxNx2 array of point prompts to the
+            model. Each point is in (X,Y) in pixels.
+          point_labels (torch.Tensor or None): A BxN array of labels for the
+            point prompts. 1 indicates a foreground point and 0 indicates a
+            background point.
+          boxes (np.ndarray or None): A Bx4 array given a box prompt to the
+            model, in XYXY format.
+          mask_input (np.ndarray): A low resolution mask input to the model, typically
+            coming from a previous prediction iteration. Has form Bx1xHxW, where
+            for SAM, H=W=256. Masks returned by a previous iteration of the
+            predict method do not need further transformation.
+          multimask_output (bool): If true, the model will return three masks.
+            For ambiguous input prompts (such as a single click), this will often
+            produce better masks than a single prediction. If only a single
+            mask is needed, the model's predicted quality score can be used
+            to select the best mask. For non-ambiguous prompts, such as multiple
+            input prompts, multimask_output=False can give better results.
+          return_logits (bool): If true, returns un-thresholded masks logits
+            instead of a binary mask.
+
+        Returns:
+          (torch.Tensor): The output masks in BxCxHxW format, where C is the
+            number of masks, and (H, W) is the original image size.
+          (torch.Tensor): An array of shape BxC containing the model's
+            predictions for the quality of each mask.
+          (torch.Tensor): An array of shape BxCxHxW, where C is the number
+            of masks and H=W=256. These low res logits can be passed to
+            a subsequent iteration as mask input.
+        """
+        if not self.is_image_set:
+            raise RuntimeError("An image must be set with .set_image(...) before mask prediction.")
+
+        if point_coords is not None:
+            points = (point_coords, point_labels)
+        else:
+            points = None
+
+        # Embed prompts
+        sparse_embeddings, dense_embeddings = self.model.prompt_encoder(
+            points=points,
+            boxes=boxes,
+            masks=mask_input,
+        )
+
+        # Predict masks
+        low_res_masks, iou_predictions = self.model.mask_decoder(
+            image_embeddings=self.features,
+            image_pe=self.model.prompt_encoder.get_dense_pe(),
+            sparse_prompt_embeddings=sparse_embeddings,
+            dense_prompt_embeddings=dense_embeddings,
+            multimask_output=multimask_output,
+            hq_token_only=hq_token_only,
+            interm_embeddings=self.interm_features,
+        )
+
+        # Upscale the masks to the original image resolution
+        masks = self.model.postprocess_masks(low_res_masks, self.input_size, self.original_size)
+
+        if not return_logits:
+            masks = masks > self.model.mask_threshold
+
+        return masks, iou_predictions, low_res_masks
+
+    def get_image_embedding(self) -> torch.Tensor:
+        """
+        Returns the image embeddings for the currently set image, with
+        shape 1xCxHxW, where C is the embedding dimension and (H,W) are
+        the embedding spatial dimension of SAM (typically C=256, H=W=64).
+        """
+        if not self.is_image_set:
+            raise RuntimeError(
+                "An image must be set with .set_image(...) to generate an embedding."
+            )
+        assert self.features is not None, "Features must exist if an image has been set."
+        return self.features
+
+    @property
+    def device(self) -> torch.device:
+        return self.model.device
+
+    def reset_image(self) -> None:
+        """Resets the currently set image."""
+        self.is_image_set = False
+        self.features = None
+        self.orig_h = None
+        self.orig_w = None
+        self.input_h = None
+        self.input_w = None

sam2.1HQ/sam-hq-main/build/lib/segment_anything/utils/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.

