Updata inference code

.gitignore

@@ -0,0 +1,12 @@
+model/__pycache__/attn_processor.cpython-39.pyc
+model/__pycache__/attn_processor.cpython-310.pyc
+model/__pycache__/cloth_masker.cpython-39.pyc
+model/__pycache__/pipeline.cpython-39.pyc
+model/__pycache__/utils.cpython-39.pyc
+model/__pycache__/utils.cpython-310.pyc
+model/DensePose/__pycache__/__init__.cpython-39.pyc
+model/DensePose/__pycache__/__init__.cpython-310.pyc
+model/DensePose/__pycache__/__init__.cpython-312.pyc
+model/SCHP/__pycache__/__init__.cpython-39.pyc
+model/SCHP/__pycache__/__init__.cpython-310.pyc
+index.html

LICENSE

@@ -0,0 +1,107 @@
+Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and does not provide legal services or legal advice. Distribution of Creative Commons public licenses does not create a lawyer-client or other relationship. Creative Commons makes its licenses and related information available on an "as-is" basis. Creative Commons gives no warranties regarding its licenses, any material licensed under their terms and conditions, or any related information. Creative Commons disclaims all liability for damages resulting from their use to the fullest extent possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and conditions that creators and other rights holders may use to share original works of authorship and other material subject to copyright and certain other rights specified in the public license below. The following considerations are for informational purposes only, are not exhaustive, and do not form part of our licenses.
+
+Considerations for licensors: Our public licenses are intended for use by those authorized to give the public permission to use material in ways otherwise restricted by copyright and certain other rights. Our licenses are irrevocable. Licensors should read and understand the terms and conditions of the license they choose before applying it. Licensors should also secure all rights necessary before applying our licenses so that the public can reuse the material as expected. Licensors should clearly mark any material not subject to the license. This includes other CC-licensed material, or material used under an exception or limitation to copyright. More considerations for licensors : wiki.creativecommons.org/Considerations_for_licensors
+
+Considerations for the public: By using one of our public licenses, a licensor grants the public permission to use the licensed material under specified terms and conditions. If the licensor's permission is not necessary for any reason–for example, because of any applicable exception or limitation to copyright–then that use is not regulated by the license. Our licenses grant only permissions under copyright and certain other rights that a licensor has authority to grant. Use of the licensed material may still be restricted for other reasons, including because others have copyright or other rights in the material. A licensor may make special requests, such as asking that all changes be marked or described. Although not required by our licenses, you are encouraged to respect those requests where reasonable. More considerations for the public : wiki.creativecommons.org/Considerations_for_licensees
+
+Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
+
+By exercising the Licensed Rights (defined below), You accept and agree to be bound by the terms and conditions of this Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License ("Public License"). To the extent this Public License may be interpreted as a contract, You are granted the Licensed Rights in consideration of Your acceptance of these terms and conditions, and the Licensor grants You such rights in consideration of benefits the Licensor receives from making the Licensed Material available under these terms and conditions.
+
+Section 1 – Definitions.
+
+a. Adapted Material means material subject to Copyright and Similar Rights that is derived from or based upon the Licensed Material and in which the Licensed Material is translated, altered, arranged, transformed, or otherwise modified in a manner requiring permission under the Copyright and Similar Rights held by the Licensor. For purposes of this Public License, where the Licensed Material is a musical work, performance, or sound recording, Adapted Material is always produced where the Licensed Material is synched in timed relation with a moving image.
+b. Adapter's License means the license You apply to Your Copyright and Similar Rights in Your contributions to Adapted Material in accordance with the terms and conditions of this Public License.
+c. BY-NC-SA Compatible License means a license listed at creativecommons.org/compatiblelicenses, approved by Creative Commons as essentially the equivalent of this Public License.
+d. Copyright and Similar Rights means copyright and/or similar rights closely related to copyright including, without limitation, performance, broadcast, sound recording, and Sui Generis Database Rights, without regard to how the rights are labeled or categorized. For purposes of this Public License, the rights specified in Section 2(b)(1)-(2) are not Copyright and Similar Rights.
+e. Effective Technological Measures means those measures that, in the absence of proper authority, may not be circumvented under laws fulfilling obligations under Article 11 of the WIPO Copyright Treaty adopted on December 20, 1996, and/or similar international agreements.
+f. Exceptions and Limitations means fair use, fair dealing, and/or any other exception or limitation to Copyright and Similar Rights that applies to Your use of the Licensed Material.
+g. License Elements means the license attributes listed in the name of a Creative Commons Public License. The License Elements of this Public License are Attribution, NonCommercial, and ShareAlike.
+h. Licensed Material means the artistic or literary work, database, or other material to which the Licensor applied this Public License.
+i. Licensed Rights means the rights granted to You subject to the terms and conditions of this Public License, which are limited to all Copyright and Similar Rights that apply to Your use of the Licensed Material and that the Licensor has authority to license.
+j. Licensor means the individual(s) or entity(ies) granting rights under this Public License.
+k. NonCommercial means not primarily intended for or directed towards commercial advantage or monetary compensation. For purposes of this Public License, the exchange of the Licensed Material for other material subject to Copyright and Similar Rights by digital file-sharing or similar means is NonCommercial provided there is no payment of monetary compensation in connection with the exchange.
+l. Share means to provide material to the public by any means or process that requires permission under the Licensed Rights, such as reproduction, public display, public performance, distribution, dissemination, communication, or importation, and to make material available to the public including in ways that members of the public may access the material from a place and at a time individually chosen by them.
+m. Sui Generis Database Rights means rights other than copyright resulting from Directive 96/9/EC of the European Parliament and of the Council of 11 March 1996 on the legal protection of databases, as amended and/or succeeded, as well as other essentially equivalent rights anywhere in the world.
+n. You means the individual or entity exercising the Licensed Rights under this Public License. Your has a corresponding meaning.
+Section 2 – Scope.
+
+a. License grant.
+1. Subject to the terms and conditions of this Public License, the Licensor hereby grants You a worldwide, royalty-free, non-sublicensable, non-exclusive, irrevocable license to exercise the Licensed Rights in the Licensed Material to:
+A. reproduce and Share the Licensed Material, in whole or in part, for NonCommercial purposes only; and
+B. produce, reproduce, and Share Adapted Material for NonCommercial purposes only.
+2. Exceptions and Limitations. For the avoidance of doubt, where Exceptions and Limitations apply to Your use, this Public License does not apply, and You do not need to comply with its terms and conditions.
+3. Term. The term of this Public License is specified in Section 6(a).
+4. Media and formats; technical modifications allowed. The Licensor authorizes You to exercise the Licensed Rights in all media and formats whether now known or hereafter created, and to make technical modifications necessary to do so. The Licensor waives and/or agrees not to assert any right or authority to forbid You from making technical modifications necessary to exercise the Licensed Rights, including technical modifications necessary to circumvent Effective Technological Measures. For purposes of this Public License, simply making modifications authorized by this Section 2(a)(4) never produces Adapted Material.
+5. Downstream recipients.
+A. Offer from the Licensor – Licensed Material. Every recipient of the Licensed Material automatically receives an offer from the Licensor to exercise the Licensed Rights under the terms and conditions of this Public License.
+B. Additional offer from the Licensor – Adapted Material. Every recipient of Adapted Material from You automatically receives an offer from the Licensor to exercise the Licensed Rights in the Adapted Material under the conditions of the Adapter's License You apply.
+C. No downstream restrictions. You may not offer or impose any additional or different terms or conditions on, or apply any Effective Technological Measures to, the Licensed Material if doing so restricts exercise of the Licensed Rights by any recipient of the Licensed Material.
+6. No endorsement. Nothing in this Public License constitutes or may be construed as permission to assert or imply that You are, or that Your use of the Licensed Material is, connected with, or sponsored, endorsed, or granted official status by, the Licensor or others designated to receive attribution as provided in Section 3(a)(1)(A)(i).
+b. Other rights.
+1. Moral rights, such as the right of integrity, are not licensed under this Public License, nor are publicity, privacy, and/or other similar personality rights; however, to the extent possible, the Licensor waives and/or agrees not to assert any such rights held by the Licensor to the limited extent necessary to allow You to exercise the Licensed Rights, but not otherwise.
+2. Patent and trademark rights are not licensed under this Public License.
+3. To the extent possible, the Licensor waives any right to collect royalties from You for the exercise of the Licensed Rights, whether directly or through a collecting society under any voluntary or waivable statutory or compulsory licensing scheme. In all other cases the Licensor expressly reserves any right to collect such royalties, including when the Licensed Material is used other than for NonCommercial purposes.
+Section 3 – License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the following conditions.
+
+a. Attribution.
+1. If You Share the Licensed Material (including in modified form), You must:
+A. retain the following if it is supplied by the Licensor with the Licensed Material:
+i. identification of the creator(s) of the Licensed Material and any others designated to receive attribution, in any reasonable manner requested by the Licensor (including by pseudonym if designated);
+ii. a copyright notice;
+iii. a notice that refers to this Public License;
+iv. a notice that refers to the disclaimer of warranties;
+v. a URI or hyperlink to the Licensed Material to the extent reasonably practicable;
+
+B. indicate if You modified the Licensed Material and retain an indication of any previous modifications; and
+C. indicate the Licensed Material is licensed under this Public License, and include the text of, or the URI or hyperlink to, this Public License.
+2. You may satisfy the conditions in Section 3(a)(1) in any reasonable manner based on the medium, means, and context in which You Share the Licensed Material. For example, it may be reasonable to satisfy the conditions by providing a URI or hyperlink to a resource that includes the required information.
+3. If requested by the Licensor, You must remove any of the information required by Section 3(a)(1)(A) to the extent reasonably practicable.
+b. ShareAlike.In addition to the conditions in Section 3(a), if You Share Adapted Material You produce, the following conditions also apply.
+1. The Adapter's License You apply must be a Creative Commons license with the same License Elements, this version or later, or a BY-NC-SA Compatible License.
+2. You must include the text of, or the URI or hyperlink to, the Adapter's License You apply. You may satisfy this condition in any reasonable manner based on the medium, means, and context in which You Share Adapted Material.
+3. You may not offer or impose any additional or different terms or conditions on, or apply any Effective Technological Measures to, Adapted Material that restrict exercise of the rights granted under the Adapter's License You apply.
+Section 4 – Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that apply to Your use of the Licensed Material:
+
+a. for the avoidance of doubt, Section 2(a)(1) grants You the right to extract, reuse, reproduce, and Share all or a substantial portion of the contents of the database for NonCommercial purposes only;
+b. if You include all or a substantial portion of the database contents in a database in which You have Sui Generis Database Rights, then the database in which You have Sui Generis Database Rights (but not its individual contents) is Adapted Material, including for purposes of Section 3(b); and
+c. You must comply with the conditions in Section 3(a) if You Share all or a substantial portion of the contents of the database.
+For the avoidance of doubt, this Section 4 supplements and does not replace Your obligations under this Public License where the Licensed Rights include other Copyright and Similar Rights.
+Section 5 – Disclaimer of Warranties and Limitation of Liability.
+
+a. Unless otherwise separately undertaken by the Licensor, to the extent possible, the Licensor offers the Licensed Material as-is and as-available, and makes no representations or warranties of any kind concerning the Licensed Material, whether express, implied, statutory, or other. This includes, without limitation, warranties of title, merchantability, fitness for a particular purpose, non-infringement, absence of latent or other defects, accuracy, or the presence or absence of errors, whether or not known or discoverable. Where disclaimers of warranties are not allowed in full or in part, this disclaimer may not apply to You.
+b. To the extent possible, in no event will the Licensor be liable to You on any legal theory (including, without limitation, negligence) or otherwise for any direct, special, indirect, incidental, consequential, punitive, exemplary, or other losses, costs, expenses, or damages arising out of this Public License or use of the Licensed Material, even if the Licensor has been advised of the possibility of such losses, costs, expenses, or damages. Where a limitation of liability is not allowed in full or in part, this limitation may not apply to You.
+c. The disclaimer of warranties and limitation of liability provided above shall be interpreted in a manner that, to the extent possible, most closely approximates an absolute disclaimer and waiver of all liability.
+Section 6 – Term and Termination.
+
+a. This Public License applies for the term of the Copyright and Similar Rights licensed here. However, if You fail to comply with this Public License, then Your rights under this Public License terminate automatically.
+b. Where Your right to use the Licensed Material has terminated under Section 6(a), it reinstates:
+1. automatically as of the date the violation is cured, provided it is cured within 30 days of Your discovery of the violation; or
+2. upon express reinstatement by the Licensor.
+For the avoidance of doubt, this Section 6(b) does not affect any right the Licensor may have to seek remedies for Your violations of this Public License.
+
+c. For the avoidance of doubt, the Licensor may also offer the Licensed Material under separate terms or conditions or stop distributing the Licensed Material at any time; however, doing so will not terminate this Public License.
+d. Sections 1, 5, 6, 7, and 8 survive termination of this Public License.
+Section 7 – Other Terms and Conditions.
+
+a. The Licensor shall not be bound by any additional or different terms or conditions communicated by You unless expressly agreed.
+b. Any arrangements, understandings, or agreements regarding the Licensed Material not stated herein are separate from and independent of the terms and conditions of this Public License.
+Section 8 – Interpretation.
+
+a. For the avoidance of doubt, this Public License does not, and shall not be interpreted to, reduce, limit, restrict, or impose conditions on any use of the Licensed Material that could lawfully be made without permission under this Public License.
+b. To the extent possible, if any provision of this Public License is deemed unenforceable, it shall be automatically reformed to the minimum extent necessary to make it enforceable. If the provision cannot be reformed, it shall be severed from this Public License without affecting the enforceability of the remaining terms and conditions.
+c. No term or condition of this Public License will be waived and no failure to comply consented to unless expressly agreed to by the Licensor.
+d. Nothing in this Public License constitutes or may be interpreted as a limitation upon, or waiver of, any privileges and immunities that apply to the Licensor or You, including from the legal processes of any jurisdiction or authority.
+Creative Commons is not a party to its public licenses. Notwithstanding, Creative Commons may elect to apply one of its public licenses to material it publishes and in those instances will be considered the "Licensor." The text of the Creative Commons public licenses is dedicated to the public domain under the CC0 Public Domain Dedication. Except for the limited purpose of indicating that material is shared under a Creative Commons public license or as otherwise permitted by the Creative Commons policies published at creativecommons.org/policies, Creative Commons does not authorize the use of the trademark "Creative Commons" or any other trademark or logo of Creative Commons without its prior written consent including, without limitation, in connection with any unauthorized modifications to any of its public licenses or any other arrangements, understandings, or agreements concerning use of licensed material. For the avoidance of doubt, this paragraph does not form part of the public licenses.
+
+Creative Commons may be contacted at creativecommons.org.