sam2.1HQ/sam-hq-main/build/lib/segment_anything/utils/amg.py

@@ -0,0 +1,346 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import numpy as np
+import torch
+
+import math
+from copy import deepcopy
+from itertools import product
+from typing import Any, Dict, Generator, ItemsView, List, Tuple
+
+
+class MaskData:
+    """
+    A structure for storing masks and their related data in batched format.
+    Implements basic filtering and concatenation.
+    """
+
+    def __init__(self, **kwargs) -> None:
+        for v in kwargs.values():
+            assert isinstance(
+                v, (list, np.ndarray, torch.Tensor)
+            ), "MaskData only supports list, numpy arrays, and torch tensors."
+        self._stats = dict(**kwargs)
+
+    def __setitem__(self, key: str, item: Any) -> None:
+        assert isinstance(
+            item, (list, np.ndarray, torch.Tensor)
+        ), "MaskData only supports list, numpy arrays, and torch tensors."
+        self._stats[key] = item
+
+    def __delitem__(self, key: str) -> None:
+        del self._stats[key]
+
+    def __getitem__(self, key: str) -> Any:
+        return self._stats[key]
+
+    def items(self) -> ItemsView[str, Any]:
+        return self._stats.items()
+
+    def filter(self, keep: torch.Tensor) -> None:
+        for k, v in self._stats.items():
+            if v is None:
+                self._stats[k] = None
+            elif isinstance(v, torch.Tensor):
+                self._stats[k] = v[torch.as_tensor(keep, device=v.device)]
+            elif isinstance(v, np.ndarray):
+                self._stats[k] = v[keep.detach().cpu().numpy()]
+            elif isinstance(v, list) and keep.dtype == torch.bool:
+                self._stats[k] = [a for i, a in enumerate(v) if keep[i]]
+            elif isinstance(v, list):
+                self._stats[k] = [v[i] for i in keep]
+            else:
+                raise TypeError(f"MaskData key {k} has an unsupported type {type(v)}.")
+
+    def cat(self, new_stats: "MaskData") -> None:
+        for k, v in new_stats.items():
+            if k not in self._stats or self._stats[k] is None:
+                self._stats[k] = deepcopy(v)
+            elif isinstance(v, torch.Tensor):
+                self._stats[k] = torch.cat([self._stats[k], v], dim=0)
+            elif isinstance(v, np.ndarray):
+                self._stats[k] = np.concatenate([self._stats[k], v], axis=0)
+            elif isinstance(v, list):
+                self._stats[k] = self._stats[k] + deepcopy(v)
+            else:
+                raise TypeError(f"MaskData key {k} has an unsupported type {type(v)}.")
+
+    def to_numpy(self) -> None:
+        for k, v in self._stats.items():
+            if isinstance(v, torch.Tensor):
+                self._stats[k] = v.detach().cpu().numpy()
+
+
+def is_box_near_crop_edge(
+    boxes: torch.Tensor, crop_box: List[int], orig_box: List[int], atol: float = 20.0
+) -> torch.Tensor:
+    """Filter masks at the edge of a crop, but not at the edge of the original image."""
+    crop_box_torch = torch.as_tensor(crop_box, dtype=torch.float, device=boxes.device)
+    orig_box_torch = torch.as_tensor(orig_box, dtype=torch.float, device=boxes.device)
+    boxes = uncrop_boxes_xyxy(boxes, crop_box).float()
+    near_crop_edge = torch.isclose(boxes, crop_box_torch[None, :], atol=atol, rtol=0)
+    near_image_edge = torch.isclose(boxes, orig_box_torch[None, :], atol=atol, rtol=0)
+    near_crop_edge = torch.logical_and(near_crop_edge, ~near_image_edge)
+    return torch.any(near_crop_edge, dim=1)
+
+
+def box_xyxy_to_xywh(box_xyxy: torch.Tensor) -> torch.Tensor:
+    box_xywh = deepcopy(box_xyxy)
+    box_xywh[2] = box_xywh[2] - box_xywh[0]
+    box_xywh[3] = box_xywh[3] - box_xywh[1]
+    return box_xywh
+
+
+def batch_iterator(batch_size: int, *args) -> Generator[List[Any], None, None]:
+    assert len(args) > 0 and all(
+        len(a) == len(args[0]) for a in args
+    ), "Batched iteration must have inputs of all the same size."
+    n_batches = len(args[0]) // batch_size + int(len(args[0]) % batch_size != 0)
+    for b in range(n_batches):
+        yield [arg[b * batch_size : (b + 1) * batch_size] for arg in args]
+
+
+def mask_to_rle_pytorch(tensor: torch.Tensor) -> List[Dict[str, Any]]:
+    """
+    Encodes masks to an uncompressed RLE, in the format expected by
+    pycoco tools.
+    """
+    # Put in fortran order and flatten h,w
+    b, h, w = tensor.shape
+    tensor = tensor.permute(0, 2, 1).flatten(1)
+
+    # Compute change indices
+    diff = tensor[:, 1:] ^ tensor[:, :-1]
+    change_indices = diff.nonzero()
+
+    # Encode run length
+    out = []
+    for i in range(b):
+        cur_idxs = change_indices[change_indices[:, 0] == i, 1]
+        cur_idxs = torch.cat(
+            [
+                torch.tensor([0], dtype=cur_idxs.dtype, device=cur_idxs.device),
+                cur_idxs + 1,
+                torch.tensor([h * w], dtype=cur_idxs.dtype, device=cur_idxs.device),
+            ]
+        )
+        btw_idxs = cur_idxs[1:] - cur_idxs[:-1]
+        counts = [] if tensor[i, 0] == 0 else [0]
+        counts.extend(btw_idxs.detach().cpu().tolist())
+        out.append({"size": [h, w], "counts": counts})
+    return out
+
+
+def rle_to_mask(rle: Dict[str, Any]) -> np.ndarray:
+    """Compute a binary mask from an uncompressed RLE."""
+    h, w = rle["size"]
+    mask = np.empty(h * w, dtype=bool)
+    idx = 0
+    parity = False
+    for count in rle["counts"]:
+        mask[idx : idx + count] = parity
+        idx += count
+        parity ^= True
+    mask = mask.reshape(w, h)
+    return mask.transpose()  # Put in C order
+
+
+def area_from_rle(rle: Dict[str, Any]) -> int:
+    return sum(rle["counts"][1::2])
+
+
+def calculate_stability_score(
+    masks: torch.Tensor, mask_threshold: float, threshold_offset: float
+) -> torch.Tensor:
+    """
+    Computes the stability score for a batch of masks. The stability
+    score is the IoU between the binary masks obtained by thresholding
+    the predicted mask logits at high and low values.
+    """
+    # One mask is always contained inside the other.
+    # Save memory by preventing unnecessary cast to torch.int64
+    intersections = (
+        (masks > (mask_threshold + threshold_offset))
+        .sum(-1, dtype=torch.int16)
+        .sum(-1, dtype=torch.int32)
+    )
+    unions = (
+        (masks > (mask_threshold - threshold_offset))
+        .sum(-1, dtype=torch.int16)
+        .sum(-1, dtype=torch.int32)
+    )
+    return intersections / unions
+
+
+def build_point_grid(n_per_side: int) -> np.ndarray:
+    """Generates a 2D grid of points evenly spaced in [0,1]x[0,1]."""
+    offset = 1 / (2 * n_per_side)
+    points_one_side = np.linspace(offset, 1 - offset, n_per_side)
+    points_x = np.tile(points_one_side[None, :], (n_per_side, 1))
+    points_y = np.tile(points_one_side[:, None], (1, n_per_side))
+    points = np.stack([points_x, points_y], axis=-1).reshape(-1, 2)
+    return points
+
+
+def build_all_layer_point_grids(
+    n_per_side: int, n_layers: int, scale_per_layer: int
+) -> List[np.ndarray]:
+    """Generates point grids for all crop layers."""
+    points_by_layer = []
+    for i in range(n_layers + 1):
+        n_points = int(n_per_side / (scale_per_layer**i))
+        points_by_layer.append(build_point_grid(n_points))
+    return points_by_layer
+
+
+def generate_crop_boxes(
+    im_size: Tuple[int, ...], n_layers: int, overlap_ratio: float
+) -> Tuple[List[List[int]], List[int]]:
+    """
+    Generates a list of crop boxes of different sizes. Each layer
+    has (2**i)**2 boxes for the ith layer.
+    """
+    crop_boxes, layer_idxs = [], []
+    im_h, im_w = im_size
+    short_side = min(im_h, im_w)
+
+    # Original image
+    crop_boxes.append([0, 0, im_w, im_h])
+    layer_idxs.append(0)
+
+    def crop_len(orig_len, n_crops, overlap):
+        return int(math.ceil((overlap * (n_crops - 1) + orig_len) / n_crops))
+
+    for i_layer in range(n_layers):
+        n_crops_per_side = 2 ** (i_layer + 1)
+        overlap = int(overlap_ratio * short_side * (2 / n_crops_per_side))
+
+        crop_w = crop_len(im_w, n_crops_per_side, overlap)
+        crop_h = crop_len(im_h, n_crops_per_side, overlap)
+
+        crop_box_x0 = [int((crop_w - overlap) * i) for i in range(n_crops_per_side)]
+        crop_box_y0 = [int((crop_h - overlap) * i) for i in range(n_crops_per_side)]
+
+        # Crops in XYWH format
+        for x0, y0 in product(crop_box_x0, crop_box_y0):
+            box = [x0, y0, min(x0 + crop_w, im_w), min(y0 + crop_h, im_h)]
+            crop_boxes.append(box)
+            layer_idxs.append(i_layer + 1)
+
+    return crop_boxes, layer_idxs
+
+
+def uncrop_boxes_xyxy(boxes: torch.Tensor, crop_box: List[int]) -> torch.Tensor:
+    x0, y0, _, _ = crop_box
+    offset = torch.tensor([[x0, y0, x0, y0]], device=boxes.device)
+    # Check if boxes has a channel dimension
+    if len(boxes.shape) == 3:
+        offset = offset.unsqueeze(1)
+    return boxes + offset
+
+
+def uncrop_points(points: torch.Tensor, crop_box: List[int]) -> torch.Tensor:
+    x0, y0, _, _ = crop_box
+    offset = torch.tensor([[x0, y0]], device=points.device)
+    # Check if points has a channel dimension
+    if len(points.shape) == 3:
+        offset = offset.unsqueeze(1)
+    return points + offset
+
+
+def uncrop_masks(
+    masks: torch.Tensor, crop_box: List[int], orig_h: int, orig_w: int
+) -> torch.Tensor:
+    x0, y0, x1, y1 = crop_box
+    if x0 == 0 and y0 == 0 and x1 == orig_w and y1 == orig_h:
+        return masks
+    # Coordinate transform masks
+    pad_x, pad_y = orig_w - (x1 - x0), orig_h - (y1 - y0)
+    pad = (x0, pad_x - x0, y0, pad_y - y0)
+    return torch.nn.functional.pad(masks, pad, value=0)
+
+
+def remove_small_regions(
+    mask: np.ndarray, area_thresh: float, mode: str
+) -> Tuple[np.ndarray, bool]:
+    """
+    Removes small disconnected regions and holes in a mask. Returns the
+    mask and an indicator of if the mask has been modified.
+    """
+    import cv2  # type: ignore
+
+    assert mode in ["holes", "islands"]
+    correct_holes = mode == "holes"
+    working_mask = (correct_holes ^ mask).astype(np.uint8)
+    n_labels, regions, stats, _ = cv2.connectedComponentsWithStats(working_mask, 8)
+    sizes = stats[:, -1][1:]  # Row 0 is background label
+    small_regions = [i + 1 for i, s in enumerate(sizes) if s < area_thresh]
+    if len(small_regions) == 0:
+        return mask, False
+    fill_labels = [0] + small_regions
+    if not correct_holes:
+        fill_labels = [i for i in range(n_labels) if i not in fill_labels]
+        # If every region is below threshold, keep largest
+        if len(fill_labels) == 0:
+            fill_labels = [int(np.argmax(sizes)) + 1]
+    mask = np.isin(regions, fill_labels)
+    return mask, True
+
+
+def coco_encode_rle(uncompressed_rle: Dict[str, Any]) -> Dict[str, Any]:
+    from pycocotools import mask as mask_utils  # type: ignore
+
+    h, w = uncompressed_rle["size"]
+    rle = mask_utils.frPyObjects(uncompressed_rle, h, w)
+    rle["counts"] = rle["counts"].decode("utf-8")  # Necessary to serialize with json
+    return rle
+
+
+def batched_mask_to_box(masks: torch.Tensor) -> torch.Tensor:
+    """
+    Calculates boxes in XYXY format around masks. Return [0,0,0,0] for
+    an empty mask. For input shape C1xC2x...xHxW, the output shape is C1xC2x...x4.
+    """
+    # torch.max below raises an error on empty inputs, just skip in this case
+    if torch.numel(masks) == 0:
+        return torch.zeros(*masks.shape[:-2], 4, device=masks.device)
+
+    # Normalize shape to CxHxW
+    shape = masks.shape
+    h, w = shape[-2:]
+    if len(shape) > 2:
+        masks = masks.flatten(0, -3)
+    else:
+        masks = masks.unsqueeze(0)
+
+    # Get top and bottom edges
+    in_height, _ = torch.max(masks, dim=-1)
+    in_height_coords = in_height * torch.arange(h, device=in_height.device)[None, :]
+    bottom_edges, _ = torch.max(in_height_coords, dim=-1)
+    in_height_coords = in_height_coords + h * (~in_height)
+    top_edges, _ = torch.min(in_height_coords, dim=-1)
+
+    # Get left and right edges
+    in_width, _ = torch.max(masks, dim=-2)
+    in_width_coords = in_width * torch.arange(w, device=in_width.device)[None, :]
+    right_edges, _ = torch.max(in_width_coords, dim=-1)
+    in_width_coords = in_width_coords + w * (~in_width)
+    left_edges, _ = torch.min(in_width_coords, dim=-1)
+
+    # If the mask is empty the right edge will be to the left of the left edge.
+    # Replace these boxes with [0, 0, 0, 0]
+    empty_filter = (right_edges < left_edges) | (bottom_edges < top_edges)
+    out = torch.stack([left_edges, top_edges, right_edges, bottom_edges], dim=-1)
+    out = out * (~empty_filter).unsqueeze(-1)
+
+    # Return to original shape
+    if len(shape) > 2:
+        out = out.reshape(*shape[:-2], 4)
+    else:
+        out = out[0]
+
+    return out

sam2.1HQ/sam-hq-main/build/lib/segment_anything/utils/onnx.py

@@ -0,0 +1,155 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+from typing import Tuple
+
+from ..modeling import Sam
+from .amg import calculate_stability_score
+
+
+class SamOnnxModel(nn.Module):
+    """
+    This model should not be called directly, but is used in ONNX export.
+    It combines the prompt encoder, mask decoder, and mask postprocessing of Sam,
+    with some functions modified to enable model tracing. Also supports extra
+    options controlling what information. See the ONNX export script for details.
+    """
+
+    def __init__(
+        self,
+        model: Sam,
+        hq_token_only: bool = False,
+        multimask_output: bool = False,
+        use_stability_score: bool = False,
+        return_extra_metrics: bool = False,
+    ) -> None:
+        super().__init__()
+        self.mask_decoder = model.mask_decoder
+        self.model = model
+        self.img_size = model.image_encoder.img_size
+        self.hq_token_only = hq_token_only
+        self.multimask_output = multimask_output
+        self.use_stability_score = use_stability_score
+        self.stability_score_offset = 1.0
+        self.return_extra_metrics = return_extra_metrics
+
+    @staticmethod
+    def resize_longest_image_size(
+        input_image_size: torch.Tensor, longest_side: int
+    ) -> torch.Tensor:
+        input_image_size = input_image_size.to(torch.float32)
+        scale = longest_side / torch.max(input_image_size)
+        transformed_size = scale * input_image_size
+        transformed_size = torch.floor(transformed_size + 0.5).to(torch.int64)
+        return transformed_size
+
+    def _embed_points(self, point_coords: torch.Tensor, point_labels: torch.Tensor) -> torch.Tensor:
+        point_coords = point_coords + 0.5
+        point_coords = point_coords / self.img_size
+        point_embedding = self.model.prompt_encoder.pe_layer._pe_encoding(point_coords)
+        point_labels = point_labels.unsqueeze(-1).expand_as(point_embedding)
+
+        point_embedding = point_embedding * (point_labels != -1)
+        point_embedding = point_embedding + self.model.prompt_encoder.not_a_point_embed.weight * (
+            point_labels == -1
+        )
+
+        for i in range(self.model.prompt_encoder.num_point_embeddings):
+            point_embedding = point_embedding + self.model.prompt_encoder.point_embeddings[
+                i
+            ].weight * (point_labels == i)
+
+        return point_embedding
+
+    def _embed_masks(self, input_mask: torch.Tensor, has_mask_input: torch.Tensor) -> torch.Tensor:
+        mask_embedding = has_mask_input * self.model.prompt_encoder.mask_downscaling(input_mask)
+        mask_embedding = mask_embedding + (
+            1 - has_mask_input
+        ) * self.model.prompt_encoder.no_mask_embed.weight.reshape(1, -1, 1, 1)
+        return mask_embedding
+
+    def mask_postprocessing(self, masks: torch.Tensor, orig_im_size: torch.Tensor) -> torch.Tensor:
+        masks = F.interpolate(
+            masks,
+            size=(self.img_size, self.img_size),
+            mode="bilinear",
+            align_corners=False,
+        )
+
+        prepadded_size = self.resize_longest_image_size(orig_im_size, self.img_size).to(torch.int64)
+        masks = masks[..., : prepadded_size[0], : prepadded_size[1]]  # type: ignore
+
+        orig_im_size = orig_im_size.to(torch.int64)
+        h, w = orig_im_size[0], orig_im_size[1]
+        masks = F.interpolate(masks, size=(h, w), mode="bilinear", align_corners=False)
+        return masks
+
+
+    @torch.no_grad()
+    def forward(
+        self,
+        image_embeddings: torch.Tensor,
+        interm_embeddings: torch.Tensor,
+        point_coords: torch.Tensor,
+        point_labels: torch.Tensor,
+        mask_input: torch.Tensor,
+        has_mask_input: torch.Tensor,
+        orig_im_size: torch.Tensor,
+    ):
+        sparse_embedding = self._embed_points(point_coords, point_labels)
+        dense_embedding = self._embed_masks(mask_input, has_mask_input)
+
+        vit_features = interm_embeddings[0].permute(0, 3, 1, 2) # early-layer ViT feature, after 1st global attention block in ViT
+        hq_features = self.model.mask_decoder.embedding_encoder(image_embeddings) + self.model.mask_decoder.compress_vit_feat(vit_features)
+
+        masks, scores = self.model.mask_decoder.predict_masks(
+            image_embeddings=image_embeddings,
+            image_pe=self.model.prompt_encoder.get_dense_pe(),
+            sparse_prompt_embeddings=sparse_embedding,
+            dense_prompt_embeddings=dense_embedding,
+            hq_features=hq_features,
+        )
+
+        if self.use_stability_score:
+            scores = calculate_stability_score(
+                masks, self.model.mask_threshold, self.stability_score_offset
+            )
+
+        if self.multimask_output:
+            # mask with highest score
+            mask_slice = slice(1,self.model.mask_decoder.num_mask_tokens-1)
+            scores = scores[:, mask_slice]
+            scores, max_iou_idx = torch.max(scores,dim=1)
+            scores = scores.unsqueeze(1)
+            masks_multi = masks[:, mask_slice, :, :]
+            masks_sam = masks_multi[torch.arange(masks_multi.size(0)),max_iou_idx].unsqueeze(1)
+        else:
+            # singale mask output, default
+            mask_slice = slice(0, 1)
+            scores = scores[:,mask_slice]
+            masks_sam = masks[:,mask_slice]
+
+        masks_hq = masks[:,slice(self.model.mask_decoder.num_mask_tokens-1, self.model.mask_decoder.num_mask_tokens)]
+
+        if self.hq_token_only:
+            masks = masks_hq
+        else:
+            masks = masks_sam + masks_hq
+
+        upscaled_masks = self.mask_postprocessing(masks, orig_im_size)
+
+        if self.return_extra_metrics:
+            stability_scores = calculate_stability_score(
+                upscaled_masks, self.model.mask_threshold, self.stability_score_offset
+            )
+            areas = (upscaled_masks > self.model.mask_threshold).sum(-1).sum(-1)
+            return upscaled_masks, scores, stability_scores, areas, masks
+
+        return upscaled_masks, scores, masks

sam2.1HQ/sam-hq-main/build/lib/segment_anything/utils/transforms.py

@@ -0,0 +1,102 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+import numpy as np
+import torch
+from torch.nn import functional as F
+from torchvision.transforms.functional import resize, to_pil_image  # type: ignore
+
+from copy import deepcopy
+from typing import Tuple
+
+
+class ResizeLongestSide:
+    """
+    Resizes images to the longest side 'target_length', as well as provides
+    methods for resizing coordinates and boxes. Provides methods for
+    transforming both numpy array and batched torch tensors.
+    """
+
+    def __init__(self, target_length: int) -> None:
+        self.target_length = target_length
+
+    def apply_image(self, image: np.ndarray) -> np.ndarray:
+        """
+        Expects a numpy array with shape HxWxC in uint8 format.
+        """
+        target_size = self.get_preprocess_shape(image.shape[0], image.shape[1], self.target_length)
+        return np.array(resize(to_pil_image(image), target_size))
+
+    def apply_coords(self, coords: np.ndarray, original_size: Tuple[int, ...]) -> np.ndarray:
+        """
+        Expects a numpy array of length 2 in the final dimension. Requires the
+        original image size in (H, W) format.
+        """
+        old_h, old_w = original_size
+        new_h, new_w = self.get_preprocess_shape(
+            original_size[0], original_size[1], self.target_length
+        )
+        coords = deepcopy(coords).astype(float)
+        coords[..., 0] = coords[..., 0] * (new_w / old_w)
+        coords[..., 1] = coords[..., 1] * (new_h / old_h)
+        return coords
+
+    def apply_boxes(self, boxes: np.ndarray, original_size: Tuple[int, ...]) -> np.ndarray:
+        """
+        Expects a numpy array shape Bx4. Requires the original image size
+        in (H, W) format.
+        """
+        boxes = self.apply_coords(boxes.reshape(-1, 2, 2), original_size)
+        return boxes.reshape(-1, 4)
+
+    def apply_image_torch(self, image: torch.Tensor) -> torch.Tensor:
+        """
+        Expects batched images with shape BxCxHxW and float format. This
+        transformation may not exactly match apply_image. apply_image is
+        the transformation expected by the model.
+        """
+        # Expects an image in BCHW format. May not exactly match apply_image.
+        target_size = self.get_preprocess_shape(image.shape[2], image.shape[3], self.target_length)
+        return F.interpolate(
+            image, target_size, mode="bilinear", align_corners=False, antialias=True
+        )
+
+    def apply_coords_torch(
+        self, coords: torch.Tensor, original_size: Tuple[int, ...]
+    ) -> torch.Tensor:
+        """
+        Expects a torch tensor with length 2 in the last dimension. Requires the
+        original image size in (H, W) format.
+        """
+        old_h, old_w = original_size
+        new_h, new_w = self.get_preprocess_shape(
+            original_size[0], original_size[1], self.target_length
+        )
+        coords = deepcopy(coords).to(torch.float)
+        coords[..., 0] = coords[..., 0] * (new_w / old_w)
+        coords[..., 1] = coords[..., 1] * (new_h / old_h)
+        return coords
+
+    def apply_boxes_torch(
+        self, boxes: torch.Tensor, original_size: Tuple[int, ...]
+    ) -> torch.Tensor:
+        """
+        Expects a torch tensor with shape Bx4. Requires the original image
+        size in (H, W) format.
+        """
+        boxes = self.apply_coords_torch(boxes.reshape(-1, 2, 2), original_size)
+        return boxes.reshape(-1, 4)
+
+    @staticmethod
+    def get_preprocess_shape(oldh: int, oldw: int, long_side_length: int) -> Tuple[int, int]:
+        """
+        Compute the output size given input size and target long side length.
+        """
+        scale = long_side_length * 1.0 / max(oldh, oldw)
+        newh, neww = oldh * scale, oldw * scale
+        neww = int(neww + 0.5)
+        newh = int(newh + 0.5)
+        return (newh, neww)