README.md

@@ -1,19 +1,92 @@
 
-# CatVTON
 
-[[`ArXiv(soon)`]()]
-[[`Demo`](http://120.76.142.206:8888)]
-
-This repository is the official implementation of ***CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffsuion Models***.
-
-**CatVTON** is a simple and efficient virtual try-on diffusion model with ***1) Lightweight Network (899.06M parameters totally)***, ***2) Parameter-Efficient Training (49.57M parameters trainable)*** and ***3) Simplified Inference (< 8G VRAM for 1024X768 resolution)***.
-
-**<u>Our paper and code are coming soon</u>**  🤗
+# <center> 🐈 CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models
 
+<p align="center">
+  <a href="https://github.com/Zheng-Chong/CatVTON">
+    <img src='https://img.shields.io/badge/arXiv-Paper(soon)-red?style=flat&logo=arXiv&logoColor=red' alt='arxiv'>
+  </a>
+  <a href="http://120.76.142.206:8888">
+    <img src='https://img.shields.io/badge/Demo-Gradio-orange?style=flat&logo=Gradio&logoColor=red' alt='Demo'>
+  </a>
+  <a href='https://huggingface.co/zhengchong/CatVTON'>
+    <img src='https://img.shields.io/badge/Hugging Face-ckpts-orange?style=flat&logo=HuggingFace&logoColor=orange' alt='huggingface'>
+  </a>
+  <a href="https://github.com/Zheng-Chong/CatVTON">
+    <img src='https://img.shields.io/badge/GitHub-Repo-blue?style=flat&logo=GitHub' alt='GitHub'>
+  </a>
+    <a href="https://github.com/Zheng-Chong/CatVTON/LICENCE"><img src='https://img.shields.io/badge/License-CC BY--NC--SA--4.0-lightgreen?style=flat&logo=Lisence' alt='License'>
+  </a>
+</p>
 
 <div align="center">
   <img src="resource/img/teaser.jpg" width="100%" height="100%"/>
 </div>
 
+<!-- This repository is the official implementation of ***CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffsuion Models***. -->
+
+**CatVTON** is a simple and efficient virtual try-on diffusion model with ***1) Lightweight Network (899.06M parameters totally)***, ***2) Parameter-Efficient Training (49.57M parameters trainable)*** and ***3) Simplified Inference (< 8G VRAM for 1024X768 resolution)***.
+
+
 ## Updates
-- **`2024/7/11`**: [**Online Demo**](http://120.76.142.206:8888) is released.
+- **`2024/7/21`**: Our **Inference Code** and [**🤗Weights**](https://huggingface.co/zhengchong/CatVTON) are released.
+- **`2024/7/11`**: [**Online Demo**](http://120.76.142.206:8888) is released.
+
+
+
+## Inference
+### Data Preparation
+Before inference, you need to download the [VITON-HD](https://github.com/shadow2496/VITON-HD) or [DressCode](https://github.com/aimagelab/dress-code) dataset.
+Once the datasets are downloaded, the folder structures should look like these:
+```
+├── VITON-HD
+|   ├── test_pairs_unpaired.txt
+│   ├── test
+|   |   ├── image
+│   │   │   ├── [000006_00.jpg | 000008_00.jpg | ...]
+│   │   ├── cloth
+│   │   │   ├── [000006_00.jpg | 000008_00.jpg | ...]
+│   │   ├── agnostic-mask
+│   │   │   ├── [000006_00_mask.png | 000008_00.png | ...]
+...
+```
+For DressCode dataset, we provide [our preprocessed agnostic masks](https://drive.google.com/drive/folders/1uT88nYQl0n5qHz6zngb9WxGlX4ArAbVX?usp=share_link), download and place in `agnostic_masks` folders under each category.
+```
+├── DressCode
+|   ├── test_pairs_paired.txt
+|   ├── test_pairs_unpaired.txt
+│   ├── [dresses | lower_body | upper_body]
+|   |   ├── test_pairs_paired.txt
+|   |   ├── test_pairs_unpaired.txt
+│   │   ├── images
+│   │   │   ├── [013563_0.jpg | 013563_1.jpg | 013564_0.jpg | 013564_1.jpg | ...]
+│   │   ├── agnostic_masks
+│   │   │   ├── [013563_0.png| 013564_0.png | ...]
+...
+```
+
+### Inference on VTIONHD/DressCode
+To run the inference on the DressCode or VITON-HD dataset, run the following command, checkpoints will be automaticly download from HuggingFace.
+
+```PowerShell
+CUDA_VISIBLE_DEVICES=0 python inference.py \
+--dataset [dresscode | vitonhd] \
+--data_root_path <path> \
+--output_dir <path> 
+--dataloader_num_workers 8 \
+--batch_size 8 \
+--seed 555 \
+--mixed_precision [no | fp16 | bf16] \
+--allow_tf32 \
+--repaint \
+--eval_pair  
+```
+
+
+## Acknowledgement
+Our code is modified based on [Diffusers](https://github.com/huggingface/diffusers). We use [SCHP](https://github.com/GoGoDuck912/Self-Correction-Human-Parsing/tree/master) and [DensePose](https://github.com/facebookresearch/DensePose) to automaticly generate mask in our [Gradio](https://github.com/gradio-app/gradio) App. Thanks to all the contributors!
+<!-- ## Citation
+
+
+```
+``` -->

inference.py

@@ -0,0 +1,324 @@
+import os
+import numpy as np
+import torch
+import argparse
+from torch.utils.data import Dataset, DataLoader
+from diffusers.image_processor import VaeImageProcessor
+from tqdm import tqdm
+from PIL import Image, ImageFilter
+
+from model.pipeline import CatVTONPipeline
+
+class InferenceDataset(Dataset):
+    def __init__(self, args):
+        self.args = args
+    
+        self.vae_processor = VaeImageProcessor(vae_scale_factor=8) 
+        self.mask_processor = VaeImageProcessor(vae_scale_factor=8, do_normalize=False, do_binarize=True, do_convert_grayscale=True) 
+        self.data = self.load_data()
+    
+    def load_data(self):
+        return []
+    
+    def __len__(self):
+        return len(self.data)
+    
+    def __getitem__(self, idx):
+        data = self.data[idx]
+        person, cloth, mask = [Image.open(data[key]) for key in ['person', 'cloth', 'mask']]
+        return {
+            'index': idx,
+            'person_name': data['person_name'],
+            'person': self.vae_processor.preprocess(person, self.args.height, self.args.width)[0],
+            'cloth': self.vae_processor.preprocess(cloth, self.args.height, self.args.width)[0],
+            'mask': self.mask_processor.preprocess(mask, self.args.height, self.args.width)[0]
+        }
+
+class VITONHDTestDataset(InferenceDataset):
+    def load_data(self):
+        assert os.path.exists(pair_txt:=os.path.join(self.args.data_root_path, 'test_pairs_unpaired.txt')), f"File {pair_txt} does not exist."
+        with open(pair_txt, 'r') as f:
+            lines = f.readlines()
+        self.args.data_root_path = os.path.join(self.args.data_root_path, "test")
+        output_dir = os.path.join(self.args.output_dir, "vitonhd", 'unpaired' if not self.args.eval_pair else 'paired')
+        data = []
+        for line in lines:
+            person_img, cloth_img = line.strip().split(" ")
+            if os.path.exists(os.path.join(output_dir, person_img)):
+                continue
+            if self.args.eval_pair:
+                cloth_img = person_img
+            data.append({
+                'person_name': person_img,
+                'person': os.path.join(self.args.data_root_path, 'image', person_img),
+                'cloth': os.path.join(self.args.data_root_path, 'cloth', cloth_img),
+                'mask': os.path.join(self.args.data_root_path, 'agnostic-mask', person_img.replace('.jpg', '_mask.png')),
+            })
+        return data
+
+class DressCodeTestDataset(InferenceDataset):
+    def load_data(self):
+        data = []
+        for sub_folder in ['upper_body', 'lower_body', 'dresses']:
+            assert os.path.exists(os.path.join(self.args.data_root_path, sub_folder)), f"Folder {sub_folder} does not exist."
+            pair_txt = os.path.join(self.args.data_root_path, sub_folder, 'test_pairs_paired.txt' if self.args.eval_pair else 'test_pairs_unpaired.txt')
+            assert os.path.exists(pair_txt), f"File {pair_txt} does not exist."
+            with open(pair_txt, 'r') as f:
+                lines = f.readlines()
+
+            output_dir = os.path.join(self.args.output_dir, f"dresscode-{self.args.height}", 
+                                      'unpaired' if not self.args.eval_pair else 'paired', sub_folder)
+            for line in lines:
+                person_img, cloth_img = line.strip().split(" ")
+                if os.path.exists(os.path.join(output_dir, person_img)):
+                    continue
+                data.append({
+                    'person_name': os.path.join(sub_folder, person_img),
+                    'person': os.path.join(self.args.data_root_path, sub_folder, 'images', person_img),
+                    'cloth': os.path.join(self.args.data_root_path, sub_folder, 'images', cloth_img),
+                    'mask': os.path.join(self.args.data_root_path, sub_folder, 'agnostic_masks', person_img.replace('.jpg', '.png'))
+                })
+        return data
+                    
+       
+def parse_args():
+    parser = argparse.ArgumentParser(description="Simple example of a training script.")
+    parser.add_argument(
+        "--base_model_path",
+        type=str,
+        default="runwayml/stable-diffusion-inpainting",
+        help=(
+            "The path to the base model to use for evaluation. This can be a local path or a model identifier from the Model Hub."
+        ),
+    )
+    parser.add_argument(
+        "--resume_path",
+        type=str,
+        default="zhengchong/CatVTON",
+        help=(
+            "The Path to the checkpoint of trained tryon model."
+        ),
+    )
+    parser.add_argument(
+        "--dataset_name",
+        type=str,
+        required=True,
+        help="The datasets to use for evaluation.",
+    )
+    parser.add_argument(
+        "--data_root_path", 
+        type=str, 
+        required=True,
+        help="Path to the dataset to evaluate."
+    )
+    parser.add_argument(
+        "--output_dir",
+        type=str,
+        default="output",
+        help="The output directory where the model predictions will be written.",
+    )
+
+    parser.add_argument(
+        "--seed", type=int, default=555, help="A seed for reproducible evaluation."
+    )
+    parser.add_argument(
+        "--batch_size", type=int, default=8, help="The batch size for evaluation."
+    )
+    
+    parser.add_argument(
+        "--num_inference_steps",
+        type=int,
+        default=50,
+        help="Number of inference steps to perform.",
+    )
+    parser.add_argument(
+        "--guidance_scale",
+        type=float,
+        default=2.5,
+        help="The scale of classifier-free guidance for inference.",
+    )
+
+    parser.add_argument(
+        "--width",
+        type=int,
+        default=384,
+        help=(
+            "The resolution for input images, all the images in the train/validation dataset will be resized to this"
+            " resolution"
+        ),
+    )
+    parser.add_argument(
+        "--height",
+        type=int,
+        default=512,
+        help=(
+            "The resolution for input images, all the images in the train/validation dataset will be resized to this"
+            " resolution"
+        ),
+    )
+    parser.add_argument(
+        "--repaint", 
+        action="store_true", 
+        help="Whether to repaint the result image with the original background."
+    )
+    parser.add_argument(
+        "--eval_pair",
+        action="store_true",
+        help="Whether or not to evaluate the pair.",
+    )
+    parser.add_argument(
+        "--concat_eval_results",
+        action="store_true",
+        help="Whether or not to  concatenate the all conditions into one image.",
+    )
+    parser.add_argument(
+        "--allow_tf32",
+        action="store_true",
+        default=True,
+        help=(
+            "Whether or not to allow TF32 on Ampere GPUs. Can be used to speed up training. For more information, see"
+            " https://pytorch.org/docs/stable/notes/cuda.html#tensorfloat-32-tf32-on-ampere-devices"
+        ),
+    )
+    parser.add_argument(
+        "--dataloader_num_workers",
+        type=int,
+        default=8,
+        help=(
+            "Number of subprocesses to use for data loading. 0 means that the data will be loaded in the main process."
+        ),
+    )
+    parser.add_argument(
+        "--mixed_precision",
+        type=str,
+        default="bf16",
+        choices=["no", "fp16", "bf16"],
+        help=(
+            "Whether to use mixed precision. Choose between fp16 and bf16 (bfloat16). Bf16 requires PyTorch >="
+            " 1.10.and an Nvidia Ampere GPU.  Default to the value of accelerate config of the current system or the"
+            " flag passed with the `accelerate.launch` command. Use this argument to override the accelerate config."
+        ),
+    )
+
+    parser.add_argument(
+        "--concat_axis",
+        type=str,
+        choices=["x", "y", 'random'],
+        default="y",
+        help="The axis to concat the cloth feature, select from ['x', 'y', 'random'].",
+    )
+    parser.add_argument(
+        "--enable_condition_noise",
+        action="store_true",
+        default=True,
+        help="Whether or not to enable condition noise.",
+    )
+    
+    args = parser.parse_args()
+    env_local_rank = int(os.environ.get("LOCAL_RANK", -1))
+    if env_local_rank != -1 and env_local_rank != args.local_rank:
+        args.local_rank = env_local_rank
+
+    return args
+
+
+def repaint(person, mask, result):
+    _, h = result.size
+    kernal_size = h // 50
+    if kernal_size % 2 == 0:
+        kernal_size += 1
+    mask = mask.filter(ImageFilter.GaussianBlur(kernal_size))
+    person_np = np.array(person)
+    result_np = np.array(result)
+    mask_np = np.array(mask) / 255
+    repaint_result = person_np * (1 - mask_np) + result_np * mask_np
+    repaint_result = Image.fromarray(repaint_result.astype(np.uint8))
+    return repaint_result
+
+def to_pil_image(images):
+    images = (images / 2 + 0.5).clamp(0, 1)
+    images = images.cpu().permute(0, 2, 3, 1).float().numpy()
+    if images.ndim == 3:
+        images = images[None, ...]
+    images = (images * 255).round().astype("uint8")
+    if images.shape[-1] == 1:
+        # special case for grayscale (single channel) images
+        pil_images = [Image.fromarray(image.squeeze(), mode="L") for image in images]
+    else:
+        pil_images = [Image.fromarray(image) for image in images]
+    return pil_images
+
+@torch.no_grad()
+def main():
+    args = parse_args()
+    # Pipeline
+    pipeline = CatVTONPipeline(
+        attn_ckpt_version=args.dataset_name,
+        attn_ckpt=args.resume_path,
+        base_ckpt=args.base_model_path,
+        weight_dtype={
+            "no": torch.float32,
+            "fp16": torch.float16,
+            "bf16": torch.bfloat16,
+        }[args.mixed_precision],
+        device="cuda"
+    )
+    # Dataset
+    if args.dataset_name == "vitonhd":
+        dataset = VITONHDTestDataset(args)
+    elif args.dataset_name == "dresscode":
+        dataset = DressCodeTestDataset(args)
+    else:
+        raise ValueError(f"Invalid dataset name {args.dataset}.")
+    print(f"Dataset {args.dataset_name} loaded, total {len(dataset)} pairs.")
+    dataloader = DataLoader(
+        dataset,
+        batch_size=args.batch_size,
+        shuffle=False,
+        num_workers=args.dataloader_num_workers
+    )
+    # Inference
+    generator = torch.Generator(device='cuda').manual_seed(args.seed)
+    args.output_dir = os.path.join(args.output_dir, f"{args.dataset_name}-{args.height}", "paired" if args.eval_pair else "unpaired")
+    if not os.path.exists(args.output_dir):
+        os.makedirs(args.output_dir)
+    for batch in tqdm(dataloader):
+        person_images = batch['person']
+        cloth_images = batch['cloth']
+        masks = batch['mask']
+        results = pipeline(
+            person_images,
+            cloth_images,
+            masks,
+            num_inference_steps=args.num_inference_steps,
+            guidance_scale=args.guidance_scale,
+            height=args.height,
+            width=args.width,
+            generator=generator,
+        )
+        
+        if args.concat_eval_results or args.repaint:
+            person_images = to_pil_image(person_images)
+            cloth_images = to_pil_image(cloth_images)
+            masks = to_pil_image(masks)
+        for i, result in enumerate(results):
+            person_name = batch['person_name'][i]
+            output_path = os.path.join(args.output_dir, person_name)
+            if not os.path.exists(os.path.dirname(output_path)):
+                os.makedirs(os.path.dirname(output_path))
+            if args.repaint:
+                person_path, mask_path = dataset.data[batch['index'][i]]['person'], dataset.data[batch['index'][i]]['mask']
+                person_image= Image.open(person_path).resize(result.size, Image.LANCZOS)
+                mask = Image.open(mask_path).resize(result.size, Image.NEAREST)
+                result = repaint(person_image, mask, result)
+            if args.concat_eval_results:
+                w, h = result.size
+                concated_result = Image.new('RGB', (w*3, h))
+                concated_result.paste(person_images[i], (0, 0))
+                concated_result.paste(cloth_images[i], (w, 0))  
+                concated_result.paste(result, (w*2, 0))
+                result = concated_result
+            result.save(output_path)
+
+if __name__ == "__main__":
+    main()