sam2.1HQ/sam-hq-main/demo/demo_hqsam.py

@@ -0,0 +1,147 @@
+import numpy as np
+import torch
+import matplotlib.pyplot as plt
+import cv2
+from segment_anything import sam_model_registry, SamPredictor
+import os
+
+def show_mask(mask, ax, random_color=False):
+    if random_color:
+        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
+    else:
+        color = np.array([30/255, 144/255, 255/255, 0.6])
+    h, w = mask.shape[-2:]
+    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
+    ax.imshow(mask_image)
+    
+def show_points(coords, labels, ax, marker_size=375):
+    pos_points = coords[labels==1]
+    neg_points = coords[labels==0]
+    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)   
+    
+def show_box(box, ax):
+    x0, y0 = box[0], box[1]
+    w, h = box[2] - box[0], box[3] - box[1]
+    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))    
+
+
+def show_res(masks, scores, input_point, input_label, input_box, filename, image):
+    for i, (mask, score) in enumerate(zip(masks, scores)):
+        plt.figure(figsize=(10,10))
+        plt.imshow(image)
+        show_mask(mask, plt.gca())
+        if input_box is not None:
+            box = input_box[i]
+            show_box(box, plt.gca())
+        if (input_point is not None) and (input_label is not None): 
+            show_points(input_point, input_label, plt.gca())
+        
+        print(f"Score: {score:.3f}")
+        plt.axis('off')
+        plt.savefig(filename+'_'+str(i)+'.png',bbox_inches='tight',pad_inches=-0.1)
+        plt.close()
+
+def show_res_multi(masks, scores, input_point, input_label, input_box, filename, image):
+    plt.figure(figsize=(10, 10))
+    plt.imshow(image)
+    for mask in masks:
+        show_mask(mask, plt.gca(), random_color=True)
+    for box in input_box:
+        show_box(box, plt.gca())
+    for score in scores:
+        print(f"Score: {score:.3f}")
+    plt.axis('off')
+    plt.savefig(filename +'.png',bbox_inches='tight',pad_inches=-0.1)
+    plt.close()
+
+
+if __name__ == "__main__":
+    sam_checkpoint = "./pretrained_checkpoint/sam_hq_vit_l.pth"
+    model_type = "vit_l"
+    device = "cuda"
+    sam = sam_model_registry[model_type](checkpoint=sam_checkpoint)
+    sam.to(device=device)
+    predictor = SamPredictor(sam)
+
+    for i in range(8):
+        print("image:   ",i)
+        # hq_token_only: False means use hq output to correct SAM output. 
+        #                True means use hq output only. 
+        #                Default: False
+        hq_token_only = False 
+        # To achieve best visualization effect, for images contain multiple objects (like typical coco images), we suggest to set hq_token_only=False
+        # For images contain single object, we suggest to set hq_token_only = True
+        # For quantiative evaluation on COCO/YTVOS/DAVIS/UVO/LVIS etc., we set hq_token_only = False
+
+        image = cv2.imread('demo/input_imgs/example'+str(i)+'.png')
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+        predictor.set_image(image)
+
+        if i==0:
+            input_box = np.array([[4,13,1007,1023]])
+            input_point, input_label = None, None
+        elif i==1:
+            input_box = np.array([[306, 132, 925, 893]])
+            input_point, input_label = None, None
+            hq_token_only = True
+        elif i==2:
+            input_point = np.array([[495,518],[217,140]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+            hq_token_only = True
+        elif i==3:
+            input_point = np.array([[221,482],[498,633],[750,379]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==4:
+            input_box = np.array([[64,76,940,919]])
+            input_point, input_label = None, None
+            hq_token_only = True
+        elif i==5:
+            input_point = np.array([[373,363], [452, 575]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==6:
+            input_box = np.array([[181, 196, 757, 495]])
+            input_point, input_label = None, None
+        elif i==7:
+            # multi box input
+            input_box = torch.tensor([[45,260,515,470], [310,228,424,296]],device=predictor.device)
+            transformed_box = predictor.transform.apply_boxes_torch(input_box, image.shape[:2])
+            input_point, input_label = None, None
+
+        batch_box = False if input_box is None else len(input_box)>1 
+        result_path = 'demo/hq_sam_result/'
+        os.makedirs(result_path, exist_ok=True)
+
+        if not batch_box: 
+            masks, scores, logits = predictor.predict(
+                point_coords=input_point,
+                point_labels=input_label,
+                box = input_box,
+                multimask_output=False,
+                hq_token_only=hq_token_only, 
+            )
+            show_res(masks,scores,input_point, input_label, input_box, result_path + 'example'+str(i), image)
+        
+        else:
+            masks, scores, logits = predictor.predict_torch(
+                point_coords=input_point,
+                point_labels=input_label,
+                boxes=transformed_box,
+                multimask_output=False,
+                hq_token_only=hq_token_only,
+            )
+            masks = masks.squeeze(1).cpu().numpy()
+            scores = scores.squeeze(1).cpu().numpy()
+            input_box = input_box.cpu().numpy()
+            show_res_multi(masks, scores, input_point, input_label, input_box, result_path + 'example'+str(i), image)
+
+
+        
+
+    
+
+
+

sam2.1HQ/sam-hq-main/demo/demo_hqsam_light.py

@@ -0,0 +1,141 @@
+import numpy as np
+import torch
+import matplotlib.pyplot as plt
+import cv2
+from segment_anything import sam_model_registry, SamPredictor
+import os
+
+def show_mask(mask, ax, random_color=False):
+    if random_color:
+        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
+    else:
+        color = np.array([30/255, 144/255, 255/255, 0.6])
+    h, w = mask.shape[-2:]
+    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
+    ax.imshow(mask_image)
+    
+def show_points(coords, labels, ax, marker_size=375):
+    pos_points = coords[labels==1]
+    neg_points = coords[labels==0]
+    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)   
+    
+def show_box(box, ax):
+    x0, y0 = box[0], box[1]
+    w, h = box[2] - box[0], box[3] - box[1]
+    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))    
+
+
+def show_res(masks, scores, input_point, input_label, input_box, filename, image):
+    for i, (mask, score) in enumerate(zip(masks, scores)):
+        plt.figure(figsize=(10,10))
+        plt.imshow(image)
+        show_mask(mask, plt.gca())
+        if input_box is not None:
+            box = input_box[i]
+            show_box(box, plt.gca())
+        if (input_point is not None) and (input_label is not None): 
+            show_points(input_point, input_label, plt.gca())
+        
+        print(f"Score: {score:.3f}")
+        plt.axis('off')
+        plt.savefig(filename+'_'+str(i)+'.png',bbox_inches='tight',pad_inches=-0.1)
+        plt.close()
+
+def show_res_multi(masks, scores, input_point, input_label, input_box, filename, image):
+    plt.figure(figsize=(10, 10))
+    plt.imshow(image)
+    for mask in masks:
+        show_mask(mask, plt.gca(), random_color=True)
+    for box in input_box:
+        show_box(box, plt.gca())
+    for score in scores:
+        print(f"Score: {score:.3f}")
+    plt.axis('off')
+    plt.savefig(filename +'.png',bbox_inches='tight',pad_inches=-0.1)
+    plt.close()
+
+
+if __name__ == "__main__":
+    sam_checkpoint = "./pretrained_checkpoint/sam_hq_vit_tiny.pth"
+    model_type = "vit_tiny"
+
+    device = "cuda"
+    sam = sam_model_registry[model_type](checkpoint=sam_checkpoint)
+    sam.to(device=device)
+    sam.eval()
+    predictor = SamPredictor(sam)
+
+
+    image = cv2.imread('demo/input_imgs/dog.jpg')
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    predictor.set_image(image)
+    # hq_token_only: False means use hq output to correct SAM output. 
+    #                True means use hq output only. 
+    #                Default: False
+    hq_token_only = False 
+    # To achieve best visualization effect, for images contain multiple objects (like typical coco images), we suggest to set hq_token_only=False
+    # For images contain single object, we suggest to set hq_token_only = True
+    # For quantiative evaluation on COCO/YTVOS/DAVIS/UVO/LVIS etc., we set hq_token_only = False
+    
+    # box prompt
+    input_box = np.array([[784,500,1789,1000]])
+    input_point, input_label = None, None
+
+    masks, scores, logits = predictor.predict(
+        point_coords=input_point,
+        point_labels=input_label,
+        box = input_box,
+        multimask_output=False,
+        hq_token_only=hq_token_only, 
+    )
+    result_path = 'demo/hq_sam_tiny_result/'
+    os.makedirs(result_path, exist_ok=True)
+    show_res(masks,scores,input_point, input_label, input_box, result_path + 'dog', image)
+
+
+
+    image = cv2.imread('demo/input_imgs/example3.png')
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    predictor.set_image(image)
+    hq_token_only = True
+    # point prompt
+    input_point = np.array([[221,482],[498,633],[750,379]])
+    input_label = np.ones(input_point.shape[0])
+    input_box = None
+
+    masks, scores, logits = predictor.predict(
+        point_coords=input_point,
+        point_labels=input_label,
+        box = input_box,
+        multimask_output=False,
+        hq_token_only=hq_token_only, 
+    )
+    show_res(masks,scores,input_point, input_label, input_box, result_path + 'example3', image)
+
+
+    image = cv2.imread('demo/input_imgs/example7.png')
+    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+    predictor.set_image(image)
+    hq_token_only = False
+    # multi box prompt
+    input_box = torch.tensor([[45,260,515,470], [310,228,424,296]],device=predictor.device)
+    transformed_box = predictor.transform.apply_boxes_torch(input_box, image.shape[:2])
+    input_point, input_label = None, None
+    masks, scores, logits = predictor.predict_torch(
+        point_coords=input_point,
+        point_labels=input_label,
+        boxes=transformed_box,
+        multimask_output=False,
+        hq_token_only=hq_token_only,
+    )
+    masks = masks.squeeze(1).cpu().numpy()
+    scores = scores.squeeze(1).cpu().numpy()
+    input_box = input_box.cpu().numpy()
+    show_res_multi(masks, scores, input_point, input_label, input_box, result_path + 'example7', image)
+
+
+    
+
+
+

sam2.1HQ/sam-hq-main/demo/demo_hqsam_pip_example.py

@@ -0,0 +1,141 @@
+import numpy as np
+import torch
+import matplotlib.pyplot as plt
+import cv2
+from segment_anything_hq import sam_model_registry, SamPredictor
+import os
+
+def show_mask(mask, ax, random_color=False):
+    if random_color:
+        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
+    else:
+        color = np.array([30/255, 144/255, 255/255, 0.6])
+    h, w = mask.shape[-2:]
+    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
+    ax.imshow(mask_image)
+    
+def show_points(coords, labels, ax, marker_size=375):
+    pos_points = coords[labels==1]
+    neg_points = coords[labels==0]
+    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)   
+    
+def show_box(box, ax):
+    x0, y0 = box[0], box[1]
+    w, h = box[2] - box[0], box[3] - box[1]
+    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))    
+
+
+def show_res(masks, scores, input_point, input_label, input_box, filename, image):
+    for i, (mask, score) in enumerate(zip(masks, scores)):
+        plt.figure(figsize=(10,10))
+        plt.imshow(image)
+        show_mask(mask, plt.gca())
+        if input_box is not None:
+            box = input_box[i]
+            show_box(box, plt.gca())
+        if (input_point is not None) and (input_label is not None): 
+            show_points(input_point, input_label, plt.gca())
+        
+        print(f"Score: {score:.3f}")
+        plt.axis('off')
+        plt.savefig(filename+'_'+str(i)+'.png',bbox_inches='tight',pad_inches=-0.1)
+        plt.close()
+
+def show_res_multi(masks, scores, input_point, input_label, input_box, filename, image):
+    plt.figure(figsize=(10, 10))
+    plt.imshow(image)
+    for mask in masks:
+        show_mask(mask, plt.gca(), random_color=True)
+    for box in input_box:
+        show_box(box, plt.gca())
+    for score in scores:
+        print(f"Score: {score:.3f}")
+    plt.axis('off')
+    plt.savefig(filename +'.png',bbox_inches='tight',pad_inches=-0.1)
+    plt.close()
+
+
+if __name__ == "__main__":
+    sam_checkpoint = "./pretrained_checkpoint/sam_hq_vit_l.pth"
+    model_type = "vit_l"
+    device = "cuda"
+    sam = sam_model_registry[model_type](checkpoint=sam_checkpoint)
+    sam.to(device=device)
+    predictor = SamPredictor(sam)
+
+    for i in range(8):
+        print("image:   ",i)
+        # hq_token_only: False means use hq output to correct SAM output. 
+        #                True means use hq output only. 
+        #                Default: False
+        hq_token_only = False 
+        # To achieve best visualization effect, for images contain multiple objects (like typical coco images), we suggest to set hq_token_only=False
+        # For images contain single object, we suggest to set hq_token_only = True
+        # For quantiative evaluation on COCO/YTVOS/DAVIS/UVO/LVIS etc., we set hq_token_only = False
+
+        image = cv2.imread('demo/input_imgs/example'+str(i)+'.png')
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+        predictor.set_image(image)
+
+        if i==0:
+            input_box = np.array([[4,13,1007,1023]])
+            input_point, input_label = None, None
+        elif i==1:
+            input_box = np.array([[306, 132, 925, 893]])
+            input_point, input_label = None, None
+            hq_token_only = True
+        elif i==2:
+            input_point = np.array([[495,518],[217,140]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+            hq_token_only = True
+        elif i==3:
+            input_point = np.array([[221,482],[498,633],[750,379]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==4:
+            input_box = np.array([[64,76,940,919]])
+            input_point, input_label = None, None
+            hq_token_only = True
+        elif i==5:
+            input_point = np.array([[373,363], [452, 575]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==6:
+            input_box = np.array([[181, 196, 757, 495]])
+            input_point, input_label = None, None
+        elif i==7:
+            # multi box input
+            input_box = torch.tensor([[45,260,515,470], [310,228,424,296]],device=predictor.device)
+            transformed_box = predictor.transform.apply_boxes_torch(input_box, image.shape[:2])
+            input_point, input_label = None, None
+
+        batch_box = False if input_box is None else len(input_box)>1 
+        result_path = 'demo/hq_sam_result/'
+        os.makedirs(result_path, exist_ok=True)
+
+        if not batch_box: 
+            masks, scores, logits = predictor.predict(
+                point_coords=input_point,
+                point_labels=input_label,
+                box = input_box,
+                multimask_output=False,
+                hq_token_only=hq_token_only, 
+            )
+            show_res(masks,scores,input_point, input_label, input_box, result_path + 'example'+str(i), image)
+        
+        else:
+            masks, scores, logits = predictor.predict_torch(
+                point_coords=input_point,
+                point_labels=input_label,
+                boxes=transformed_box,
+                multimask_output=False,
+                hq_token_only=hq_token_only,
+            )
+            masks = masks.squeeze(1).cpu().numpy()
+            scores = scores.squeeze(1).cpu().numpy()
+            input_box = input_box.cpu().numpy()
+            show_res_multi(masks, scores, input_point, input_label, input_box, result_path + 'example'+str(i), image)
+
+

sam2.1HQ/sam-hq-main/demo/demo_sam.py

@@ -0,0 +1,127 @@
+import numpy as np
+import torch
+import matplotlib.pyplot as plt
+import cv2
+from segment_anything import sam_model_registry_baseline, SamPredictor
+import os
+
+def show_mask(mask, ax, random_color=False):
+    if random_color:
+        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
+    else:
+        color = np.array([30/255, 144/255, 255/255, 0.6])
+    h, w = mask.shape[-2:]
+    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
+    ax.imshow(mask_image)
+    
+def show_points(coords, labels, ax, marker_size=375):
+    pos_points = coords[labels==1]
+    neg_points = coords[labels==0]
+    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)   
+    
+def show_box(box, ax):
+    x0, y0 = box[0], box[1]
+    w, h = box[2] - box[0], box[3] - box[1]
+    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))    
+
+
+def show_res(masks, scores, input_point, input_label, input_box, filename, image):
+    for i, (mask, score) in enumerate(zip(masks, scores)):
+        plt.figure(figsize=(10,10))
+        plt.imshow(image)
+        show_mask(mask, plt.gca())
+        if input_box is not None:
+            box = input_box[i]
+            show_box(box, plt.gca())
+        if (input_point is not None) and (input_label is not None): 
+            show_points(input_point, input_label, plt.gca())
+        
+        print(f"Score: {score:.3f}")
+        plt.axis('off')
+        plt.savefig(filename+'_'+str(i)+'.png',bbox_inches='tight',pad_inches=-0.1)
+        plt.close()
+
+def show_res_multi(masks, scores, input_point, input_label, input_box, filename, image):
+    plt.figure(figsize=(10, 10))
+    plt.imshow(image)
+    for mask in masks:
+        show_mask(mask, plt.gca(), random_color=True)
+    for box in input_box:
+        show_box(box, plt.gca())
+    for score in scores:
+        print(f"Score: {score:.3f}")
+    plt.axis('off')
+    plt.savefig(filename +'.png',bbox_inches='tight',pad_inches=-0.1)
+    plt.close()
+
+if __name__ == "__main__":
+    sam_checkpoint = "./pretrained_checkpoint/sam_vit_l_0b3195.pth"
+    model_type = "vit_l"
+    device = "cuda"
+    sam = sam_model_registry_baseline[model_type](checkpoint=sam_checkpoint)
+    sam.to(device=device)
+    predictor = SamPredictor(sam)
+
+    for i in range(8):
+        print("image:   ",i)
+        image = cv2.imread('demo/input_imgs/example'+str(i)+'.png')
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+        predictor.set_image(image)
+
+        if i==0:
+            input_box = np.array([[4,13,1007,1023]])
+            input_point, input_label = None, None
+        elif i==1:
+            input_box = np.array([[306, 132, 925, 893]])
+            input_point, input_label = None, None
+        elif i==2:
+            input_point = np.array([[495,518],[217,140]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==3:
+            input_point = np.array([[221,482],[498,633],[750,379]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==4:
+            input_box = np.array([[64,76,940,919]])
+            input_point, input_label = None, None
+        elif i==5:
+            input_point = np.array([[373,363], [452, 575]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==6:
+            input_box = np.array([[181, 196, 757, 495]])
+            input_point, input_label = None, None
+        elif i==7:
+            # multi box input
+            input_box = torch.tensor([[45,260,515,470], [310,228,424,296]],device=predictor.device)
+            transformed_box = predictor.transform.apply_boxes_torch(input_box, image.shape[:2])
+            input_point, input_label = None, None
+
+        batch_box = False if input_box is None else len(input_box)>1 
+        result_path = 'demo/baseline_sam_result/'
+        os.makedirs(result_path, exist_ok=True)
+
+        if not batch_box: 
+            masks, scores, logits = predictor.predict(
+                point_coords=input_point,
+                point_labels=input_label,
+                box = input_box,
+                multimask_output=False,
+            )
+            show_res(masks,scores,input_point, input_label, input_box, result_path + 'example'+str(i), image)
+        else:
+            masks, scores, logits = predictor.predict_torch(
+                point_coords=input_point,
+                point_labels=input_label,
+                boxes=transformed_box,
+                multimask_output=False,
+            )
+            masks = masks.squeeze(1).cpu().numpy()
+            scores = scores.squeeze(1).cpu().numpy()
+            input_box = input_box.cpu().numpy()
+            show_res_multi(masks, scores, input_point, input_label, input_box, result_path + 'example'+str(i), image)
+
+
+