model/DensePose/__init__.py

@@ -0,0 +1,158 @@
+
+import glob
+import os
+from random import randint
+import shutil
+import time
+
+import cv2
+import numpy as np
+import torch
+from PIL import Image
+from densepose import add_densepose_config
+from densepose.vis.base import CompoundVisualizer
+from densepose.vis.densepose_results import DensePoseResultsFineSegmentationVisualizer
+from densepose.vis.extractor import create_extractor, CompoundExtractor
+from detectron2.config import get_cfg
+from detectron2.data.detection_utils import read_image
+from detectron2.engine.defaults import DefaultPredictor
+
+
+class DensePose:
+    """
+    DensePose used in this project is from Detectron2 (https://github.com/facebookresearch/detectron2).
+    These codes are modified from https://github.com/facebookresearch/detectron2/tree/main/projects/DensePose.
+    The checkpoint is downloaded from https://github.com/facebookresearch/detectron2/blob/main/projects/DensePose/doc/DENSEPOSE_IUV.md#ModelZoo.
+
+    We use the model R_50_FPN_s1x with id 165712039, but other models should also work.
+    The config file is downloaded from https://github.com/facebookresearch/detectron2/tree/main/projects/DensePose/configs.
+    Noted that the config file should match the model checkpoint and Base-DensePose-RCNN-FPN.yaml is also needed.
+    """
+
+    def __init__(self, model_path="./checkpoints/densepose_", device="cuda"):
+        self.device = device
+        self.config_path = os.path.join(model_path, 'densepose_rcnn_R_50_FPN_s1x.yaml')
+        self.model_path = os.path.join(model_path, 'model_final_162be9.pkl')
+        self.visualizations = ["dp_segm"]
+        self.VISUALIZERS = {"dp_segm": DensePoseResultsFineSegmentationVisualizer}
+        self.min_score = 0.8
+
+        self.cfg = self.setup_config()
+        self.predictor = DefaultPredictor(self.cfg)
+        self.predictor.model.to(self.device)
+
+    def setup_config(self):
+        opts = ["MODEL.ROI_HEADS.SCORE_THRESH_TEST", str(self.min_score)]
+        cfg = get_cfg()
+        add_densepose_config(cfg)
+        cfg.merge_from_file(self.config_path)
+        cfg.merge_from_list(opts)
+        cfg.MODEL.WEIGHTS = self.model_path
+        cfg.freeze()
+        return cfg
+
+    @staticmethod
+    def _get_input_file_list(input_spec: str):
+        if os.path.isdir(input_spec):
+            file_list = [os.path.join(input_spec, fname) for fname in os.listdir(input_spec)
+                         if os.path.isfile(os.path.join(input_spec, fname))]
+        elif os.path.isfile(input_spec):
+            file_list = [input_spec]
+        else:
+            file_list = glob.glob(input_spec)
+        return file_list
+
+    def create_context(self, cfg, output_path):
+        vis_specs = self.visualizations
+        visualizers = []
+        extractors = []
+        for vis_spec in vis_specs:
+            texture_atlas = texture_atlases_dict = None
+            vis = self.VISUALIZERS[vis_spec](
+                cfg=cfg,
+                texture_atlas=texture_atlas,
+                texture_atlases_dict=texture_atlases_dict,
+                alpha=1.0
+            )
+            visualizers.append(vis)
+            extractor = create_extractor(vis)
+            extractors.append(extractor)
+        visualizer = CompoundVisualizer(visualizers)
+        extractor = CompoundExtractor(extractors)
+        context = {
+            "extractor": extractor,
+            "visualizer": visualizer,
+            "out_fname": output_path,
+            "entry_idx": 0,
+        }
+        return context
+
+    def execute_on_outputs(self, context, entry, outputs):
+        extractor = context["extractor"]
+
+        data = extractor(outputs)
+
+        H, W, _ = entry["image"].shape
+        result = np.zeros((H, W), dtype=np.uint8)
+
+        data, box = data[0]
+        x, y, w, h = [int(_) for _ in box[0].cpu().numpy()]
+        i_array = data[0].labels[None].cpu().numpy()[0]
+        result[y:y + h, x:x + w] = i_array
+        result = Image.fromarray(result)
+        result.save(context["out_fname"])
+
+    def __call__(self, image_or_path, resize=512) -> Image.Image:
+        """
+        :param image_or_path: Path of the input image.
+        :param resize: Resize the input image if its max size is larger than this value.
+        :return: Dense pose image.
+        """
+        # random tmp path with timestamp
+        tmp_path = f"./densepose_/tmp/"
+        if not os.path.exists(tmp_path):
+            os.makedirs(tmp_path)
+
+        image_path = os.path.join(tmp_path, f"{int(time.time())}-{self.device}-{randint(0, 100000)}.png")
+        if isinstance(image_or_path, str):
+            assert image_or_path.split(".")[-1] in ["jpg", "png"], "Only support jpg and png images."
+            shutil.copy(image_or_path, image_path)
+        elif isinstance(image_or_path, Image.Image):
+            image_or_path.save(image_path)
+        else:
+            shutil.rmtree(tmp_path)
+            raise TypeError("image_path must be str or PIL.Image.Image")
+
+        output_path = image_path.replace(".png", "_dense.png").replace(".jpg", "_dense.png")
+        w, h = Image.open(image_path).size
+
+        file_list = self._get_input_file_list(image_path)
+        assert len(file_list), "No input images found!"
+        context = self.create_context(self.cfg, output_path)
+        for file_name in file_list:
+            img = read_image(file_name, format="BGR")  # predictor expects BGR image.
+            # resize
+            if (_ := max(img.shape)) > resize:
+                scale = resize / _
+                img = cv2.resize(img, (int(img.shape[1] * scale), int(img.shape[0] * scale)))
+
+            with torch.no_grad():
+                outputs = self.predictor(img)["instances"]
+                try:
+                    self.execute_on_outputs(context, {"file_name": file_name, "image": img}, outputs)
+                except Exception as e:
+                    null_gray = Image.new('L', (1, 1))
+                    null_gray.save(output_path)
+
+        dense_gray = Image.open(output_path).convert("L")
+        dense_gray = dense_gray.resize((w, h), Image.NEAREST)
+        # remove image_path and output_path
+        os.remove(image_path)
+        os.remove(output_path)
+
+
+        return dense_gray
+
+
+if __name__ == '__main__':
+    pass

model/SCHP/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 Peike Li
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

model/SCHP/README.md

@@ -0,0 +1,129 @@
+# Self Correction for Human Parsing
+
+![Python 3.6](https://img.shields.io/badge/python-3.6-green.svg)
+[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)
+
+An out-of-box human parsing representation extractor.
+
+Our solution ranks 1st for all human parsing tracks (including single, multiple and video) in the third LIP challenge!
+
+![lip-visualization](./demo/lip-visualization.jpg) 
+
+Features:
+- [x] Out-of-box human parsing extractor for other downstream applications.
+- [x] Pretrained model on three popular single person human parsing datasets.
+- [x] Training and inferecne code.
+- [x] Simple yet effective extension on multi-person and video human parsing tasks.
+
+## Requirements
+
+```
+conda env create -f environment.yaml
+conda activate schp
+pip install -r requirements.txt
+```
+
+## Simple Out-of-Box Extractor
+
+The easiest way to get started is to use our trained SCHP models on your own images to extract human parsing representations. Here we provided state-of-the-art [trained models](https://drive.google.com/drive/folders/1uOaQCpNtosIjEL2phQKEdiYd0Td18jNo?usp=sharing) on three popular datasets. Theses three datasets have different label system, you can choose the best one to fit on your own task.
+
+**LIP** ([exp-schp-201908261155-lip.pth](https://drive.google.com/file/d/1k4dllHpu0bdx38J7H28rVVLpU-kOHmnH/view?usp=sharing))
+
+* mIoU on LIP validation: **59.36 %**.
+
+* LIP is the largest single person human parsing dataset with 50000+ images. This dataset focus more on the complicated real scenarios. LIP has 20 labels, including 'Background', 'Hat', 'Hair', 'Glove', 'Sunglasses', 'Upper-clothes', 'Dress', 'Coat', 'Socks', 'Pants', 'Jumpsuits', 'Scarf', 'Skirt', 'Face', 'Left-arm', 'Right-arm', 'Left-leg', 'Right-leg', 'Left-shoe', 'Right-shoe'.
+
+**ATR** ([exp-schp-201908301523-atr.pth](https://drive.google.com/file/d/1ruJg4lqR_jgQPj-9K0PP-L2vJERYOxLP/view?usp=sharing))
+
+* mIoU on ATR test: **82.29%**.
+
+* ATR is a large single person human parsing dataset with 17000+ images. This dataset focus more on fashion AI. ATR has 18 labels, including 'Background', 'Hat', 'Hair', 'Sunglasses', 'Upper-clothes', 'Skirt', 'Pants', 'Dress', 'Belt', 'Left-shoe', 'Right-shoe', 'Face', 'Left-leg', 'Right-leg', 'Left-arm', 'Right-arm', 'Bag', 'Scarf'.
+
+**Pascal-Person-Part** ([exp-schp-201908270938-pascal-person-part.pth](https://drive.google.com/file/d/1E5YwNKW2VOEayK9mWCS3Kpsxf-3z04ZE/view?usp=sharing))
+
+* mIoU on Pascal-Person-Part validation: **71.46** %.
+
+* Pascal Person Part is a tiny single person human parsing dataset with 3000+ images. This dataset focus more on body parts segmentation. Pascal Person Part has 7 labels, including 'Background', 'Head', 'Torso', 'Upper Arms', 'Lower Arms', 'Upper Legs', 'Lower Legs'.
+
+Choose one and have fun on your own task!
+
+To extract the human parsing representation, simply put your own image in the `INPUT_PATH` folder, then download a pretrained model and run the following command. The output images with the same file name will be saved in `OUTPUT_PATH`
+
+```
+python simple_extractor.py --dataset [DATASET] --model-restore [CHECKPOINT_PATH] --input-dir [INPUT_PATH] --output-dir [OUTPUT_PATH]
+```
+
+**[Updated]** Here is also a [colab demo example](https://colab.research.google.com/drive/1JOwOPaChoc9GzyBi5FUEYTSaP2qxJl10?usp=sharing) for quick inference provided by [@levindabhi](https://github.com/levindabhi).
+
+The `DATASET` command has three options, including 'lip', 'atr' and 'pascal'. Note each pixel in the output images denotes the predicted label number. The output images have the same size as the input ones. To better visualization, we put a palette with the output images. We suggest you to read the image with `PIL`.
+
+If you need not only the final parsing images, but also the feature map representations. Add `--logits` command to save the output feature maps. These feature maps are the logits before softmax layer.
+
+## Dataset Preparation
+
+Please download the [LIP](http://sysu-hcp.net/lip/) dataset following the below structure.
+
+```commandline
+data/LIP
+|--- train_imgaes # 30462 training single person images
+|--- val_images # 10000 validation single person images
+|--- train_segmentations # 30462 training annotations
+|--- val_segmentations # 10000 training annotations
+|--- train_id.txt # training image list
+|--- val_id.txt # validation image list
+```
+
+## Training
+
+```
+python train.py 
+```
+By default, the trained model will be saved in `./log` directory. Please read the arguments for more details.
+
+## Evaluation
+```
+python evaluate.py --model-restore [CHECKPOINT_PATH]
+```
+CHECKPOINT_PATH should be the path of trained model.
+
+## Extension on Multiple Human Parsing
+
+Please read [MultipleHumanParsing.md](./mhp_extension/README.md) for more details.
+
+## Citation
+
+Please cite our work if you find this repo useful in your research.
+
+```latex
+@article{li2020self,
+  title={Self-Correction for Human Parsing}, 
+  author={Li, Peike and Xu, Yunqiu and Wei, Yunchao and Yang, Yi},
+  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, 
+  year={2020},
+  doi={10.1109/TPAMI.2020.3048039}}
+```
+
+## Visualization
+
+* Source Image.
+![demo](./demo/demo.jpg)
+* LIP Parsing Result.
+![demo-lip](./demo/demo_lip.png)
+* ATR Parsing Result.
+![demo-atr](./demo/demo_atr.png)
+* Pascal-Person-Part Parsing Result.
+![demo-pascal](./demo/demo_pascal.png)
+* Source Image.
+![demo](./mhp_extension/demo/demo.jpg)
+* Instance Human Mask.
+![demo-lip](./mhp_extension/demo/demo_instance_human_mask.png)
+* Global Human Parsing Result.
+![demo-lip](./mhp_extension/demo/demo_global_human_parsing.png)
+* Multiple Human Parsing Result.
+![demo-lip](./mhp_extension/demo/demo_multiple_human_parsing.png)
+
+
+## Related
+Our code adopts the [InplaceSyncBN](https://github.com/mapillary/inplace_abn) to save gpu memory cost.
+
+There is also a [PaddlePaddle](https://github.com/PaddlePaddle/PaddleSeg/tree/develop/contrib/ACE2P) Implementation of this project.

model/SCHP/__init__.py

@@ -0,0 +1,163 @@
+from model.SCHP import networks
+from model.SCHP.utils.transforms import get_affine_transform, transform_logits
+
+from collections import OrderedDict
+import torch
+import numpy as np
+import cv2
+from PIL import Image
+from torchvision import transforms
+
+def get_palette(num_cls):
+    """ Returns the color map for visualizing the segmentation mask.
+    Args:
+        num_cls: Number of classes
+    Returns:
+        The color map
+    """
+    n = num_cls
+    palette = [0] * (n * 3)
+    for j in range(0, n):
+        lab = j
+        palette[j * 3 + 0] = 0
+        palette[j * 3 + 1] = 0
+        palette[j * 3 + 2] = 0
+        i = 0
+        while lab:
+            palette[j * 3 + 0] |= (((lab >> 0) & 1) << (7 - i))
+            palette[j * 3 + 1] |= (((lab >> 1) & 1) << (7 - i))
+            palette[j * 3 + 2] |= (((lab >> 2) & 1) << (7 - i))
+            i += 1
+            lab >>= 3
+    return palette
+
+dataset_settings = {
+    'lip': {
+        'input_size': [473, 473],
+        'num_classes': 20,
+        'label': ['Background', 'Hat', 'Hair', 'Glove', 'Sunglasses', 'Upper-clothes', 'Dress', 'Coat',
+                  'Socks', 'Pants', 'Jumpsuits', 'Scarf', 'Skirt', 'Face', 'Left-arm', 'Right-arm',
+                  'Left-leg', 'Right-leg', 'Left-shoe', 'Right-shoe']
+    },
+    'atr': {
+        'input_size': [512, 512],
+        'num_classes': 18,
+        'label': ['Background', 'Hat', 'Hair', 'Sunglasses', 'Upper-clothes', 'Skirt', 'Pants', 'Dress', 'Belt',
+                  'Left-shoe', 'Right-shoe', 'Face', 'Left-leg', 'Right-leg', 'Left-arm', 'Right-arm', 'Bag', 'Scarf']
+    },
+    'pascal': {
+        'input_size': [512, 512],
+        'num_classes': 7,
+        'label': ['Background', 'Head', 'Torso', 'Upper Arms', 'Lower Arms', 'Upper Legs', 'Lower Legs'],
+    }
+}
+
+class SCHP:
+    def __init__(self, ckpt_path, device):
+        dataset_type = None
+        if 'lip' in ckpt_path:
+            dataset_type = 'lip'
+        elif 'atr' in ckpt_path:
+            dataset_type = 'atr'
+        elif 'pascal' in ckpt_path:
+            dataset_type = 'pascal'
+        assert dataset_type is not None, 'Dataset type not found in checkpoint path'
+        self.device = device
+        self.num_classes = dataset_settings[dataset_type]['num_classes']
+        self.input_size = dataset_settings[dataset_type]['input_size']
+        self.aspect_ratio = self.input_size[1] * 1.0 / self.input_size[0]
+        self.palette = get_palette(self.num_classes)
+
+        self.label = dataset_settings[dataset_type]['label']
+        self.model = networks.init_model('resnet101', num_classes=self.num_classes, pretrained=None).to(device)
+        self.load_ckpt(ckpt_path)
+        self.model.eval()
+        
+        self.transform = transforms.Compose([
+            transforms.ToTensor(),
+            transforms.Normalize(mean=[0.406, 0.456, 0.485], std=[0.225, 0.224, 0.229])
+        ])
+        self.upsample = torch.nn.Upsample(size=self.input_size, mode='bilinear', align_corners=True)
+
+
+    def load_ckpt(self, ckpt_path):
+        state_dict = torch.load(ckpt_path, map_location='cpu')['state_dict']
+        new_state_dict = OrderedDict()
+        for k, v in state_dict.items():
+            name = k[7:]  # remove `module.`
+            new_state_dict[name] = v
+        self.model.load_state_dict(new_state_dict)
+
+    def _box2cs(self, box):
+        x, y, w, h = box[:4]
+        return self._xywh2cs(x, y, w, h)
+
+    def _xywh2cs(self, x, y, w, h):
+        center = np.zeros((2), dtype=np.float32)
+        center[0] = x + w * 0.5
+        center[1] = y + h * 0.5
+        if w > self.aspect_ratio * h:
+            h = w * 1.0 / self.aspect_ratio
+        elif w < self.aspect_ratio * h:
+            w = h * self.aspect_ratio
+        scale = np.array([w, h], dtype=np.float32)
+        return center, scale
+
+    def preprocess(self, image):
+        if isinstance(image, str):
+            img = cv2.imread(image, cv2.IMREAD_COLOR)
+        elif isinstance(image, Image.Image):
+            # to cv2 format
+            img = np.array(image)
+    
+        h, w, _ = img.shape
+        # Get person center and scale
+        person_center, s = self._box2cs([0, 0, w - 1, h - 1])
+        r = 0
+        trans = get_affine_transform(person_center, s, r, self.input_size)
+        input = cv2.warpAffine(
+            img,
+            trans,
+            (int(self.input_size[1]), int(self.input_size[0])),
+            flags=cv2.INTER_LINEAR,
+            borderMode=cv2.BORDER_CONSTANT,
+            borderValue=(0, 0, 0))
+
+        input = self.transform(input).to(self.device).unsqueeze(0)
+        meta = {
+                'center': person_center,
+                'height': h,
+                'width': w,
+                'scale': s,
+                'rotation': r
+        }
+        return input, meta
+
+
+    def __call__(self, image_or_path):
+        if isinstance(image_or_path, list):
+            image_list = []
+            meta_list = []
+            for image in image_or_path:
+                image, meta = self.preprocess(image)
+                image_list.append(image)
+                meta_list.append(meta)
+            image = torch.cat(image_list, dim=0)
+        else:
+            image, meta = self.preprocess(image_or_path)
+            meta_list = [meta]
+                
+        output = self.model(image)
+        upsample_outputs = self.upsample(output[0][-1])
+        upsample_outputs = upsample_outputs.permute(0, 2, 3, 1)  # BCHW -> BHWC
+
+        output_img_list = []
+        for upsample_output, meta in zip(upsample_outputs, meta_list):
+            c, s, w, h = meta['center'], meta['scale'], meta['width'], meta['height']
+            logits_result = transform_logits(upsample_output.data.cpu().numpy(), c, s, w, h, input_size=self.input_size)
+            parsing_result = np.argmax(logits_result, axis=2)
+            output_img = Image.fromarray(np.asarray(parsing_result, dtype=np.uint8))
+            output_img.putpalette(self.palette)
+            output_img_list.append(output_img)
+
+        return output_img_list[0] if len(output_img_list) == 1 else output_img_list