sam2.1HQ/sam-hq-main/sam-hq2/INSTALL.md

@@ -0,0 +1,189 @@
+## Installation
+
+### Requirements
+
+- Linux with Python ≥ 3.10, PyTorch ≥ 2.3.1 and [torchvision](https://github.com/pytorch/vision/) that matches the PyTorch installation. Install them together at https://pytorch.org to ensure this.
+  * Note older versions of Python or PyTorch may also work. However, the versions above are strongly recommended to provide all features such as `torch.compile`.
+- [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) that match the CUDA version for your PyTorch installation. This should typically be CUDA 12.1 if you follow the default installation command.
+- If you are installing on Windows, it's strongly recommended to use [Windows Subsystem for Linux (WSL)](https://learn.microsoft.com/en-us/windows/wsl/install) with Ubuntu.
+
+Then, install SAM 2 from the root of this repository via
+```bash
+pip install -e ".[notebooks]"
+```
+
+Note that you may skip building the SAM 2 CUDA extension during installation via environment variable `SAM2_BUILD_CUDA=0`, as follows:
+```bash
+# skip the SAM 2 CUDA extension
+SAM2_BUILD_CUDA=0 pip install -e ".[notebooks]"
+```
+This would also skip the post-processing step at runtime (removing small holes and sprinkles in the output masks, which requires the CUDA extension), but shouldn't affect the results in most cases.
+
+### Building the SAM 2 CUDA extension
+
+By default, we allow the installation to proceed even if the SAM 2 CUDA extension fails to build. (In this case, the build errors are hidden unless using `-v` for verbose output in `pip install`.)
+
+If you see a message like `Skipping the post-processing step due to the error above` at runtime or `Failed to build the SAM 2 CUDA extension due to the error above` during installation, it indicates that the SAM 2 CUDA extension failed to build in your environment. In this case, **you can still use SAM 2 for both image and video applications**. The post-processing step (removing small holes and sprinkles in the output masks) will be skipped, but this shouldn't affect the results in most cases.
+
+If you would like to enable this post-processing step, you can reinstall SAM 2 on a GPU machine with environment variable `SAM2_BUILD_ALLOW_ERRORS=0` to force building the CUDA extension (and raise errors if it fails to build), as follows
+```bash
+pip uninstall -y SAM-2 && \
+rm -f ./sam2/*.so && \
+SAM2_BUILD_ALLOW_ERRORS=0 pip install -v -e ".[notebooks]"
+```
+
+Note that PyTorch needs to be installed first before building the SAM 2 CUDA extension. It's also necessary to install [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) that match the CUDA version for your PyTorch installation. (This should typically be CUDA 12.1 if you follow the default installation command.) After installing the CUDA toolkits, you can check its version via `nvcc --version`.
+
+Please check the section below on common installation issues if the CUDA extension fails to build during installation or load at runtime.
+
+### Common Installation Issues
+
+Click each issue for its solutions:
+
+<details>
+<summary>
+I got `ImportError: cannot import name '_C' from 'sam2'`
+</summary>
+<br/>
+
+This is usually because you haven't run the `pip install -e ".[notebooks]"` step above or the installation failed. Please install SAM 2 first, and see the other issues if your installation fails.
+
+In some systems, you may need to run `python setup.py build_ext --inplace` in the SAM 2 repo root as suggested in https://github.com/facebookresearch/sam2/issues/77.
+</details>
+
+<details>
+<summary>
+I got `MissingConfigException: Cannot find primary config 'configs/sam2.1/sam2.1_hiera_l.yaml'`
+</summary>
+<br/>
+
+This is usually because you haven't run the `pip install -e .` step above, so `sam2` isn't in your Python's `sys.path`. Please run this installation step. In case it still fails after the installation step, you may try manually adding the root of this repo to `PYTHONPATH` via
+```bash
+export SAM2_REPO_ROOT=/path/to/sam2  # path to this repo
+export PYTHONPATH="${SAM2_REPO_ROOT}:${PYTHONPATH}"
+```
+to manually add `sam2_configs` into your Python's `sys.path`.
+
+</details>
+
+<details>
+<summary>
+I got `RuntimeError: Error(s) in loading state_dict for SAM2Base` when loading the new SAM 2.1 checkpoints
+</summary>
+<br/>
+
+This is likely because you have installed a previous version of this repo, which doesn't have the new modules to support the SAM 2.1 checkpoints yet. Please try the following steps:
+
+1. pull the latest code from the `main` branch of this repo
+2. run `pip uninstall -y SAM-2` to uninstall any previous installations
+3. then install the latest repo again using `pip install -e ".[notebooks]"`
+
+In case the steps above still don't resolve the error, please try running in your Python environment the following
+```python
+from sam2.modeling import sam2_base
+
+print(sam2_base.__file__)
+```
+and check whether the content in the printed local path of `sam2/modeling/sam2_base.py` matches the latest one in https://github.com/facebookresearch/sam2/blob/main/sam2/modeling/sam2_base.py (e.g. whether your local file has `no_obj_embed_spatial`) to indentify if you're still using a previous installation.
+
+</details>
+
+<details>
+<summary>
+My installation failed with `CUDA_HOME environment variable is not set`
+</summary>
+<br/>
+
+This usually happens because the installation step cannot find the CUDA toolkits (that contain the NVCC compiler) to build a custom CUDA kernel in SAM 2. Please install [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) or the version that matches the CUDA version for your PyTorch installation. If the error persists after installing CUDA toolkits, you may explicitly specify `CUDA_HOME` via
+```
+export CUDA_HOME=/usr/local/cuda  # change to your CUDA toolkit path
+```
+and rerun the installation.
+
+Also, you should make sure
+```
+python -c 'import torch; from torch.utils.cpp_extension import CUDA_HOME; print(torch.cuda.is_available(), CUDA_HOME)'
+```
+print `(True, a directory with cuda)` to verify that the CUDA toolkits are correctly set up.
+
+If you are still having problems after verifying that the CUDA toolkit is installed and the `CUDA_HOME` environment variable is set properly, you may have to add the `--no-build-isolation` flag to the pip command:
+```
+pip install --no-build-isolation -e .
+```
+
+</details>
+
+<details>
+<summary>
+I got `undefined symbol: _ZN3c1015SmallVectorBaseIjE8grow_podEPKvmm` (or similar errors)
+</summary>
+<br/>
+
+This usually happens because you have multiple versions of dependencies (PyTorch or CUDA) in your environment. During installation, the SAM 2 library is compiled against one version library while at run time it links against another version. This might be due to that you have different versions of PyTorch or CUDA installed separately via `pip` or `conda`. You may delete one of the duplicates to only keep a single PyTorch and CUDA version.
+
+In particular, if you have a lower PyTorch version than 2.3.1, it's recommended to upgrade to PyTorch 2.3.1 or higher first. Otherwise, the installation script will try to upgrade to the latest PyTorch using `pip`, which could sometimes lead to duplicated PyTorch installation if you have previously installed another PyTorch version using `conda`.
+
+We have been building SAM 2 against PyTorch 2.3.1 internally. However, a few user comments (e.g. https://github.com/facebookresearch/sam2/issues/22, https://github.com/facebookresearch/sam2/issues/14) suggested that downgrading to PyTorch 2.1.0 might resolve this problem. In case the error persists, you may try changing the restriction from `torch>=2.3.1` to `torch>=2.1.0` in both [`pyproject.toml`](pyproject.toml) and [`setup.py`](setup.py) to allow PyTorch 2.1.0.
+</details>
+
+<details>
+<summary>
+I got `CUDA error: no kernel image is available for execution on the device`
+</summary>
+<br/>
+
+A possible cause could be that the CUDA kernel is somehow not compiled towards your GPU's CUDA [capability](https://developer.nvidia.com/cuda-gpus). This could happen if the installation is done in an environment different from the runtime (e.g. in a slurm system).
+
+You can try pulling the latest code from the SAM 2 repo and running the following
+```
+export TORCH_CUDA_ARCH_LIST=9.0 8.0 8.6 8.9 7.0 7.2 7.5 6.0`
+```
+to manually specify the CUDA capability in the compilation target that matches your GPU.
+</details>
+
+<details>
+<summary>
+I got `RuntimeError: No available kernel. Aborting execution.` (or similar errors)
+</summary>
+<br/>
+
+This is probably because your machine doesn't have a GPU or a compatible PyTorch version for Flash Attention (see also https://discuss.pytorch.org/t/using-f-scaled-dot-product-attention-gives-the-error-runtimeerror-no-available-kernel-aborting-execution/180900 for a discussion in PyTorch forum). You may be able to resolve this error by replacing the line
+```python
+OLD_GPU, USE_FLASH_ATTN, MATH_KERNEL_ON = get_sdpa_settings()
+```
+in [`sam2/modeling/sam/transformer.py`](sam2/modeling/sam/transformer.py) with
+```python
+OLD_GPU, USE_FLASH_ATTN, MATH_KERNEL_ON = True, True, True
+```
+to relax the attention kernel setting and use other kernels than Flash Attention.
+</details>
+
+<details>
+<summary>
+I got `Error compiling objects for extension`
+</summary>
+<br/>
+
+You may see error log of:
+> unsupported Microsoft Visual Studio version! Only the versions between 2017 and 2022 (inclusive) are supported! The nvcc flag '-allow-unsupported-compiler' can be used to override this version check; however, using an unsupported host compiler may cause compilation failure or incorrect run time execution. Use at your own risk.
+
+This is probably because your versions of CUDA and Visual Studio are incompatible. (see also https://stackoverflow.com/questions/78515942/cuda-compatibility-with-visual-studio-2022-version-17-10 for a discussion in stackoverflow).<br> 
+You may be able to fix this by adding the `-allow-unsupported-compiler` argument to `nvcc` after L48 in the [setup.py](https://github.com/facebookresearch/sam2/blob/main/setup.py). <br>
+After adding the argument, `get_extension()` will look like this:
+```python
+def get_extensions():
+    srcs = ["sam2/csrc/connected_components.cu"]
+    compile_args = {
+        "cxx": [],
+        "nvcc": [
+            "-DCUDA_HAS_FP16=1",
+            "-D__CUDA_NO_HALF_OPERATORS__",
+            "-D__CUDA_NO_HALF_CONVERSIONS__",
+            "-D__CUDA_NO_HALF2_OPERATORS__",
+            "-allow-unsupported-compiler"  # Add this argument
+        ],
+    }
+    ext_modules = [CUDAExtension("sam2._C", srcs, extra_compile_args=compile_args)]
+    return ext_modules
+```
+</details>