model/SCHP/datasets/datasets.py

@@ -0,0 +1,205 @@
+#!/usr/bin/env python
+# -*- encoding: utf-8 -*-
+
+"""
+@Author  :   Peike Li
+@Contact :   peike.li@yahoo.com
+@File    :   datasets.py
+@Time    :   8/4/19 3:35 PM
+@Desc    :
+@License :   This source code is licensed under the license found in the
+             LICENSE file in the root directory of this source tree.
+"""
+
+import os
+import numpy as np
+import random
+import torch
+import cv2
+from torch.utils import data
+from utils.transforms import get_affine_transform
+
+
+class LIPDataSet(data.Dataset):
+    def __init__(self, root, dataset, crop_size=[473, 473], scale_factor=0.25,
+                 rotation_factor=30, ignore_label=255, transform=None):
+        self.root = root
+        self.aspect_ratio = crop_size[1] * 1.0 / crop_size[0]
+        self.crop_size = np.asarray(crop_size)
+        self.ignore_label = ignore_label
+        self.scale_factor = scale_factor
+        self.rotation_factor = rotation_factor
+        self.flip_prob = 0.5
+        self.transform = transform
+        self.dataset = dataset
+
+        list_path = os.path.join(self.root, self.dataset + '_id.txt')
+        train_list = [i_id.strip() for i_id in open(list_path)]
+
+        self.train_list = train_list
+        self.number_samples = len(self.train_list)
+
+    def __len__(self):
+        return self.number_samples
+
+    def _box2cs(self, box):
+        x, y, w, h = box[:4]
+        return self._xywh2cs(x, y, w, h)
+
+    def _xywh2cs(self, x, y, w, h):
+        center = np.zeros((2), dtype=np.float32)
+        center[0] = x + w * 0.5
+        center[1] = y + h * 0.5
+        if w > self.aspect_ratio * h:
+            h = w * 1.0 / self.aspect_ratio
+        elif w < self.aspect_ratio * h:
+            w = h * self.aspect_ratio
+        scale = np.array([w * 1.0, h * 1.0], dtype=np.float32)
+        return center, scale
+
+    def __getitem__(self, index):
+        train_item = self.train_list[index]
+
+        im_path = os.path.join(self.root, self.dataset + '_images', train_item + '.jpg')
+        parsing_anno_path = os.path.join(self.root, self.dataset + '_segmentations', train_item + '.png')
+
+        im = cv2.imread(im_path, cv2.IMREAD_COLOR)
+        h, w, _ = im.shape
+        parsing_anno = np.zeros((h, w), dtype=np.long)
+
+        # Get person center and scale
+        person_center, s = self._box2cs([0, 0, w - 1, h - 1])
+        r = 0
+
+        if self.dataset != 'test':
+            # Get pose annotation
+            parsing_anno = cv2.imread(parsing_anno_path, cv2.IMREAD_GRAYSCALE)
+            if self.dataset == 'train' or self.dataset == 'trainval':
+                sf = self.scale_factor
+                rf = self.rotation_factor
+                s = s * np.clip(np.random.randn() * sf + 1, 1 - sf, 1 + sf)
+                r = np.clip(np.random.randn() * rf, -rf * 2, rf * 2) if random.random() <= 0.6 else 0
+
+                if random.random() <= self.flip_prob:
+                    im = im[:, ::-1, :]
+                    parsing_anno = parsing_anno[:, ::-1]
+                    person_center[0] = im.shape[1] - person_center[0] - 1
+                    right_idx = [15, 17, 19]
+                    left_idx = [14, 16, 18]
+                    for i in range(0, 3):
+                        right_pos = np.where(parsing_anno == right_idx[i])
+                        left_pos = np.where(parsing_anno == left_idx[i])
+                        parsing_anno[right_pos[0], right_pos[1]] = left_idx[i]
+                        parsing_anno[left_pos[0], left_pos[1]] = right_idx[i]
+
+        trans = get_affine_transform(person_center, s, r, self.crop_size)
+        input = cv2.warpAffine(
+            im,
+            trans,
+            (int(self.crop_size[1]), int(self.crop_size[0])),
+            flags=cv2.INTER_LINEAR,
+            borderMode=cv2.BORDER_CONSTANT,
+            borderValue=(0, 0, 0))
+
+        if self.transform:
+            input = self.transform(input)
+
+        meta = {
+            'name': train_item,
+            'center': person_center,
+            'height': h,
+            'width': w,
+            'scale': s,
+            'rotation': r
+        }
+
+        if self.dataset == 'val' or self.dataset == 'test':
+            return input, meta
+        else:
+            label_parsing = cv2.warpAffine(
+                parsing_anno,
+                trans,
+                (int(self.crop_size[1]), int(self.crop_size[0])),
+                flags=cv2.INTER_NEAREST,
+                borderMode=cv2.BORDER_CONSTANT,
+                borderValue=(255))
+
+            label_parsing = torch.from_numpy(label_parsing)
+
+            return input, label_parsing, meta
+
+
+class LIPDataValSet(data.Dataset):
+    def __init__(self, root, dataset='val', crop_size=[473, 473], transform=None, flip=False):
+        self.root = root
+        self.crop_size = crop_size
+        self.transform = transform
+        self.flip = flip
+        self.dataset = dataset
+        self.root = root
+        self.aspect_ratio = crop_size[1] * 1.0 / crop_size[0]
+        self.crop_size = np.asarray(crop_size)
+
+        val_list=[]
+        for root, dirs, files in os.walk("/home/chongzheng_p23/data/Datasets/UniFashion/YOOX/YOOX-Images"):
+            for file in files:
+                if file.endswith(".jpg"):
+                    source_file_path = os.path.join(root, file)
+                    val_list.append(source_file_path)
+
+        self.val_list = val_list
+        self.number_samples = len(self.val_list)
+
+    def __len__(self):
+        return len(self.val_list)
+
+    def _box2cs(self, box):
+        x, y, w, h = box[:4]
+        return self._xywh2cs(x, y, w, h)
+
+    def _xywh2cs(self, x, y, w, h):
+        center = np.zeros((2), dtype=np.float32)
+        center[0] = x + w * 0.5
+        center[1] = y + h * 0.5
+        if w > self.aspect_ratio * h:
+            h = w * 1.0 / self.aspect_ratio
+        elif w < self.aspect_ratio * h:
+            w = h * self.aspect_ratio
+        scale = np.array([w * 1.0, h * 1.0], dtype=np.float32)
+
+        return center, scale
+
+    def __getitem__(self, index):
+        val_item = self.val_list[index]
+        # Load training image
+        im_path = val_item
+        im = cv2.imread(im_path, cv2.IMREAD_COLOR)
+        h, w, _ = im.shape
+        # Get person center and scale
+        person_center, s = self._box2cs([0, 0, w - 1, h - 1])
+        r = 0
+        trans = get_affine_transform(person_center, s, r, self.crop_size)
+        input = cv2.warpAffine(
+            im,
+            trans,
+            (int(self.crop_size[1]), int(self.crop_size[0])),
+            flags=cv2.INTER_LINEAR,
+            borderMode=cv2.BORDER_CONSTANT,
+            borderValue=(0, 0, 0))
+        input = self.transform(input)
+        flip_input = input.flip(dims=[-1])
+        if self.flip:
+            batch_input_im = torch.stack([input, flip_input])
+        else:
+            batch_input_im = input
+
+        meta = {
+            'name': val_item, #root
+            'center': person_center,
+            'height': h,
+            'width': w,
+            'scale': s,
+            'rotation': r
+        }
+
+        return batch_input_im, meta

model/SCHP/datasets/simple_extractor_dataset.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python
+# -*- encoding: utf-8 -*-
+
+"""
+@Author  :   Peike Li
+@Contact :   peike.li@yahoo.com
+@File    :   dataset.py
+@Time    :   8/30/19 9:12 PM
+@Desc    :   Dataset Definition
+@License :   This source code is licensed under the license found in the
+             LICENSE file in the root directory of this source tree.
+"""
+
+import os
+import cv2
+import numpy as np
+
+from torch.utils import data
+from utils.transforms import get_affine_transform
+
+
+class SimpleFolderDataset(data.Dataset):
+    def __init__(self, root, input_size=[512, 512], transform=None):
+        self.root = root
+        self.input_size = input_size
+        self.transform = transform
+        self.aspect_ratio = input_size[1] * 1.0 / input_size[0]
+        self.input_size = np.asarray(input_size)
+
+        self.file_list=[]
+        self.root_list=[]
+        for root, dirs, files in os.walk(root):
+            for file in files:
+                if file.endswith(".jpg"):
+                    source_file_path = os.path.join(root, file)
+                    self.file_list.append(source_file_path)
+                    self.root_list.append(root)
+
+    def __len__(self):
+        return len(self.file_list)
+
+    def _box2cs(self, box):
+        x, y, w, h = box[:4]
+        return self._xywh2cs(x, y, w, h)
+
+    def _xywh2cs(self, x, y, w, h):
+        center = np.zeros((2), dtype=np.float32)
+        center[0] = x + w * 0.5
+        center[1] = y + h * 0.5
+        if w > self.aspect_ratio * h:
+            h = w * 1.0 / self.aspect_ratio
+        elif w < self.aspect_ratio * h:
+            w = h * self.aspect_ratio
+        scale = np.array([w, h], dtype=np.float32)
+        return center, scale
+
+    def __getitem__(self, index):
+        img_path = self.file_list[index]
+        root = self.root_list[index]
+        img_name = img_path.split("/")[-1].split(".")[0]
+        img = cv2.imread(img_path, cv2.IMREAD_COLOR)
+        
+        if img is None:
+            return self.__getitem__(index+1)
+        else:
+            h, w, _ = img.shape
+
+            # Get person center and scale
+            person_center, s = self._box2cs([0, 0, w - 1, h - 1])
+            r = 0
+            trans = get_affine_transform(person_center, s, r, self.input_size)
+            input = cv2.warpAffine(
+                img,
+                trans,
+                (int(self.input_size[1]), int(self.input_size[0])),
+                flags=cv2.INTER_LINEAR,
+                borderMode=cv2.BORDER_CONSTANT,
+                borderValue=(0, 0, 0))
+
+            input = self.transform(input)
+            meta = {
+                'img_path': img_path,
+                'name': img_name,
+                'root': root,
+                'center': person_center,
+                'height': h,
+                'width': w,
+                'scale': s,
+                'rotation': r
+            }
+
+            return input, meta

model/SCHP/datasets/target_generation.py

@@ -0,0 +1,40 @@
+import torch
+from torch.nn import functional as F
+
+
+def generate_edge_tensor(label, edge_width=3):
+    # label = label.type(torch.cuda.FloatTensor)
+    if len(label.shape) == 2:
+        label = label.unsqueeze(0)
+    n, h, w = label.shape
+    edge = torch.zeros(label.shape, dtype=torch.float)#.cuda()
+    # right
+    edge_right = edge[:, 1:h, :]
+    edge_right[(label[:, 1:h, :] != label[:, :h - 1, :]) & (label[:, 1:h, :] != 255)
+               & (label[:, :h - 1, :] != 255)] = 1
+
+    # up
+    edge_up = edge[:, :, :w - 1]
+    edge_up[(label[:, :, :w - 1] != label[:, :, 1:w])
+            & (label[:, :, :w - 1] != 255)
+            & (label[:, :, 1:w] != 255)] = 1
+
+    # upright
+    edge_upright = edge[:, :h - 1, :w - 1]
+    edge_upright[(label[:, :h - 1, :w - 1] != label[:, 1:h, 1:w])
+                 & (label[:, :h - 1, :w - 1] != 255)
+                 & (label[:, 1:h, 1:w] != 255)] = 1
+
+    # bottomright
+    edge_bottomright = edge[:, :h - 1, 1:w]
+    edge_bottomright[(label[:, :h - 1, 1:w] != label[:, 1:h, :w - 1])
+                     & (label[:, :h - 1, 1:w] != 255)
+                     & (label[:, 1:h, :w - 1] != 255)] = 1
+
+    kernel = torch.ones((1, 1, edge_width, edge_width), dtype=torch.float)#.cuda()
+    with torch.no_grad():
+        edge = edge.unsqueeze(1)
+        edge = F.conv2d(edge, kernel, stride=1, padding=1)
+    edge[edge!=0] = 1
+    edge = edge.squeeze()
+    return edge

model/SCHP/environment.yaml

@@ -0,0 +1,49 @@
+name: schp
+channels:
+  - pytorch
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - blas=1.0=mkl
+  - ca-certificates=2020.12.8=h06a4308_0
+  - certifi=2020.12.5=py38h06a4308_0
+  - cudatoolkit=10.1.243=h6bb024c_0
+  - freetype=2.10.4=h5ab3b9f_0
+  - intel-openmp=2020.2=254
+  - jpeg=9b=h024ee3a_2
+  - lcms2=2.11=h396b838_0
+  - ld_impl_linux-64=2.33.1=h53a641e_7
+  - libedit=3.1.20191231=h14c3975_1
+  - libffi=3.3=he6710b0_2
+  - libgcc-ng=9.1.0=hdf63c60_0
+  - libpng=1.6.37=hbc83047_0
+  - libstdcxx-ng=9.1.0=hdf63c60_0
+  - libtiff=4.1.0=h2733197_1
+  - lz4-c=1.9.2=heb0550a_3
+  - mkl=2020.2=256
+  - mkl-service=2.3.0=py38he904b0f_0
+  - mkl_fft=1.2.0=py38h23d657b_0
+  - mkl_random=1.1.1=py38h0573a6f_0
+  - ncurses=6.2=he6710b0_1
+  - ninja=1.10.2=py38hff7bd54_0
+  - numpy=1.19.2=py38h54aff64_0
+  - numpy-base=1.19.2=py38hfa32c7d_0
+  - olefile=0.46=py_0
+  - openssl=1.1.1i=h27cfd23_0
+  - pillow=8.0.1=py38he98fc37_0
+  - pip=20.3.3=py38h06a4308_0
+  - python=3.8.5=h7579374_1
+  - readline=8.0=h7b6447c_0
+  - setuptools=51.0.0=py38h06a4308_2
+  - six=1.15.0=py38h06a4308_0
+  - sqlite=3.33.0=h62c20be_0
+  - tk=8.6.10=hbc83047_0
+  - tqdm=4.55.0=pyhd3eb1b0_0
+  - wheel=0.36.2=pyhd3eb1b0_0
+  - xz=5.2.5=h7b6447c_0
+  - zlib=1.2.11=h7b6447c_3
+  - zstd=1.4.5=h9ceee32_0
+  - pytorch=1.5.1=py3.8_cuda10.1.243_cudnn7.6.3_0
+  - torchvision=0.6.1=py38_cu101
+prefix: /home/peike/opt/anaconda3/envs/schp
+