sam2.1HQ/sam-hq-main/sam-hq2/README.md

@@ -0,0 +1,252 @@
+# HQ-SAM 2: Segment Anything in High Quality for Images and Videos    
+
+
+We propose **HQ-SAM2** to upgrade SAM2 to **higher quality** by extending our training strategy in [HQ-SAM](https://arxiv.org/abs/2306.01567). 
+
+## Latest updates
+
+**2024/11/17 -- HQ-SAM 2 is released**
+
+- A new suite of improved model checkpoints (denoted as **HQ-SAM 2**, **beta-version**) are released. See [Model Description](#model-description) for details.
+
+![HQ-SAM2 results comparison](assets/hq-sam2-results.png?raw=true)
+
+## Installation
+
+HQ-SAM 2 needs to be installed first before use. The code requires `python>=3.10`, as well as `torch>=2.3.1` and `torchvision>=0.18.1`. Please follow the instructions [here](https://pytorch.org/get-started/locally/) to install both PyTorch and TorchVision dependencies. You can install SAM 2 on a GPU machine using:
+
+```bash
+git clone https://github.com/SysCV/sam-hq.git
+conda create -n sam_hq2 python=3.10 -y
+conda activate sam_hq2
+cd sam-hq/sam-hq2
+pip install -e .
+```
+If you are installing on Windows, it's strongly recommended to use [Windows Subsystem for Linux (WSL)](https://learn.microsoft.com/en-us/windows/wsl/install) with Ubuntu.
+
+To use the HQ-SAM 2 predictor and run the example notebooks, `jupyter` and `matplotlib` are required and can be installed by:
+
+```bash
+pip install -e ".[notebooks]"
+```
+
+Note:
+1. It's recommended to create a new Python environment via [Anaconda](https://www.anaconda.com/) for this installation and install PyTorch 2.3.1 (or higher) via `pip` following https://pytorch.org/. If you have a PyTorch version lower than 2.3.1 in your current environment, the installation command above will try to upgrade it to the latest PyTorch version using `pip`.
+2. The step above requires compiling a custom CUDA kernel with the `nvcc` compiler. If it isn't already available on your machine, please install the [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) with a version that matches your PyTorch CUDA version.
+3. If you see a message like `Failed to build the SAM 2 CUDA extension` during installation, you can ignore it and still use SAM 2 (some post-processing functionality may be limited, but it doesn't affect the results in most cases).
+
+Please see [`INSTALL.md`](./INSTALL.md) for FAQs on potential issues and solutions.
+
+## Getting Started
+
+### Download Checkpoints
+
+First, we need to download a model checkpoint. All the model checkpoints can be downloaded by running:
+
+```bash
+cd checkpoints && \
+./download_ckpts.sh && \
+cd ..
+```
+
+or individually from:
+
+<!-- - [sam2.1_hiera_large.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt) -->
+- [sam2.1_hq_hiera_large.pt](https://huggingface.co/lkeab/hq-sam/resolve/main/sam2.1_hq_hiera_large.pt?download=true)
+
+(note that these are the improved checkpoints denoted as SAM 2.1; see [Model Description](#model-description) for details.)
+
+Then HQ-SAM 2 can be used in a few lines as follows for image and video prediction.
+
+### Image prediction
+
+HQ-SAM 2 has all the capabilities of [HQ-SAM](https://github.com/SysCV/sam-hq) on static images, and we provide image prediction APIs that closely resemble SAM for image use cases. The `SAM2ImagePredictor` class has an easy interface for image prompting.
+
+```python
+import torch
+from sam2.build_sam import build_sam2
+from sam2.sam2_image_predictor import SAM2ImagePredictor
+# Baseline SAM2.1
+# checkpoint = "./checkpoints/sam2.1_hiera_large.pt"
+# model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"
+
+# Ours HQ-SAM 2
+checkpoint = "./checkpoints/sam2.1_hq_hiera_large.pt"
+model_cfg = "configs/sam2.1/sam2.1_hq_hiera_l.yaml"
+predictor = SAM2ImagePredictor(build_sam2(model_cfg, checkpoint))
+
+with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
+    predictor.set_image(<your_image>)
+    masks, _, _ = predictor.predict(<input_prompts>, multimask_output=False)
+```
+
+Please refer to the examples in [python demo/demo_hqsam2.py](./demo/demo_hqsam2.py) for details on how to add click or box prompts.
+
+Please refer to the examples in [image_predictor_example.ipynb](./notebooks/image_predictor_example.ipynb) for static image use cases.
+
+### Video prediction
+
+For promptable segmentation and tracking in videos, we provide a video predictor with APIs for example to add prompts and propagate masklets throughout a video. SAM 2 supports video inference on multiple objects and uses an inference state to keep track of the interactions in each video.
+
+```python
+import torch
+from sam2.build_sam import build_sam2_video_predictor
+from sam2.build_sam import build_sam2_hq_video_predictor
+# Baseline SAM2.1
+# checkpoint = "./checkpoints/sam2.1_hiera_large.pt"
+# model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"
+# predictor = build_sam2_video_predictor(model_cfg, checkpoint)
+
+# Ours HQ-SAM 2
+checkpoint = "./checkpoints/sam2.1_hq_hiera_large.pt"
+model_cfg = "configs/sam2.1/sam2.1_hq_hiera_l.yaml"
+predictor = build_sam2_hq_video_predictor(model_cfg, checkpoint)
+
+with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
+    state = predictor.init_state(<your_video>)
+
+    # add new prompts and instantly get the output on the same frame
+    frame_idx, object_ids, masks = predictor.add_new_points_or_box(state, <your_prompts>):
+
+    # propagate the prompts to get masklets throughout the video
+    for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
+        ...
+```
+
+
+Please refer to the examples in [video_predictor_example.ipynb](./notebooks/video_predictor_example.ipynb) for static image use cases.
+
+
+## Model Description
+
+### HQ-SAM 2 checkpoints
+
+The table below shows the **zero-shot** image segmentation performance of SAM2.1 and HQ-SAM 2 on **COCO (AP)** using same bounding box detector from Focal-net DINO. The FPS speed of SAM2.1 and HQ-SAM 2 is on par.
+|      **Model**       | **Size (M)** | **Single Mode (AP)** | **Multi-Mode (AP)** |
+| :------------------: | :----------: | :-----------------: | :----------------: |
+|   sam2.1_hiera_large <br /> ([config](sam2/configs/sam2.1/sam2.1_hiera_l.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt))   |    224.4     |        50.0         |        48.3       |
+|   sam2.1_hq_hiera_large <br /> ([config](sam2/configs/sam2.1/sam2.1_hq_hiera_l.yaml), [checkpoint](https://huggingface.co/lkeab/hq-sam/resolve/main/sam2.1_hq_hiera_large.pt?download=true))   |    224.7     |        **50.9**         |        **50.4**       |
+
+The table below shows the **zero-shot** image segmentation AP performance of Grounded-SAM 2 and Grounded-HQ-SAM 2 on [**Seginw (Segmentation in the Wild)** dataset](https://github.com/SysCV/sam-hq/tree/main/seginw).
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Model Name</th>
+<th valign="bottom">SAM</th>
+<th valign="bottom">GroundingDINO</th>
+<th valign="bottom">Mean AP</th>
+<th valign="bottom">Airplane-Parts</th>
+<th valign="bottom">Bottles</th>
+<th valign="bottom">Brain-Tumor</th>
+<th valign="bottom">Chicken</th>
+<th valign="bottom">Cows</th>
+<th valign="bottom">Electric-Shaver</th>
+<th valign="bottom">Elephants</th>
+<th valign="bottom">Fruits</th>
+<th valign="bottom">Garbage</th>
+<th valign="bottom">Ginger-Garlic</th>
+<th valign="bottom">Hand-Metal</th>
+<th valign="bottom">Hand</th>
+<th valign="bottom">House-Parts</th>
+<th valign="bottom">HouseHold-Items</th>
+<th valign="bottom">Nutterfly-Squireel</th>
+<th valign="bottom">Phones</th>
+<th valign="bottom">Poles</th>
+<th valign="bottom">Puppies</th>
+<th valign="bottom">Rail</th>
+<th valign="bottom">Salmon-Fillet</th>
+<th valign="bottom">Strawberry</th>
+<th valign="bottom">Tablets</th>
+<th valign="bottom">Toolkits</th>
+<th valign="bottom">Trash</th>
+<th valign="bottom">Watermelon</th>
+<!-- TABLE BODY -->
+ <tr><td align="left">Grounded SAM2</td>
+<td align="center">vit-l</td>
+<td align="center">swin-b</td>
+<td align="center">49.5</td>
+<td align="center">38.3</td>
+<td align="center">67.1</td>
+<td align="center">12.1</td>
+<td align="center">80.7</td>
+<td align="center">52.8</td>
+<td align="center">72.0</td>
+<td align="center">78.2</td>
+<td align="center">83.3</td>
+<td align="center">26.0</td>
+<td align="center">45.7</td>
+<td align="center">73.7</td>
+<td align="center">77.6</td>
+<td align="center">8.6</td>
+<td align="center">60.1</td>
+<td align="center">84.1</td>
+<td align="center">34.6</td>
+<td align="center">28.8</td>
+<td align="center">48.9</td>
+<td align="center">14.3</td>
+<td align="center">24.2</td>
+<td align="center">83.7</td>
+<td align="center">29.1</td>
+<td align="center">20.1</td>
+<td align="center">28.4</td>
+<td align="center">66.0</td>
+</tr>
+
+ <tr><td align="left">Grounded HQ-SAM2</td>
+<td align="center">vit-l</td>
+<td align="center">swin-b</td>
+<td align="center"><b>50.0</b></td>
+<td align="center">38.6</td>
+<td align="center">66.8</td>
+<td align="center">12.0</td>
+<td align="center">81.0</td>
+<td align="center">52.8</td>
+<td align="center">71.9</td>
+<td align="center">77.2</td>
+<td align="center">83.3</td>
+<td align="center">26.1</td>
+<td align="center">45.5</td>
+<td align="center">74.8</td>
+<td align="center">79.0</td>
+<td align="center">8.6</td>
+<td align="center">60.1</td>
+<td align="center">84.7</td>
+<td align="center">34.3</td>
+<td align="center">25.5</td>
+<td align="center">48.9</td>
+<td align="center">14.1</td>
+<td align="center">34.1</td>
+<td align="center">85.7</td>
+<td align="center">29.2</td>
+<td align="center">21.5</td>
+<td align="center">28.9</td>
+<td align="center">66.6</td>
+
+</tr>
+</tbody></table>
+
+
+The table below shows the **zero-shot** video object segmentation performance of SAM2.1 and HQ-SAM 2.
+|      **Model**       | **Size (M)** | **DAVIS val (J&F)** | **MOSE(J&F)** |
+| :------------------: | :----------: |:----------------: | :---------------: |
+|   sam2.1_hiera_large <br /> ([config](sam2/configs/sam2.1/sam2.1_hiera_l.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt))   |    224.4     |        89.8        |       74.6        |
+|   sam2.1_hq_hiera_large <br /> ([config](sam2/configs/sam2.1/sam2.1_hq_hiera_l.yaml), [checkpoint](https://huggingface.co/lkeab/hq-sam/resolve/main/sam2.1_hq_hiera_large.pt?download=true))   |    224.7     |        **91.0**        |       **74.7**        |
+
+
+
+## License
+
+The HQ-SAM 2, SAM 2 model checkpoints, SAM 2 demo code (front-end and back-end), and SAM 2 training code are licensed under [Apache 2.0](./LICENSE), however the [Inter Font](https://github.com/rsms/inter?tab=OFL-1.1-1-ov-file) and [Noto Color Emoji](https://github.com/googlefonts/noto-emoji) used in the SAM 2 demo code are made available under the [SIL Open Font License, version 1.1](https://openfontlicense.org/open-font-license-official-text/).
+
+## Citing HQ-SAM 2
+If you find HQ-SAM2 useful in your research or refer to the provided baseline results, please star :star: this repository and consider citing :pencil::
+```
+@inproceedings{sam_hq,
+    title={Segment Anything in High Quality},
+    author={Ke, Lei and Ye, Mingqiao and Danelljan, Martin and Liu, Yifan and Tai, Yu-Wing and Tang, Chi-Keung and Yu, Fisher},
+    booktitle={NeurIPS},
+    year={2023}
+}  
+```

sam2.1HQ/sam-hq-main/sam-hq2/checkpoints/download_ckpts.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+# Use either wget or curl to download the checkpoints
+if command -v wget &> /dev/null; then
+    CMD="wget"
+elif command -v curl &> /dev/null; then
+    CMD="curl -L -O"
+else
+    echo "Please install wget or curl to download the checkpoints."
+    exit 1
+fi
+
+# Define the URLs for SAM 2 checkpoints
+# SAM2_BASE_URL="https://dl.fbaipublicfiles.com/segment_anything_2/072824"
+# sam2_hiera_t_url="${SAM2_BASE_URL}/sam2_hiera_tiny.pt"
+# sam2_hiera_s_url="${SAM2_BASE_URL}/sam2_hiera_small.pt"
+# sam2_hiera_b_plus_url="${SAM2_BASE_URL}/sam2_hiera_base_plus.pt"
+# sam2_hiera_l_url="${SAM2_BASE_URL}/sam2_hiera_large.pt"
+
+# Download each of the four checkpoints using wget
+# echo "Downloading sam2_hiera_tiny.pt checkpoint..."
+# $CMD $sam2_hiera_t_url || { echo "Failed to download checkpoint from $sam2_hiera_t_url"; exit 1; }
+
+# echo "Downloading sam2_hiera_small.pt checkpoint..."
+# $CMD $sam2_hiera_s_url || { echo "Failed to download checkpoint from $sam2_hiera_s_url"; exit 1; }
+
+# echo "Downloading sam2_hiera_base_plus.pt checkpoint..."
+# $CMD $sam2_hiera_b_plus_url || { echo "Failed to download checkpoint from $sam2_hiera_b_plus_url"; exit 1; }
+
+# echo "Downloading sam2_hiera_large.pt checkpoint..."
+# $CMD $sam2_hiera_l_url || { echo "Failed to download checkpoint from $sam2_hiera_l_url"; exit 1; }
+
+# Define the URLs for SAM 2.1 checkpoints
+#SAM2p1_BASE_URL="https://dl.fbaipublicfiles.com/segment_anything_2/092824"
+#sam2p1_hiera_t_url="${SAM2p1_BASE_URL}/sam2.1_hiera_tiny.pt"
+#sam2p1_hiera_s_url="${SAM2p1_BASE_URL}/sam2.1_hiera_small.pt"
+#sam2p1_hiera_b_plus_url="${SAM2p1_BASE_URL}/sam2.1_hiera_base_plus.pt"
+#sam2p1_hiera_l_url="${SAM2p1_BASE_URL}/sam2.1_hiera_large.pt"
+# sam2p1_hq_hiera_l_url="https://huggingface.co/mqye/sam-hq2/resolve/main/sam2.1_hq_hiera_large.pt?download=true"
+sam2p1_hq_hiera_l_url="https://huggingface.co/lkeab/hq-sam/resolve/main/sam2.1_hq_hiera_large.pt?download=true"
+# SAM 2.1 checkpoints
+
+echo "Downloading sam2.1_hq_hiera_l.pt checkpoint..."
+$CMD $sam2p1_hq_hiera_l_url || { echo "Failed to download checkpoint from $sam2p1_hiera_t_url"; exit 1; }
+
+mv sam2.1_hq_hiera_large.pt?download=true sam2.1_hq_hiera_large.pt
+
+echo "HQ-SAM-2 checkpoints are downloaded successfully."

sam2.1HQ/sam-hq-main/sam-hq2/demo/demo_hqsam2.py

@@ -0,0 +1,118 @@
+import numpy as np
+import torch
+import matplotlib.pyplot as plt
+import cv2
+from sam2.build_sam import build_sam2
+from sam2.sam2_image_predictor import SAM2ImagePredictor
+import os
+
+def show_mask(mask, ax, random_color=False):
+    if random_color:
+        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
+    else:
+        color = np.array([30/255, 144/255, 255/255, 0.6])
+    h, w = mask.shape[-2:]
+    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
+    ax.imshow(mask_image)
+    
+def show_points(coords, labels, ax, marker_size=375):
+    pos_points = coords[labels==1]
+    neg_points = coords[labels==0]
+    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
+    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)   
+    
+def show_box(box, ax):
+    x0, y0 = box[0], box[1]
+    w, h = box[2] - box[0], box[3] - box[1]
+    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))    
+
+
+def show_res(masks, scores, input_point, input_label, input_box, filename, image):
+    for i, (mask, score) in enumerate(zip(masks, scores)):
+        plt.figure(figsize=(10,10))
+        plt.imshow(image)
+        show_mask(mask, plt.gca())
+        if input_box is not None:
+            box = input_box[i]
+            show_box(box, plt.gca())
+        if (input_point is not None) and (input_label is not None): 
+            show_points(input_point, input_label, plt.gca())
+        
+        print(f"Score: {score:.3f}")
+        plt.axis('off')
+        plt.savefig(filename+'_'+str(i)+'.png',bbox_inches='tight',pad_inches=-0.1)
+        plt.close()
+
+def show_res_multi(masks, scores, input_point, input_label, input_box, filename, image):
+    plt.figure(figsize=(10, 10))
+    plt.imshow(image)
+    for mask in masks:
+        show_mask(mask, plt.gca(), random_color=True)
+    for box in input_box:
+        show_box(box, plt.gca())
+    for score in scores:
+        print(f"Score: {score:.3f}")
+    plt.axis('off')
+    plt.savefig(filename +'.png',bbox_inches='tight',pad_inches=-0.1)
+    plt.close()
+
+
+if __name__ == "__main__":
+    checkpoint = "./checkpoints/sam2.1_hq_hiera_large.pt"
+    model_cfg = "configs/sam2.1/sam2.1_hq_hiera_l.yaml"
+    predictor = SAM2ImagePredictor(build_sam2(model_cfg, checkpoint))
+
+    for i in range(1,5):
+        print("image:   ",i)
+        # hq_token_only: False means use hq output to correct SAM output. 
+        #                True means use hq output only. 
+        #                Default: False
+        hq_token_only = False 
+        # To achieve best visualization effect, for images contain multiple objects (like typical coco images), we suggest to set hq_token_only=False
+        # For images contain single object, we suggest to set hq_token_only = True
+        # For quantiative evaluation on COCO/YTVOS/DAVIS/UVO/LVIS etc., we set hq_token_only = False
+
+        image = cv2.imread('./demo/input_images/example'+str(i)+'.png')
+        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+        predictor.set_image(image)
+
+        if i==1:
+            input_box = np.array([[306, 132, 925, 893]])
+            input_point, input_label = None, None
+        elif i==2:
+            input_point = np.array([[495,518],[217,140]])
+            input_label = np.ones(input_point.shape[0])
+            input_box = None
+        elif i==3:
+            input_box = np.array([[64,76,940,919]])
+            input_point, input_label = None, None
+        elif i==4:
+            # multi box input
+            input_box = torch.tensor([[45,260,515,470], [310,228,424,296]],device=predictor.device)
+            # transformed_box = predictor.transform.apply_boxes_torch(input_box, image.shape[:2])
+            input_point, input_label = None, None
+
+        batch_box = False if input_box is None else len(input_box)>1 
+        result_path = 'demo/hq_sam_result_vis/'
+        os.makedirs(result_path, exist_ok=True)
+
+        with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
+            masks, scores, logits = predictor.predict(point_coords=input_point,
+                                            point_labels=input_label,
+                                            box=input_box,
+                                            multimask_output=False, hq_token_only=hq_token_only)
+
+            if not batch_box:
+                show_res(masks,scores,input_point, input_label, input_box, result_path + 'example'+str(i), image)
+            else:
+                masks = masks.squeeze(1)
+                scores = scores.squeeze(1)
+                input_box = input_box.cpu().numpy()
+                show_res_multi(masks, scores, input_point, input_label, input_box, result_path + 'example'+str(i), image)
+
+        
+
+    
+
+
+