model/SCHP/evaluate.py

@@ -0,0 +1,210 @@
+#!/usr/bin/env python
+# -*- encoding: utf-8 -*-
+
+"""
+@Author  :   Peike Li
+@Contact :   peike.li@yahoo.com
+@File    :   evaluate.py
+@Time    :   8/4/19 3:36 PM
+@Desc    :
+@License :   This source code is licensed under the license found in the
+             LICENSE file in the root directory of this source tree.
+"""
+
+import os
+import argparse
+import numpy as np
+import torch
+
+from torch.utils import data
+from tqdm import tqdm
+from PIL import Image as PILImage
+import torchvision.transforms as transforms
+import torch.backends.cudnn as cudnn
+
+import networks
+from datasets.datasets import LIPDataValSet
+from utils.miou import compute_mean_ioU
+from utils.transforms import BGR2RGB_transform
+from utils.transforms import transform_parsing
+
+
+def get_arguments():
+    """Parse all the arguments provided from the CLI.
+
+    Returns:
+      A list of parsed arguments.
+    """
+    parser = argparse.ArgumentParser(description="Self Correction for Human Parsing")
+
+    # Network Structure
+    parser.add_argument("--arch", type=str, default='resnet101')
+    # Data Preference
+    parser.add_argument("--data-dir", type=str, default='./data/LIP')
+    parser.add_argument("--batch-size", type=int, default=1)
+    parser.add_argument("--input-size", type=str, default='473,473')
+    parser.add_argument("--num-classes", type=int, default=20)
+    parser.add_argument("--ignore-label", type=int, default=255)
+    parser.add_argument("--random-mirror", action="store_true")
+    parser.add_argument("--random-scale", action="store_true")
+    # Evaluation Preference
+    parser.add_argument("--log-dir", type=str, default='./log')
+    parser.add_argument("--model-restore", type=str, 
+                        default='/data1/chongzheng/zhangwq/Self-Correction-Human-Parsing-master/exp-schp-201908301523-atr.pth')
+    parser.add_argument("--gpu", type=str, default='0', help="choose gpu device.")
+    parser.add_argument("--save-results", action="store_true", help="whether to save the results.")
+    parser.add_argument("--flip", action="store_true", help="random flip during the test.")
+    parser.add_argument("--multi-scales", type=str, default='1', help="multiple scales during the test")
+    return parser.parse_args()
+
+
+def get_palette(num_cls):
+    """ Returns the color map for visualizing the segmentation mask.
+    Args:
+        num_cls: Number of classes
+    Returns:
+        The color map
+    """
+    n = num_cls
+    palette = [0] * (n * 3)
+    for j in range(0, n):
+        lab = j
+        palette[j * 3 + 0] = 0
+        palette[j * 3 + 1] = 0
+        palette[j * 3 + 2] = 0
+        i = 0
+        while lab:
+            palette[j * 3 + 0] |= (((lab >> 0) & 1) << (7 - i))
+            palette[j * 3 + 1] |= (((lab >> 1) & 1) << (7 - i))
+            palette[j * 3 + 2] |= (((lab >> 2) & 1) << (7 - i))
+            i += 1
+            lab >>= 3
+    return palette
+
+
+def multi_scale_testing(model, batch_input_im, crop_size=[473, 473], flip=True, multi_scales=[1]):
+    flipped_idx = (15, 14, 17, 16, 19, 18)
+    if len(batch_input_im.shape) > 4:
+        batch_input_im = batch_input_im.squeeze()
+    if len(batch_input_im.shape) == 3:
+        batch_input_im = batch_input_im.unsqueeze(0)
+
+    interp = torch.nn.Upsample(size=crop_size, mode='bilinear', align_corners=True)
+    ms_outputs = []
+    for s in multi_scales:
+        interp_im = torch.nn.Upsample(scale_factor=s, mode='bilinear', align_corners=True)
+        scaled_im = interp_im(batch_input_im)
+        parsing_output = model(scaled_im)
+        parsing_output = parsing_output[0][-1]
+        output = parsing_output[0]
+        if flip:
+            flipped_output = parsing_output[1]
+            flipped_output[14:20, :, :] = flipped_output[flipped_idx, :, :]
+            output += flipped_output.flip(dims=[-1])
+            output *= 0.5
+        output = interp(output.unsqueeze(0))
+        ms_outputs.append(output[0])
+    ms_fused_parsing_output = torch.stack(ms_outputs)
+    ms_fused_parsing_output = ms_fused_parsing_output.mean(0)
+    ms_fused_parsing_output = ms_fused_parsing_output.permute(1, 2, 0)  # HWC
+    parsing = torch.argmax(ms_fused_parsing_output, dim=2)
+    parsing = parsing.data.cpu().numpy()
+    ms_fused_parsing_output = ms_fused_parsing_output.data.cpu().numpy()
+    return parsing, ms_fused_parsing_output
+
+
+def main():
+    """Create the model and start the evaluation process."""
+    args = get_arguments()
+    multi_scales = [float(i) for i in args.multi_scales.split(',')]
+    gpus = [int(i) for i in args.gpu.split(',')]
+    assert len(gpus) == 1
+    if not args.gpu == 'None':
+        os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
+
+    cudnn.benchmark = True
+    cudnn.enabled = True
+
+    h, w = map(int, args.input_size.split(','))
+    input_size = [h, w]
+
+    model = networks.init_model(args.arch, num_classes=args.num_classes, pretrained=None)
+
+    IMAGE_MEAN = model.mean
+    IMAGE_STD = model.std
+    INPUT_SPACE = model.input_space
+    print('image mean: {}'.format(IMAGE_MEAN))
+    print('image std: {}'.format(IMAGE_STD))
+    print('input space:{}'.format(INPUT_SPACE))
+    if INPUT_SPACE == 'BGR':
+        print('BGR Transformation')
+        transform = transforms.Compose([
+            transforms.ToTensor(),
+            transforms.Normalize(mean=IMAGE_MEAN,
+                                 std=IMAGE_STD),
+
+        ])
+    if INPUT_SPACE == 'RGB':
+        print('RGB Transformation')
+        transform = transforms.Compose([
+            transforms.ToTensor(),
+            BGR2RGB_transform(),
+            transforms.Normalize(mean=IMAGE_MEAN,
+                                 std=IMAGE_STD),
+        ])
+
+    # Data loader
+    lip_test_dataset = LIPDataValSet(args.data_dir, 'val', crop_size=input_size, transform=transform, flip=args.flip)
+    num_samples = len(lip_test_dataset)
+    print('Totoal testing sample numbers: {}'.format(num_samples))
+    testloader = data.DataLoader(lip_test_dataset, batch_size=args.batch_size, shuffle=False, pin_memory=True)
+
+    # Load model weight
+    state_dict = torch.load(args.model_restore)['state_dict']
+    from collections import OrderedDict
+    new_state_dict = OrderedDict()
+    for k, v in state_dict.items():
+        name = k[7:]  # remove `module.`
+        new_state_dict[name] = v
+    model.load_state_dict(new_state_dict)
+    model.cuda()
+    model.eval()
+
+    sp_results_dir = os.path.join(args.log_dir, 'sp_results')
+    if not os.path.exists(sp_results_dir):
+        os.makedirs(sp_results_dir)
+
+    palette = get_palette(20)
+    parsing_preds = []
+    scales = np.zeros((num_samples, 2), dtype=np.float32)
+    centers = np.zeros((num_samples, 2), dtype=np.int32)
+    with torch.no_grad():
+        for idx, batch in enumerate(tqdm(testloader)):
+            image, meta = batch
+            if (len(image.shape) > 4):
+                image = image.squeeze()
+            im_name = meta['name'][0]
+            c = meta['center'].numpy()[0]
+            s = meta['scale'].numpy()[0]
+            w = meta['width'].numpy()[0]
+            h = meta['height'].numpy()[0]
+            scales[idx, :] = s
+            centers[idx, :] = c
+            parsing, logits = multi_scale_testing(model, image.cuda(), crop_size=input_size, flip=args.flip,
+                                                  multi_scales=multi_scales)
+            if args.save_results:
+                parsing_result = transform_parsing(parsing, c, s, w, h, input_size)
+                parsing_result_path = os.path.join(sp_results_dir, im_name + '.png')
+                output_im = PILImage.fromarray(np.asarray(parsing_result, dtype=np.uint8))
+                output_im.putpalette(palette)
+                output_im.save(parsing_result_path)
+
+            parsing_preds.append(parsing)
+    assert len(parsing_preds) == num_samples
+    mIoU = compute_mean_ioU(parsing_preds, scales, centers, args.num_classes, args.data_dir, input_size)
+    print(mIoU)
+    return
+
+
+if __name__ == '__main__':
+    main()

model/SCHP/mhp_extension/README.md

@@ -0,0 +1,38 @@
+# Self Correction for Human Parsing
+
+We propose a simple yet effective multiple human parsing framework by extending our self-correction network.
+
+Here we show an example usage jupyter notebook in [demo.ipynb](./demo.ipynb).
+
+## Requirements
+
+Please see [INSTALL.md](https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md) for further requirements.
+
+## Citation
+
+Please cite our work if you find this repo useful in your research.
+
+```latex
+@article{li2019self,
+  title={Self-Correction for Human Parsing},
+  author={Li, Peike and Xu, Yunqiu and Wei, Yunchao and Yang, Yi},
+  journal={arXiv preprint arXiv:1910.09777},
+  year={2019}
+}
+```
+
+## Visualization
+
+* Source Image.
+![demo](./demo/demo.jpg)
+* Instance Human Mask.
+![demo-lip](./demo/demo_instance_human_mask.png)
+* Global Human Parsing Result.
+![demo-lip](./demo/demo_global_human_parsing.png)
+* Multiple Human Parsing Result.
+![demo-lip](./demo/demo_multiple_human_parsing.png)
+
+## Related
+
+Our implementation is based on the [Detectron2](https://github.com/facebookresearch/detectron2).
+

model/SCHP/mhp_extension/coco_style_annotation_creator/human_to_coco.py

@@ -0,0 +1,166 @@
+import argparse
+import datetime
+import json
+import os
+from PIL import Image
+import numpy as np
+
+import pycococreatortools
+
+
+def get_arguments():
+    parser = argparse.ArgumentParser(description="transform mask annotation to coco annotation")
+    parser.add_argument("--dataset", type=str, default='CIHP', help="name of dataset (CIHP, MHPv2 or VIP)")
+    parser.add_argument("--json_save_dir", type=str, default='../data/msrcnn_finetune_annotations',
+                        help="path to save coco-style annotation json file")
+    parser.add_argument("--use_val", type=bool, default=False,
+                        help="use train+val set for finetuning or not")
+    parser.add_argument("--train_img_dir", type=str, default='../data/instance-level_human_parsing/Training/Images',
+                        help="train image path")
+    parser.add_argument("--train_anno_dir", type=str,
+                        default='../data/instance-level_human_parsing/Training/Human_ids',
+                        help="train human mask path")
+    parser.add_argument("--val_img_dir", type=str, default='../data/instance-level_human_parsing/Validation/Images',
+                        help="val image path")
+    parser.add_argument("--val_anno_dir", type=str,
+                        default='../data/instance-level_human_parsing/Validation/Human_ids',
+                        help="val human mask path")
+    return parser.parse_args()
+
+
+def main(args):
+    INFO = {
+        "description": args.split_name + " Dataset",
+        "url": "",
+        "version": "",
+        "year": 2019,
+        "contributor": "xyq",
+        "date_created": datetime.datetime.utcnow().isoformat(' ')
+    }
+
+    LICENSES = [
+        {
+            "id": 1,
+            "name": "",
+            "url": ""
+        }
+    ]
+
+    CATEGORIES = [
+        {
+            'id': 1,
+            'name': 'person',
+            'supercategory': 'person',
+        },
+    ]
+
+    coco_output = {
+        "info": INFO,
+        "licenses": LICENSES,
+        "categories": CATEGORIES,
+        "images": [],
+        "annotations": []
+    }
+
+    image_id = 1
+    segmentation_id = 1
+
+    for image_name in os.listdir(args.train_img_dir):
+        image = Image.open(os.path.join(args.train_img_dir, image_name))
+        image_info = pycococreatortools.create_image_info(
+            image_id, image_name, image.size
+        )
+        coco_output["images"].append(image_info)
+
+        human_mask_name = os.path.splitext(image_name)[0] + '.png'
+        human_mask = np.asarray(Image.open(os.path.join(args.train_anno_dir, human_mask_name)))
+        human_gt_labels = np.unique(human_mask)
+
+        for i in range(1, len(human_gt_labels)):
+            category_info = {'id': 1, 'is_crowd': 0}
+            binary_mask = np.uint8(human_mask == i)
+            annotation_info = pycococreatortools.create_annotation_info(
+                segmentation_id, image_id, category_info, binary_mask,
+                image.size, tolerance=10
+            )
+            if annotation_info is not None:
+                coco_output["annotations"].append(annotation_info)
+
+            segmentation_id += 1
+        image_id += 1
+
+    if not os.path.exists(args.json_save_dir):
+        os.makedirs(args.json_save_dir)
+    if not args.use_val:
+        with open('{}/{}_train.json'.format(args.json_save_dir, args.split_name), 'w') as output_json_file:
+            json.dump(coco_output, output_json_file)
+    else:
+        for image_name in os.listdir(args.val_img_dir):
+            image = Image.open(os.path.join(args.val_img_dir, image_name))
+            image_info = pycococreatortools.create_image_info(
+                image_id, image_name, image.size
+            )
+            coco_output["images"].append(image_info)
+
+            human_mask_name = os.path.splitext(image_name)[0] + '.png'
+            human_mask = np.asarray(Image.open(os.path.join(args.val_anno_dir, human_mask_name)))
+            human_gt_labels = np.unique(human_mask)
+
+            for i in range(1, len(human_gt_labels)):
+                category_info = {'id': 1, 'is_crowd': 0}
+                binary_mask = np.uint8(human_mask == i)
+                annotation_info = pycococreatortools.create_annotation_info(
+                    segmentation_id, image_id, category_info, binary_mask,
+                    image.size, tolerance=10
+                )
+                if annotation_info is not None:
+                    coco_output["annotations"].append(annotation_info)
+
+                segmentation_id += 1
+            image_id += 1
+
+        with open('{}/{}_trainval.json'.format(args.json_save_dir, args.split_name), 'w') as output_json_file:
+            json.dump(coco_output, output_json_file)
+
+    coco_output_val = {
+        "info": INFO,
+        "licenses": LICENSES,
+        "categories": CATEGORIES,
+        "images": [],
+        "annotations": []
+    }
+
+    image_id_val = 1
+    segmentation_id_val = 1
+
+    for image_name in os.listdir(args.val_img_dir):
+        image = Image.open(os.path.join(args.val_img_dir, image_name))
+        image_info = pycococreatortools.create_image_info(
+            image_id_val, image_name, image.size
+        )
+        coco_output_val["images"].append(image_info)
+
+        human_mask_name = os.path.splitext(image_name)[0] + '.png'
+        human_mask = np.asarray(Image.open(os.path.join(args.val_anno_dir, human_mask_name)))
+        human_gt_labels = np.unique(human_mask)
+
+        for i in range(1, len(human_gt_labels)):
+            category_info = {'id': 1, 'is_crowd': 0}
+            binary_mask = np.uint8(human_mask == i)
+            annotation_info = pycococreatortools.create_annotation_info(
+                segmentation_id_val, image_id_val, category_info, binary_mask,
+                image.size, tolerance=10
+            )
+            if annotation_info is not None:
+                coco_output_val["annotations"].append(annotation_info)
+
+            segmentation_id_val += 1
+        image_id_val += 1
+
+    with open('{}/{}_val.json'.format(args.json_save_dir, args.split_name), 'w') as output_json_file_val:
+        json.dump(coco_output_val, output_json_file_val)
+
+
+if __name__ == "__main__":
+    args = get_arguments()
+    main(args)

model/SCHP/mhp_extension/coco_style_annotation_creator/pycococreatortools.py

@@ -0,0 +1,114 @@
+import re
+import datetime
+import numpy as np
+from itertools import groupby
+from skimage import measure
+from PIL import Image
+from pycocotools import mask
+
+convert = lambda text: int(text) if text.isdigit() else text.lower()
+natrual_key = lambda key: [convert(c) for c in re.split('([0-9]+)', key)]
+
+
+def resize_binary_mask(array, new_size):
+    image = Image.fromarray(array.astype(np.uint8) * 255)
+    image = image.resize(new_size)
+    return np.asarray(image).astype(np.bool_)
+
+
+def close_contour(contour):
+    if not np.array_equal(contour[0], contour[-1]):
+        contour = np.vstack((contour, contour[0]))
+    return contour
+
+
+def binary_mask_to_rle(binary_mask):
+    rle = {'counts': [], 'size': list(binary_mask.shape)}
+    counts = rle.get('counts')
+    for i, (value, elements) in enumerate(groupby(binary_mask.ravel(order='F'))):
+        if i == 0 and value == 1:
+            counts.append(0)
+        counts.append(len(list(elements)))
+
+    return rle
+
+
+def binary_mask_to_polygon(binary_mask, tolerance=0):
+    """Converts a binary mask to COCO polygon representation
+    Args:
+        binary_mask: a 2D binary numpy array where '1's represent the object
+        tolerance: Maximum distance from original points of polygon to approximated
+            polygonal chain. If tolerance is 0, the original coordinate array is returned.
+    """
+    polygons = []
+    # pad mask to close contours of shapes which start and end at an edge
+    padded_binary_mask = np.pad(binary_mask, pad_width=1, mode='constant', constant_values=0)
+    contours = measure.find_contours(padded_binary_mask, 0.5)
+    contours = np.subtract(contours, 1)
+    for contour in contours:
+        contour = close_contour(contour)
+        contour = measure.approximate_polygon(contour, tolerance)
+        if len(contour) < 3:
+            continue
+        contour = np.flip(contour, axis=1)
+        segmentation = contour.ravel().tolist()
+        # after padding and subtracting 1 we may get -0.5 points in our segmentation 
+        segmentation = [0 if i < 0 else i for i in segmentation]
+        polygons.append(segmentation)
+
+    return polygons
+
+
+def create_image_info(image_id, file_name, image_size,
+                      date_captured=datetime.datetime.utcnow().isoformat(' '),
+                      license_id=1, coco_url="", flickr_url=""):
+    image_info = {
+        "id": image_id,
+        "file_name": file_name,
+        "width": image_size[0],
+        "height": image_size[1],
+        "date_captured": date_captured,
+        "license": license_id,
+        "coco_url": coco_url,
+        "flickr_url": flickr_url
+    }
+
+    return image_info
+
+
+def create_annotation_info(annotation_id, image_id, category_info, binary_mask,
+                           image_size=None, tolerance=2, bounding_box=None):
+    if image_size is not None:
+        binary_mask = resize_binary_mask(binary_mask, image_size)
+
+    binary_mask_encoded = mask.encode(np.asfortranarray(binary_mask.astype(np.uint8)))
+
+    area = mask.area(binary_mask_encoded)
+    if area < 1:
+        return None
+
+    if bounding_box is None:
+        bounding_box = mask.toBbox(binary_mask_encoded)
+
+    if category_info["is_crowd"]:
+        is_crowd = 1
+        segmentation = binary_mask_to_rle(binary_mask)
+    else:
+        is_crowd = 0
+        segmentation = binary_mask_to_polygon(binary_mask, tolerance)
+        if not segmentation:
+            return None
+
+    annotation_info = {
+        "id": annotation_id,
+        "image_id": image_id,
+        "category_id": category_info["id"],
+        "iscrowd": is_crowd,
+        "area": area.tolist(),
+        "bbox": bounding_box.tolist(),
+        "segmentation": segmentation,
+        "width": binary_mask.shape[1],
+        "height": binary_mask.shape[0],
+    }
+
+    return annotation_info

model/SCHP/mhp_extension/coco_style_annotation_creator/test_human2coco_format.py

@@ -0,0 +1,74 @@
+import argparse
+import datetime
+import json
+import os
+from PIL import Image
+
+import pycococreatortools
+
+
+def get_arguments():
+    parser = argparse.ArgumentParser(description="transform mask annotation to coco annotation")
+    parser.add_argument("--dataset", type=str, default='CIHP', help="name of dataset (CIHP, MHPv2 or VIP)")
+    parser.add_argument("--json_save_dir", type=str, default='../data/CIHP/annotations',
+                        help="path to save coco-style annotation json file")
+    parser.add_argument("--test_img_dir", type=str, default='../data/CIHP/Testing/Images',
+                        help="test image path")
+    return parser.parse_args()
+
+args = get_arguments()
+
+INFO = {
+    "description": args.dataset + "Dataset",
+    "url": "",
+    "version": "",
+    "year": 2020,
+    "contributor": "yunqiuxu",
+    "date_created": datetime.datetime.utcnow().isoformat(' ')
+}
+
+LICENSES = [
+    {
+        "id": 1,
+        "name": "",
+        "url": ""
+    }
+]
+
+CATEGORIES = [
+    {
+        'id': 1,
+        'name': 'person',
+        'supercategory': 'person',
+    },
+]
+
+
+def main(args):
+    coco_output = {
+        "info": INFO,
+        "licenses": LICENSES,
+        "categories": CATEGORIES,
+        "images": [],
+        "annotations": []
+    }
+
+    image_id = 1
+
+    for image_name in os.listdir(args.test_img_dir):
+        image = Image.open(os.path.join(args.test_img_dir, image_name))
+        image_info = pycococreatortools.create_image_info(
+            image_id, image_name, image.size
+        )
+        coco_output["images"].append(image_info)
+        image_id += 1
+
+    if not os.path.exists(os.path.join(args.json_save_dir)):
+        os.mkdir(os.path.join(args.json_save_dir))
+
+    with open('{}/{}.json'.format(args.json_save_dir, args.dataset), 'w') as output_json_file:
+        json.dump(coco_output, output_json_file)
+
+
+if __name__ == "__main__":
+    main(args)

model/SCHP/mhp_extension/detectron2/.circleci/config.yml

@@ -0,0 +1,179 @@
+# Python CircleCI 2.0 configuration file
+#
+# Check https://circleci.com/docs/2.0/language-python/ for more details
+#
+version: 2
+
+# -------------------------------------------------------------------------------------
+# Environments to run the jobs in
+# -------------------------------------------------------------------------------------
+cpu: &cpu
+  docker:
+    - image: circleci/python:3.6.8-stretch
+  resource_class: medium
+
+gpu: &gpu
+  machine:
+    image: ubuntu-1604:201903-01
+    docker_layer_caching: true
+  resource_class: gpu.small
+
+# -------------------------------------------------------------------------------------
+# Re-usable commands
+# -------------------------------------------------------------------------------------
+install_python: &install_python
+  - run:
+      name: Install Python
+      working_directory: ~/
+      command: |
+        pyenv install 3.6.1
+        pyenv global 3.6.1
+
+setup_venv: &setup_venv
+  - run:
+      name: Setup Virtual Env
+      working_directory: ~/
+      command: |
+        python -m venv ~/venv
+        echo ". ~/venv/bin/activate" >> $BASH_ENV
+        . ~/venv/bin/activate
+        python --version
+        which python
+        which pip
+        pip install --upgrade pip
+
+install_dep: &install_dep
+  - run:
+      name: Install Dependencies
+      command: |
+        pip install --progress-bar off -U 'git+https://github.com/facebookresearch/fvcore'
+        pip install --progress-bar off cython opencv-python
+        pip install --progress-bar off 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'
+        pip install --progress-bar off torch torchvision
+
+install_detectron2: &install_detectron2
+  - run:
+      name: Install Detectron2
+      command: |
+        gcc --version
+        pip install -U --progress-bar off -e .[dev]
+        python -m detectron2.utils.collect_env
+
+install_nvidia_driver: &install_nvidia_driver
+  - run:
+      name: Install nvidia driver
+      working_directory: ~/
+      command: |
+        wget -q 'https://s3.amazonaws.com/ossci-linux/nvidia_driver/NVIDIA-Linux-x86_64-430.40.run'
+        sudo /bin/bash ./NVIDIA-Linux-x86_64-430.40.run -s --no-drm
+        nvidia-smi
+
+run_unittests: &run_unittests
+  - run:
+      name: Run Unit Tests
+      command: |
+        python -m unittest discover -v -s tests
+
+# -------------------------------------------------------------------------------------
+# Jobs to run
+# -------------------------------------------------------------------------------------
+jobs:
+  cpu_tests:
+    <<: *cpu
+
+    working_directory: ~/detectron2
+
+    steps:
+      - checkout
+      - <<: *setup_venv
+
+      # Cache the venv directory that contains dependencies
+      - restore_cache:
+          keys:
+            - cache-key-{{ .Branch }}-ID-20200425
+
+      - <<: *install_dep
+
+      - save_cache:
+          paths:
+            - ~/venv
+          key: cache-key-{{ .Branch }}-ID-20200425
+
+      - <<: *install_detectron2
+
+      - run:
+          name: isort
+          command: |
+            isort -c -sp .
+      - run:
+          name: black
+          command: |
+            black --check -l 100 .
+      - run:
+          name: flake8
+          command: |
+            flake8 .
+
+      - <<: *run_unittests
+
+  gpu_tests:
+    <<: *gpu
+
+    working_directory: ~/detectron2
+
+    steps:
+      - checkout
+      - <<: *install_nvidia_driver
+
+      - run:
+          name: Install nvidia-docker
+          working_directory: ~/
+          command: |
+            curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
+            distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
+            curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | \
+            sudo tee /etc/apt/sources.list.d/nvidia-docker.list
+            sudo apt-get update && sudo apt-get install -y nvidia-docker2
+            # reload the docker daemon configuration
+            sudo pkill -SIGHUP dockerd
+
+      - run:
+          name: Launch docker
+          working_directory: ~/detectron2/docker
+          command: |
+            nvidia-docker build -t detectron2:v0 -f Dockerfile-circleci .
+            nvidia-docker run -itd --name d2 detectron2:v0
+            docker exec -it d2 nvidia-smi
+
+      - run:
+          name: Build Detectron2
+          command: |
+            docker exec -it d2 pip install 'git+https://github.com/facebookresearch/fvcore'
+            docker cp ~/detectron2 d2:/detectron2
+            # This will build d2 for the target GPU arch only
+            docker exec -it d2 pip install -e /detectron2
+            docker exec -it d2 python3 -m detectron2.utils.collect_env
+            docker exec -it d2 python3 -c 'import torch; assert(torch.cuda.is_available())'
+
+      - run:
+          name: Run Unit Tests
+          command: |
+            docker exec -e CIRCLECI=true -it d2 python3 -m unittest discover -v -s /detectron2/tests
+
+workflows:
+  version: 2
+  regular_test:
+    jobs:
+      - cpu_tests
+      - gpu_tests
+
+  #nightly_test:
+    #jobs:
+      #- gpu_tests
+    #triggers:
+      #- schedule:
+          #cron: "0 0 * * *"
+          #filters:
+            #branches:
+              #only:
+                #- master

model/SCHP/mhp_extension/detectron2/.clang-format

@@ -0,0 +1,85 @@
+AccessModifierOffset: -1
+AlignAfterOpenBracket: AlwaysBreak
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlinesLeft: true
+AlignOperands:   false
+AlignTrailingComments: false
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: Empty
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: true
+BinPackArguments: false
+BinPackParameters: false
+BraceWrapping:
+  AfterClass:      false
+  AfterControlStatement: false
+  AfterEnum:       false
+  AfterFunction:   false
+  AfterNamespace:  false
+  AfterObjCDeclaration: false
+  AfterStruct:     false
+  AfterUnion:      false
+  BeforeCatch:     false
+  BeforeElse:      false
+  IndentBraces:    false
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Attach
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: false
+ColumnLimit:     80
+CommentPragmas:  '^ IWYU pragma:'
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat:   false
+ForEachMacros:   [ FOR_EACH, FOR_EACH_ENUMERATE, FOR_EACH_KV, FOR_EACH_R, FOR_EACH_RANGE, ]
+IncludeCategories:
+  - Regex:           '^<.*\.h(pp)?>'
+    Priority:        1
+  - Regex:           '^<.*'
+    Priority:        2
+  - Regex:           '.*'
+    Priority:        3
+IndentCaseLabels: true
+IndentWidth:     2
+IndentWrappedFunctionNames: false
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBlockIndentWidth: 2
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: false
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Left
+ReflowComments:  true
+SortIncludes:    true
+SpaceAfterCStyleCast: false
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeParens: ControlStatements
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 1
+SpacesInAngles:  false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard:        Cpp11
+TabWidth:        8
+UseTab:          Never

model/SCHP/mhp_extension/detectron2/.flake8

@@ -0,0 +1,9 @@
+# This is an example .flake8 config, used when developing *Black* itself.
+# Keep in sync with setup.cfg which is used for source packages.
+
+[flake8]
+ignore = W503, E203, E221, C901, C408, E741
+max-line-length = 100
+max-complexity = 18
+select = B,C,E,F,W,T4,B9
+exclude = build,__init__.py

model/SCHP/mhp_extension/detectron2/.github/CODE_OF_CONDUCT.md

@@ -0,0 +1,5 @@
+# Code of Conduct
+
+Facebook has adopted a Code of Conduct that we expect project participants to adhere to.
+Please read the [full text](https://code.fb.com/codeofconduct/)
+so that you can understand what actions will and will not be tolerated.

model/SCHP/mhp_extension/detectron2/.github/CONTRIBUTING.md

@@ -0,0 +1,49 @@
+# Contributing to detectron2
+
+## Issues
+We use GitHub issues to track public bugs and questions.
+Please make sure to follow one of the
+[issue templates](https://github.com/facebookresearch/detectron2/issues/new/choose)
+when reporting any issues.
+
+Facebook has a [bounty program](https://www.facebook.com/whitehat/) for the safe
+disclosure of security bugs. In those cases, please go through the process
+outlined on that page and do not file a public issue.
+
+## Pull Requests
+We actively welcome your pull requests.
+
+However, if you're adding any significant features (e.g. > 50 lines), please
+make sure to have a corresponding issue to discuss your motivation and proposals,
+before sending a PR. We do not always accept new features, and we take the following
+factors into consideration:
+
+1. Whether the same feature can be achieved without modifying detectron2.
+Detectron2 is designed so that you can implement many extensions from the outside, e.g.
+those in [projects](https://github.com/facebookresearch/detectron2/tree/master/projects).
+If some part is not as extensible, you can also bring up the issue to make it more extensible.
+2. Whether the feature is potentially useful to a large audience, or only to a small portion of users.
+3. Whether the proposed solution has a good design / interface.
+4. Whether the proposed solution adds extra mental/practical overhead to users who don't
+   need such feature.
+5. Whether the proposed solution breaks existing APIs.
+
+When sending a PR, please do:
+
+1. If a PR contains multiple orthogonal changes, split it to several PRs.
+2. If you've added code that should be tested, add tests.
+3. For PRs that need experiments (e.g. adding a new model or new methods),
+	 you don't need to update model zoo, but do provide experiment results in the description of the PR.
+4. If APIs are changed, update the documentation.
+5. Make sure your code lints with `./dev/linter.sh`.
+
+
+## Contributor License Agreement ("CLA")
+In order to accept your pull request, we need you to submit a CLA. You only need
+to do this once to work on any of Facebook's open source projects.
+
+Complete your CLA here: <https://code.facebook.com/cla>
+
+## License
+By contributing to detectron2, you agree that your contributions will be licensed
+under the LICENSE file in the root directory of this source tree.

model/SCHP/mhp_extension/detectron2/.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,5 @@
+
+Please select an issue template from
+https://github.com/facebookresearch/detectron2/issues/new/choose .
+
+Otherwise your issue will be closed.

model/SCHP/mhp_extension/detectron2/.github/ISSUE_TEMPLATE/bugs.md

@@ -0,0 +1,36 @@
+---
+name: "🐛 Bugs"
+about: Report bugs in detectron2
+title: Please read & provide the following
+
+---
+
+## Instructions To Reproduce the 🐛 Bug:
+
+1. what changes you made (`git diff`) or what code you wrote
+```
+<put diff or code here>
+```
+2. what exact command you run:
+3. what you observed (including __full logs__):
+```
+<put logs here>
+```
+4. please simplify the steps as much as possible so they do not require additional resources to
+	 run, such as a private dataset.
+
+## Expected behavior:
+
+If there are no obvious error in "what you observed" provided above,
+please tell us the expected behavior.
+
+## Environment:
+
+Provide your environment information using the following command:
+```
+wget -nc -q https://github.com/facebookresearch/detectron2/raw/master/detectron2/utils/collect_env.py && python collect_env.py
+```
+
+If your issue looks like an installation issue / environment issue,
+please first try to solve it yourself with the instructions in
+https://detectron2.readthedocs.io/tutorials/install.html#common-installation-issues

model/SCHP/mhp_extension/detectron2/.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,9 @@
+# require an issue template to be chosen
+blank_issues_enabled: false
+
+# Unexpected behaviors & bugs are split to two templates.
+# When they are one template, users think "it's not a bug" and don't choose the template.
+#
+# But the file name is still "unexpected-problems-bugs.md" so that old references
+# to this issue template still works.
+# It's ok since this template should be a superset of "bugs.md" (unexpected behaviors is a superset of bugs)

model/SCHP/mhp_extension/detectron2/.github/ISSUE_TEMPLATE/feature-request.md

@@ -0,0 +1,31 @@
+---
+name: "\U0001F680Feature Request"
+about: Submit a proposal/request for a new detectron2 feature
+
+---
+
+## 🚀 Feature
+A clear and concise description of the feature proposal.
+
+
+## Motivation & Examples
+
+Tell us why the feature is useful.
+
+Describe what the feature would look like, if it is implemented.
+Best demonstrated using **code examples** in addition to words.
+
+## Note
+
+We only consider adding new features if they are relevant to many users.
+
+If you request implementation of research papers --
+we only consider papers that have enough significance and prevalance in the object detection field.
+
+We do not take requests for most projects in the `projects/` directory,
+because they are research code release that is mainly for other researchers to reproduce results.
+
+Instead of adding features inside detectron2,
+you can implement many features by [extending detectron2](https://detectron2.readthedocs.io/tutorials/extend.html).
+The [projects/](https://github.com/facebookresearch/detectron2/tree/master/projects/) directory contains many of such examples.
+

model/SCHP/mhp_extension/detectron2/.github/ISSUE_TEMPLATE/questions-help-support.md

@@ -0,0 +1,26 @@
+---
+name: "❓How to do something?"
+about: How to do something using detectron2? What does an API do?
+
+---
+
+## ❓ How to do something using detectron2
+
+Describe what you want to do, including:
+1. what inputs you will provide, if any:
+2. what outputs you are expecting:
+
+## ❓ What does an API do and how to use it?
+Please link to which API or documentation you're asking about from
+https://detectron2.readthedocs.io/
+
+
+NOTE:
+
+1. Only general answers are provided.
+   If you want to ask about "why X did not work", please use the
+   [Unexpected behaviors](https://github.com/facebookresearch/detectron2/issues/new/choose) issue template.
+
+2. About how to implement new models / new dataloader / new training logic, etc., check documentation first.
+
+3. We do not answer general machine learning / computer vision questions that are not specific to detectron2, such as how a model works, how to improve your training/make it converge, or what algorithm/methods can be used to achieve X.

model/SCHP/mhp_extension/detectron2/.github/ISSUE_TEMPLATE/unexpected-problems-bugs.md

@@ -0,0 +1,45 @@
+---
+name: "Unexpected behaviors"
+about: Run into unexpected behaviors when using detectron2
+title: Please read & provide the following
+
+---
+
+If you do not know the root cause of the problem, and wish someone to help you, please
+post according to this template:
+
+## Instructions To Reproduce the Issue:
+
+1. what changes you made (`git diff`) or what code you wrote
+```
+<put diff or code here>
+```
+2. what exact command you run:
+3. what you observed (including __full logs__):
+```
+<put logs here>
+```
+4. please simplify the steps as much as possible so they do not require additional resources to
+	 run, such as a private dataset.
+
+## Expected behavior:
+
+If there are no obvious error in "what you observed" provided above,
+please tell us the expected behavior.
+
+If you expect the model to converge / work better, note that we do not give suggestions
+on how to train a new model.
+Only in one of the two conditions we will help with it:
+(1) You're unable to reproduce the results in detectron2 model zoo.
+(2) It indicates a detectron2 bug.
+
+## Environment:
+
+Provide your environment information using the following command:
+```
+wget -nc -q https://github.com/facebookresearch/detectron2/raw/master/detectron2/utils/collect_env.py && python collect_env.py
+```
+
+If your issue looks like an installation issue / environment issue,
+please first try to solve it yourself with the instructions in
+https://detectron2.readthedocs.io/tutorials/install.html#common-installation-issues

model/SCHP/mhp_extension/detectron2/.github/pull_request_template.md

@@ -0,0 +1,9 @@
+Thanks for your contribution!
+
+If you're sending a large PR (e.g., >50 lines),
+please open an issue first about the feature / bug, and indicate how you want to contribute.
+
+Before submitting a PR, please run `dev/linter.sh` to lint the code.
+
+See https://detectron2.readthedocs.io/notes/contributing.html#pull-requests
+about how we handle PRs.

model/SCHP/mhp_extension/detectron2/.gitignore

@@ -0,0 +1,46 @@
+# output dir
+output
+instant_test_output
+inference_test_output
+
+
+*.jpg
+*.png
+*.txt
+*.json
+*.diff
+
+# compilation and distribution
+__pycache__
+_ext
+*.pyc
+*.so
+detectron2.egg-info/
+build/
+dist/
+wheels/
+
+# pytorch/python/numpy formats
+*.pth
+*.pkl
+*.npy
+
+# ipython/jupyter notebooks
+*.ipynb
+**/.ipynb_checkpoints/
+
+# Editor temporaries
+*.swn
+*.swo
+*.swp
+*~
+
+# editor settings
+.idea
+.vscode
+
+# project dirs
+/detectron2/model_zoo/configs
+/datasets
+/projects/*/datasets
+/models

model/SCHP/mhp_extension/detectron2/GETTING_STARTED.md

@@ -0,0 +1,79 @@
+## Getting Started with Detectron2
+
+This document provides a brief intro of the usage of builtin command-line tools in detectron2.
+
+For a tutorial that involves actual coding with the API,
+see our [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
+which covers how to run inference with an
+existing model, and how to train a builtin model on a custom dataset.
+
+For more advanced tutorials, refer to our [documentation](https://detectron2.readthedocs.io/tutorials/extend.html).
+
+
+### Inference Demo with Pre-trained Models
+
+1. Pick a model and its config file from
+	[model zoo](MODEL_ZOO.md),
+	for example, `mask_rcnn_R_50_FPN_3x.yaml`.
+2. We provide `demo.py` that is able to run builtin standard models. Run it with:
+```
+cd demo/
+python demo.py --config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml \
+  --input input1.jpg input2.jpg \
+  [--other-options]
+  --opts MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl
+```
+The configs are made for training, therefore we need to specify `MODEL.WEIGHTS` to a model from model zoo for evaluation.
+This command will run the inference and show visualizations in an OpenCV window.
+
+For details of the command line arguments, see `demo.py -h` or look at its source code
+to understand its behavior. Some common arguments are:
+* To run __on your webcam__, replace `--input files` with `--webcam`.
+* To run __on a video__, replace `--input files` with `--video-input video.mp4`.
+* To run __on cpu__, add `MODEL.DEVICE cpu` after `--opts`.
+* To save outputs to a directory (for images) or a file (for webcam or video), use `--output`.
+
+
+### Training & Evaluation in Command Line
+
+We provide a script in "tools/{,plain_}train_net.py", that is made to train
+all the configs provided in detectron2.
+You may want to use it as a reference to write your own training script.
+
+To train a model with "train_net.py", first
+setup the corresponding datasets following
+[datasets/README.md](./datasets/README.md),
+then run:
+```
+cd tools/
+./train_net.py --num-gpus 8 \
+	--config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml
+```
+
+The configs are made for 8-GPU training.
+To train on 1 GPU, you may need to [change some parameters](https://arxiv.org/abs/1706.02677), e.g.:
+```
+./train_net.py \
+	--config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml \
+	--num-gpus 1 SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025
+```
+
+For most models, CPU training is not supported.
+
+To evaluate a model's performance, use
+```
+./train_net.py \
+	--config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml \
+	--eval-only MODEL.WEIGHTS /path/to/checkpoint_file
+```
+For more options, see `./train_net.py -h`.
+
+### Use Detectron2 APIs in Your Code
+
+See our [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
+to learn how to use detectron2 APIs to:
+1. run inference with an existing model
+2. train a builtin model on a custom dataset
+
+See [detectron2/projects](https://github.com/facebookresearch/detectron2/tree/master/projects)
+for more ways to build your project on detectron2.

model/SCHP/mhp_extension/detectron2/INSTALL.md

@@ -0,0 +1,184 @@
+## Installation
+
+Our [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
+has step-by-step instructions that install detectron2.
+The [Dockerfile](docker)
+also installs detectron2 with a few simple commands.
+
+### Requirements
+- Linux or macOS with Python ≥ 3.6
+- PyTorch ≥ 1.4
+- [torchvision](https://github.com/pytorch/vision/) that matches the PyTorch installation.
+	You can install them together at [pytorch.org](https://pytorch.org) to make sure of this.
+- OpenCV, optional, needed by demo and visualization
+- pycocotools: `pip install cython; pip install -U 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'`
+
+
+### Build Detectron2 from Source
+
+gcc & g++ ≥ 5 are required. [ninja](https://ninja-build.org/) is recommended for faster build.
+After having them, run:
+```
+python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
+# (add --user if you don't have permission)
+
+# Or, to install it from a local clone:
+git clone https://github.com/facebookresearch/detectron2.git
+python -m pip install -e detectron2
+
+# Or if you are on macOS
+# CC=clang CXX=clang++ python -m pip install -e .
+```
+
+To __rebuild__ detectron2 that's built from a local clone, use `rm -rf build/ **/*.so` to clean the
+old build first. You often need to rebuild detectron2 after reinstalling PyTorch.
+
+### Install Pre-Built Detectron2 (Linux only)
+```
+# for CUDA 10.1:
+python -m pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/index.html
+```
+You can replace cu101 with "cu{100,92}" or "cpu".
+
+Note that:
+1. Such installation has to be used with certain version of official PyTorch release.
+   See [releases](https://github.com/facebookresearch/detectron2/releases) for requirements.
+   It will not work with a different version of PyTorch or a non-official build of PyTorch.
+2. Such installation is out-of-date w.r.t. master branch of detectron2. It may not be
+	 compatible with the master branch of a research project that uses detectron2 (e.g. those in
+	 [projects](projects) or [meshrcnn](https://github.com/facebookresearch/meshrcnn/)).
+
+### Common Installation Issues
+
+If you met issues using the pre-built detectron2, please uninstall it and try building it from source.
+
+Click each issue for its solutions:
+
+<details>
+<summary>
+Undefined torch/aten/caffe2 symbols, or segmentation fault immediately when running the library.
+</summary>
+<br/>
+
+This usually happens when detectron2 or torchvision is not
+compiled with the version of PyTorch you're running.
+
+Pre-built torchvision or detectron2 has to work with the corresponding official release of pytorch.
+If the error comes from a pre-built torchvision, uninstall torchvision and pytorch and reinstall them
+following [pytorch.org](http://pytorch.org). So the versions will match.
+
+If the error comes from a pre-built detectron2, check [release notes](https://github.com/facebookresearch/detectron2/releases)
+to see the corresponding pytorch version required for each pre-built detectron2.
+
+If the error comes from detectron2 or torchvision that you built manually from source,
+remove files you built (`build/`, `**/*.so`) and rebuild it so it can pick up the version of pytorch currently in your environment.
+
+If you cannot resolve this problem, please include the output of `gdb -ex "r" -ex "bt" -ex "quit" --args python -m detectron2.utils.collect_env`
+in your issue.
+</details>
+
+<details>
+<summary>
+Undefined C++ symbols (e.g. `GLIBCXX`) or C++ symbols not found.
+</summary>
+<br/>
+Usually it's because the library is compiled with a newer C++ compiler but run with an old C++ runtime.
+
+This often happens with old anaconda.
+Try `conda update libgcc`. Then rebuild detectron2.
+
+The fundamental solution is to run the code with proper C++ runtime.
+One way is to use `LD_PRELOAD=/path/to/libstdc++.so`.
+
+</details>
+
+<details>
+<summary>
+"Not compiled with GPU support" or "Detectron2 CUDA Compiler: not available".
+</summary>
+<br/>
+CUDA is not found when building detectron2.
+You should make sure
+
+```
+python -c 'import torch; from torch.utils.cpp_extension import CUDA_HOME; print(torch.cuda.is_available(), CUDA_HOME)'
+```
+
+print valid outputs at the time you build detectron2.
+
+Most models can run inference (but not training) without GPU support. To use CPUs, set `MODEL.DEVICE='cpu'` in the config.
+</details>
+
+<details>
+<summary>
+"invalid device function" or "no kernel image is available for execution".
+</summary>
+<br/>
+Two possibilities:
+
+* You build detectron2 with one version of CUDA but run it with a different version.
+
+  To check whether it is the case,
+  use `python -m detectron2.utils.collect_env` to find out inconsistent CUDA versions.
+	In the output of this command, you should expect "Detectron2 CUDA Compiler", "CUDA_HOME", "PyTorch built with - CUDA"
+	to contain cuda libraries of the same version.
+
+	When they are inconsistent,
+	you need to either install a different build of PyTorch (or build by yourself)
+	to match your local CUDA installation, or install a different version of CUDA to match PyTorch.
+
+* Detectron2 or PyTorch/torchvision is not built for the correct GPU architecture (compute compatibility).
+
+	The GPU architecture for PyTorch/detectron2/torchvision is available in the "architecture flags" in
+	`python -m detectron2.utils.collect_env`.
+
+	The GPU architecture flags of detectron2/torchvision by default matches the GPU model detected
+	during compilation. This means the compiled code may not work on a different GPU model.
+	To overwrite the GPU architecture for detectron2/torchvision, use `TORCH_CUDA_ARCH_LIST` environment variable during compilation.
+
+	For example, `export TORCH_CUDA_ARCH_LIST=6.0,7.0` makes it compile for both P100s and V100s.
+	Visit [developer.nvidia.com/cuda-gpus](https://developer.nvidia.com/cuda-gpus) to find out
+	the correct compute compatibility number for your device.
+
+</details>
+
+<details>
+<summary>
+Undefined CUDA symbols; cannot open libcudart.so; other nvcc failures.
+</summary>
+<br/>
+The version of NVCC you use to build detectron2 or torchvision does
+not match the version of CUDA you are running with.
+This often happens when using anaconda's CUDA runtime.
+
+Use `python -m detectron2.utils.collect_env` to find out inconsistent CUDA versions.
+In the output of this command, you should expect "Detectron2 CUDA Compiler", "CUDA_HOME", "PyTorch built with - CUDA"
+to contain cuda libraries of the same version.
+
+When they are inconsistent,
+you need to either install a different build of PyTorch (or build by yourself)
+to match your local CUDA installation, or install a different version of CUDA to match PyTorch.
+</details>
+
+
+<details>
+<summary>
+"ImportError: cannot import name '_C'".
+</summary>
+<br/>
+Please build and install detectron2 following the instructions above.
+
+If you are running code from detectron2's root directory, `cd` to a different one.
+Otherwise you may not import the code that you installed.
+</details>
+
+<details>
+<summary>
+ONNX conversion segfault after some "TraceWarning".
+</summary>
+<br/>
+The ONNX package is compiled with too old compiler.
+
+Please build and install ONNX from its source code using a compiler
+whose version is closer to what's used by PyTorch (available in `torch.__config__.show()`).
+</details>

model/SCHP/mhp_extension/detectron2/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 2019 - present, Facebook, Inc
+
+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.

model/SCHP/mhp_extension/detectron2/MODEL_ZOO.md

@@ -0,0 +1,903 @@
+# Detectron2 Model Zoo and Baselines
+
+## Introduction
+
+This file documents a large collection of baselines trained
+with detectron2 in Sep-Oct, 2019.
+All numbers were obtained on [Big Basin](https://engineering.fb.com/data-center-engineering/introducing-big-basin-our-next-generation-ai-hardware/)
+servers with 8 NVIDIA V100 GPUs & NVLink. The software in use were PyTorch 1.3, CUDA 9.2, cuDNN 7.4.2 or 7.6.3.
+You can access these models from code using [detectron2.model_zoo](https://detectron2.readthedocs.io/modules/model_zoo.html) APIs.
+
+In addition to these official baseline models, you can find more models in [projects/](projects/).
+
+#### How to Read the Tables
+* The "Name" column contains a link to the config file. Running `tools/train_net.py` with this config file
+	and 8 GPUs will reproduce the model.
+* Training speed is averaged across the entire training.
+	We keep updating the speed with latest version of detectron2/pytorch/etc.,
+	so they might be different from the `metrics` file.
+	Training speed for multi-machine jobs is not provided.
+* Inference speed is measured by `tools/train_net.py --eval-only`, or [inference_on_dataset()](https://detectron2.readthedocs.io/modules/evaluation.html#detectron2.evaluation.inference_on_dataset),
+  with batch size 1 in detectron2 directly.
+	Measuring it with your own code will likely introduce other overhead.
+  Actual deployment in production should in general be faster than the given inference
+  speed due to more optimizations.
+* The *model id* column is provided for ease of reference.
+  To check downloaded file integrity, any model on this page contains its md5 prefix in its file name.
+* Training curves and other statistics can be found in `metrics` for each model.
+
+#### Common Settings for COCO Models
+* All COCO models were trained on `train2017` and evaluated on `val2017`.
+* The default settings are __not directly comparable__ with Detectron's standard settings.
+  For example, our default training data augmentation uses scale jittering in addition to horizontal flipping.
+
+  To make fair comparisons with Detectron's settings, see
+  [Detectron1-Comparisons](configs/Detectron1-Comparisons/) for accuracy comparison,
+  and [benchmarks](https://detectron2.readthedocs.io/notes/benchmarks.html)
+  for speed comparison.
+* For Faster/Mask R-CNN, we provide baselines based on __3 different backbone combinations__:
+  * __FPN__: Use a ResNet+FPN backbone with standard conv and FC heads for mask and box prediction,
+    respectively. It obtains the best
+    speed/accuracy tradeoff, but the other two are still useful for research.
+  * __C4__: Use a ResNet conv4 backbone with conv5 head. The original baseline in the Faster R-CNN paper.
+  * __DC5__ (Dilated-C5): Use a ResNet conv5 backbone with dilations in conv5, and standard conv and FC heads
+    for mask and box prediction, respectively.
+    This is used by the Deformable ConvNet paper.
+* Most models are trained with the 3x schedule (~37 COCO epochs).
+  Although 1x models are heavily under-trained, we provide some ResNet-50 models with the 1x (~12 COCO epochs)
+  training schedule for comparison when doing quick research iteration.
+
+#### ImageNet Pretrained Models
+
+We provide backbone models pretrained on ImageNet-1k dataset.
+These models have __different__ format from those provided in Detectron: we do not fuse BatchNorm into an affine layer.
+* [R-50.pkl](https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-50.pkl): converted copy of [MSRA's original ResNet-50](https://github.com/KaimingHe/deep-residual-networks) model.
+* [R-101.pkl](https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/MSRA/R-101.pkl): converted copy of [MSRA's original ResNet-101](https://github.com/KaimingHe/deep-residual-networks) model.
+* [X-101-32x8d.pkl](https://dl.fbaipublicfiles.com/detectron2/ImageNetPretrained/FAIR/X-101-32x8d.pkl): ResNeXt-101-32x8d model trained with Caffe2 at FB.
+
+Pretrained models in Detectron's format can still be used. For example:
+* [X-152-32x8d-IN5k.pkl](https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/25093814/X-152-32x8d-IN5k.pkl):
+  ResNeXt-152-32x8d model trained on ImageNet-5k with Caffe2 at FB (see ResNeXt paper for details on ImageNet-5k).
+* [R-50-GN.pkl](https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47261647/R-50-GN.pkl):
+  ResNet-50 with Group Normalization.
+* [R-101-GN.pkl](https://dl.fbaipublicfiles.com/detectron/ImageNetPretrained/47592356/R-101-GN.pkl):
+  ResNet-101 with Group Normalization.
+
+Torchvision's ResNet models can be used after converted by [this script](tools/convert-torchvision-to-d2.py).
+
+#### License
+
+All models available for download through this document are licensed under the
+[Creative Commons Attribution-ShareAlike 3.0 license](https://creativecommons.org/licenses/by-sa/3.0/).
+
+### COCO Object Detection Baselines
+
+#### Faster R-CNN:
+<!--
+(fb only) To update the table in vim:
+1. Remove the old table: d}
+2. Copy the below command to the place of the table
+3. :.!bash
+
+./gen_html_table.py --config 'COCO-Detection/faster*50*'{1x,3x}'*' 'COCO-Detection/faster*101*' --name R50-C4 R50-DC5 R50-FPN R50-C4 R50-DC5 R50-FPN R101-C4 R101-DC5 R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: faster_rcnn_R_50_C4_1x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml">R50-C4</a></td>
+<td align="center">1x</td>
+<td align="center">0.551</td>
+<td align="center">0.102</td>
+<td align="center">4.8</td>
+<td align="center">35.7</td>
+<td align="center">137257644</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_1x/137257644/model_final_721ade.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_1x/137257644/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_50_DC5_1x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_DC5_1x.yaml">R50-DC5</a></td>
+<td align="center">1x</td>
+<td align="center">0.380</td>
+<td align="center">0.068</td>
+<td align="center">5.0</td>
+<td align="center">37.3</td>
+<td align="center">137847829</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_1x/137847829/model_final_51d356.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_1x/137847829/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.210</td>
+<td align="center">0.038</td>
+<td align="center">3.0</td>
+<td align="center">37.9</td>
+<td align="center">137257794</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_1x/137257794/model_final_b275ba.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_1x/137257794/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_50_C4_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_C4_3x.yaml">R50-C4</a></td>
+<td align="center">3x</td>
+<td align="center">0.543</td>
+<td align="center">0.104</td>
+<td align="center">4.8</td>
+<td align="center">38.4</td>
+<td align="center">137849393</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_3x/137849393/model_final_f97cb7.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_C4_3x/137849393/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_50_DC5_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml">R50-DC5</a></td>
+<td align="center">3x</td>
+<td align="center">0.378</td>
+<td align="center">0.070</td>
+<td align="center">5.0</td>
+<td align="center">39.0</td>
+<td align="center">137849425</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_3x/137849425/model_final_68d202.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_DC5_3x/137849425/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_50_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml">R50-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.209</td>
+<td align="center">0.038</td>
+<td align="center">3.0</td>
+<td align="center">40.2</td>
+<td align="center">137849458</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_101_C4_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_101_C4_3x.yaml">R101-C4</a></td>
+<td align="center">3x</td>
+<td align="center">0.619</td>
+<td align="center">0.139</td>
+<td align="center">5.9</td>
+<td align="center">41.1</td>
+<td align="center">138204752</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_C4_3x/138204752/model_final_298dad.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_C4_3x/138204752/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_101_DC5_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml">R101-DC5</a></td>
+<td align="center">3x</td>
+<td align="center">0.452</td>
+<td align="center">0.086</td>
+<td align="center">6.1</td>
+<td align="center">40.6</td>
+<td align="center">138204841</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_DC5_3x/138204841/model_final_3e0943.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_DC5_3x/138204841/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_101_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml">R101-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.286</td>
+<td align="center">0.051</td>
+<td align="center">4.1</td>
+<td align="center">42.0</td>
+<td align="center">137851257</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_FPN_3x/137851257/model_final_f6e8b1.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_101_FPN_3x/137851257/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_X_101_32x8d_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml">X101-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.638</td>
+<td align="center">0.098</td>
+<td align="center">6.7</td>
+<td align="center">43.0</td>
+<td align="center">139173657</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x/139173657/model_final_68b088.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x/139173657/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+#### RetinaNet:
+<!--
+./gen_html_table.py --config 'COCO-Detection/retina*50*' 'COCO-Detection/retina*101*' --name R50 R50 R101 --fields lr_sched train_speed inference_speed mem box_AP
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: retinanet_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml">R50</a></td>
+<td align="center">1x</td>
+<td align="center">0.200</td>
+<td align="center">0.055</td>
+<td align="center">3.9</td>
+<td align="center">36.5</td>
+<td align="center">137593951</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_1x/137593951/model_final_b796dc.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_1x/137593951/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: retinanet_R_50_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml">R50</a></td>
+<td align="center">3x</td>
+<td align="center">0.201</td>
+<td align="center">0.055</td>
+<td align="center">3.9</td>
+<td align="center">37.9</td>
+<td align="center">137849486</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_3x/137849486/model_final_4cafe0.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_50_FPN_3x/137849486/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: retinanet_R_101_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/retinanet_R_101_FPN_3x.yaml">R101</a></td>
+<td align="center">3x</td>
+<td align="center">0.280</td>
+<td align="center">0.068</td>
+<td align="center">5.1</td>
+<td align="center">39.9</td>
+<td align="center">138363263</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_101_FPN_3x/138363263/model_final_59f53c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/retinanet_R_101_FPN_3x/138363263/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+#### RPN & Fast R-CNN:
+<!--
+./gen_html_table.py --config 'COCO-Detection/rpn*' 'COCO-Detection/fast_rcnn*' --name "RPN R50-C4" "RPN R50-FPN" "Fast R-CNN R50-FPN" --fields lr_sched train_speed inference_speed mem box_AP prop_AR
+-->
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">prop.<br/>AR</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: rpn_R_50_C4_1x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/rpn_R_50_C4_1x.yaml">RPN R50-C4</a></td>
+<td align="center">1x</td>
+<td align="center">0.130</td>
+<td align="center">0.034</td>
+<td align="center">1.5</td>
+<td align="center"></td>
+<td align="center">51.6</td>
+<td align="center">137258005</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_C4_1x/137258005/model_final_450694.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_C4_1x/137258005/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: rpn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/rpn_R_50_FPN_1x.yaml">RPN R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.186</td>
+<td align="center">0.032</td>
+<td align="center">2.7</td>
+<td align="center"></td>
+<td align="center">58.0</td>
+<td align="center">137258492</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_FPN_1x/137258492/model_final_02ce48.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/rpn_R_50_FPN_1x/137258492/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: fast_rcnn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml">Fast R-CNN R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.140</td>
+<td align="center">0.029</td>
+<td align="center">2.6</td>
+<td align="center">37.8</td>
+<td align="center"></td>
+<td align="center">137635226</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/model_final_e5f7ce.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+### COCO Instance Segmentation Baselines with Mask R-CNN
+<!--
+./gen_html_table.py --config 'COCO-InstanceSegmentation/mask*50*'{1x,3x}'*' 'COCO-InstanceSegmentation/mask*101*' --name R50-C4 R50-DC5 R50-FPN R50-C4 R50-DC5 R50-FPN R101-C4 R101-DC5 R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP mask_AP
+-->
+
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">mask<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: mask_rcnn_R_50_C4_1x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml">R50-C4</a></td>
+<td align="center">1x</td>
+<td align="center">0.584</td>
+<td align="center">0.110</td>
+<td align="center">5.2</td>
+<td align="center">36.8</td>
+<td align="center">32.2</td>
+<td align="center">137259246</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x/137259246/model_final_9243eb.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x/137259246/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_DC5_1x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml">R50-DC5</a></td>
+<td align="center">1x</td>
+<td align="center">0.471</td>
+<td align="center">0.076</td>
+<td align="center">6.5</td>
+<td align="center">38.3</td>
+<td align="center">34.2</td>
+<td align="center">137260150</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x/137260150/model_final_4f86c3.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x/137260150/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.261</td>
+<td align="center">0.043</td>
+<td align="center">3.4</td>
+<td align="center">38.6</td>
+<td align="center">35.2</td>
+<td align="center">137260431</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/model_final_a54504.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_C4_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml">R50-C4</a></td>
+<td align="center">3x</td>
+<td align="center">0.575</td>
+<td align="center">0.111</td>
+<td align="center">5.2</td>
+<td align="center">39.8</td>
+<td align="center">34.4</td>
+<td align="center">137849525</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x/137849525/model_final_4ce675.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x/137849525/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_DC5_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml">R50-DC5</a></td>
+<td align="center">3x</td>
+<td align="center">0.470</td>
+<td align="center">0.076</td>
+<td align="center">6.5</td>
+<td align="center">40.0</td>
+<td align="center">35.9</td>
+<td align="center">137849551</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x/137849551/model_final_84107b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x/137849551/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml">R50-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.261</td>
+<td align="center">0.043</td>
+<td align="center">3.4</td>
+<td align="center">41.0</td>
+<td align="center">37.2</td>
+<td align="center">137849600</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_101_C4_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml">R101-C4</a></td>
+<td align="center">3x</td>
+<td align="center">0.652</td>
+<td align="center">0.145</td>
+<td align="center">6.3</td>
+<td align="center">42.6</td>
+<td align="center">36.7</td>
+<td align="center">138363239</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x/138363239/model_final_a2914c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x/138363239/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_101_DC5_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml">R101-DC5</a></td>
+<td align="center">3x</td>
+<td align="center">0.545</td>
+<td align="center">0.092</td>
+<td align="center">7.6</td>
+<td align="center">41.9</td>
+<td align="center">37.3</td>
+<td align="center">138363294</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x/138363294/model_final_0464b7.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x/138363294/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_101_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml">R101-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.340</td>
+<td align="center">0.056</td>
+<td align="center">4.6</td>
+<td align="center">42.9</td>
+<td align="center">38.6</td>
+<td align="center">138205316</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x/138205316/model_final_a3ec72.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x/138205316/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_X_101_32x8d_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml">X101-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.690</td>
+<td align="center">0.103</td>
+<td align="center">7.2</td>
+<td align="center">44.3</td>
+<td align="center">39.5</td>
+<td align="center">139653917</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x/139653917/model_final_2d9806.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x/139653917/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+### COCO Person Keypoint Detection Baselines with Keypoint R-CNN
+<!--
+./gen_html_table.py --config 'COCO-Keypoints/*50*' 'COCO-Keypoints/*101*'  --name R50-FPN R50-FPN R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP keypoint_AP
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">kp.<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: keypoint_rcnn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.315</td>
+<td align="center">0.072</td>
+<td align="center">5.0</td>
+<td align="center">53.6</td>
+<td align="center">64.0</td>
+<td align="center">137261548</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x/137261548/model_final_04e291.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x/137261548/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: keypoint_rcnn_R_50_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml">R50-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.316</td>
+<td align="center">0.066</td>
+<td align="center">5.0</td>
+<td align="center">55.4</td>
+<td align="center">65.5</td>
+<td align="center">137849621</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x/137849621/model_final_a6e10b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x/137849621/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: keypoint_rcnn_R_101_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x.yaml">R101-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.390</td>
+<td align="center">0.076</td>
+<td align="center">6.1</td>
+<td align="center">56.4</td>
+<td align="center">66.1</td>
+<td align="center">138363331</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x/138363331/model_final_997cc7.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x/138363331/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: keypoint_rcnn_X_101_32x8d_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x.yaml">X101-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.738</td>
+<td align="center">0.121</td>
+<td align="center">8.7</td>
+<td align="center">57.3</td>
+<td align="center">66.0</td>
+<td align="center">139686956</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x/139686956/model_final_5ad38f.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x/139686956/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+### COCO Panoptic Segmentation Baselines with Panoptic FPN
+<!--
+./gen_html_table.py --config 'COCO-PanopticSegmentation/*50*' 'COCO-PanopticSegmentation/*101*'  --name R50-FPN R50-FPN R101-FPN --fields lr_sched train_speed inference_speed mem box_AP mask_AP PQ
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">mask<br/>AP</th>
+<th valign="bottom">PQ</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: panoptic_fpn_R_50_1x -->
+ <tr><td align="left"><a href="configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml">R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.304</td>
+<td align="center">0.053</td>
+<td align="center">4.8</td>
+<td align="center">37.6</td>
+<td align="center">34.7</td>
+<td align="center">39.4</td>
+<td align="center">139514544</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x/139514544/model_final_dbfeb4.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x/139514544/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: panoptic_fpn_R_50_3x -->
+ <tr><td align="left"><a href="configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml">R50-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.302</td>
+<td align="center">0.053</td>
+<td align="center">4.8</td>
+<td align="center">40.0</td>
+<td align="center">36.5</td>
+<td align="center">41.5</td>
+<td align="center">139514569</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x/139514569/model_final_c10459.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x/139514569/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: panoptic_fpn_R_101_3x -->
+ <tr><td align="left"><a href="configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml">R101-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.392</td>
+<td align="center">0.066</td>
+<td align="center">6.0</td>
+<td align="center">42.4</td>
+<td align="center">38.5</td>
+<td align="center">43.0</td>
+<td align="center">139514519</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x/139514519/model_final_cafdb1.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x/139514519/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+
+### LVIS Instance Segmentation Baselines with Mask R-CNN
+
+Mask R-CNN baselines on the [LVIS dataset](https://lvisdataset.org), v0.5.
+These baselines are described in Table 3(c) of the [LVIS paper](https://arxiv.org/abs/1908.03195).
+
+NOTE: the 1x schedule here has the same amount of __iterations__ as the COCO 1x baselines.
+They are roughly 24 epochs of LVISv0.5 data.
+The final results of these configs have large variance across different runs.
+
+<!--
+./gen_html_table.py --config 'LVIS-InstanceSegmentation/mask*50*' 'LVIS-InstanceSegmentation/mask*101*' --name R50-FPN R101-FPN X101-FPN --fields lr_sched train_speed inference_speed mem box_AP mask_AP
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">mask<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: mask_rcnn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml">R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.292</td>
+<td align="center">0.107</td>
+<td align="center">7.1</td>
+<td align="center">23.6</td>
+<td align="center">24.4</td>
+<td align="center">144219072</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/144219072/model_final_571f7c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/144219072/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_101_FPN_1x -->
+ <tr><td align="left"><a href="configs/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x.yaml">R101-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.371</td>
+<td align="center">0.114</td>
+<td align="center">7.8</td>
+<td align="center">25.6</td>
+<td align="center">25.9</td>
+<td align="center">144219035</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x/144219035/model_final_824ab5.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x/144219035/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_X_101_32x8d_FPN_1x -->
+ <tr><td align="left"><a href="configs/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x.yaml">X101-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.712</td>
+<td align="center">0.151</td>
+<td align="center">10.2</td>
+<td align="center">26.7</td>
+<td align="center">27.1</td>
+<td align="center">144219108</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x/144219108/model_final_5e3439.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x/144219108/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+
+
+### Cityscapes & Pascal VOC Baselines
+
+Simple baselines for
+* Mask R-CNN on Cityscapes instance segmentation (initialized from COCO pre-training, then trained on Cityscapes fine annotations only)
+* Faster R-CNN on PASCAL VOC object detection (trained on VOC 2007 train+val + VOC 2012 train+val, tested on VOC 2007 using 11-point interpolated AP)
+
+<!--
+./gen_html_table.py --config 'Cityscapes/*' 'PascalVOC-Detection/*' --name "R50-FPN, Cityscapes" "R50-C4, VOC" --fields train_speed inference_speed mem box_AP box_AP50 mask_AP
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">box<br/>AP50</th>
+<th valign="bottom">mask<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: mask_rcnn_R_50_FPN -->
+ <tr><td align="left"><a href="configs/Cityscapes/mask_rcnn_R_50_FPN.yaml">R50-FPN, Cityscapes</a></td>
+<td align="center">0.240</td>
+<td align="center">0.078</td>
+<td align="center">4.4</td>
+<td align="center"></td>
+<td align="center"></td>
+<td align="center">36.5</td>
+<td align="center">142423278</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Cityscapes/mask_rcnn_R_50_FPN/142423278/model_final_af9cf5.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Cityscapes/mask_rcnn_R_50_FPN/142423278/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: faster_rcnn_R_50_C4 -->
+ <tr><td align="left"><a href="configs/PascalVOC-Detection/faster_rcnn_R_50_C4.yaml">R50-C4, VOC</a></td>
+<td align="center">0.537</td>
+<td align="center">0.081</td>
+<td align="center">4.8</td>
+<td align="center">51.9</td>
+<td align="center">80.3</td>
+<td align="center"></td>
+<td align="center">142202221</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/PascalVOC-Detection/faster_rcnn_R_50_C4/142202221/model_final_b1acc2.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/PascalVOC-Detection/faster_rcnn_R_50_C4/142202221/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+
+
+### Other Settings
+
+Ablations for Deformable Conv and Cascade R-CNN:
+
+<!--
+./gen_html_table.py --config 'COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml' 'Misc/*R_50_FPN_1x_dconv*' 'Misc/cascade*1x.yaml' 'COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml' 'Misc/*R_50_FPN_3x_dconv*' 'Misc/cascade*3x.yaml' --name "Baseline R50-FPN" "Deformable Conv" "Cascade R-CNN" "Baseline R50-FPN" "Deformable Conv" "Cascade R-CNN"  --fields lr_sched train_speed inference_speed mem box_AP mask_AP
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">mask<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: mask_rcnn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml">Baseline R50-FPN</a></td>
+<td align="center">1x</td>
+<td align="center">0.261</td>
+<td align="center">0.043</td>
+<td align="center">3.4</td>
+<td align="center">38.6</td>
+<td align="center">35.2</td>
+<td align="center">137260431</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/model_final_a54504.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x/137260431/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_FPN_1x_dconv_c3-c5 -->
+ <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml">Deformable Conv</a></td>
+<td align="center">1x</td>
+<td align="center">0.342</td>
+<td align="center">0.048</td>
+<td align="center">3.5</td>
+<td align="center">41.5</td>
+<td align="center">37.5</td>
+<td align="center">138602867</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5/138602867/model_final_65c703.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5/138602867/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: cascade_mask_rcnn_R_50_FPN_1x -->
+ <tr><td align="left"><a href="configs/Misc/cascade_mask_rcnn_R_50_FPN_1x.yaml">Cascade R-CNN</a></td>
+<td align="center">1x</td>
+<td align="center">0.317</td>
+<td align="center">0.052</td>
+<td align="center">4.0</td>
+<td align="center">42.1</td>
+<td align="center">36.4</td>
+<td align="center">138602847</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_1x/138602847/model_final_e9d89b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_1x/138602847/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml">Baseline R50-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.261</td>
+<td align="center">0.043</td>
+<td align="center">3.4</td>
+<td align="center">41.0</td>
+<td align="center">37.2</td>
+<td align="center">137849600</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_FPN_3x_dconv_c3-c5 -->
+ <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml">Deformable Conv</a></td>
+<td align="center">3x</td>
+<td align="center">0.349</td>
+<td align="center">0.047</td>
+<td align="center">3.5</td>
+<td align="center">42.7</td>
+<td align="center">38.5</td>
+<td align="center">144998336</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5/144998336/model_final_821d0b.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5/144998336/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: cascade_mask_rcnn_R_50_FPN_3x -->
+ <tr><td align="left"><a href="configs/Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml">Cascade R-CNN</a></td>
+<td align="center">3x</td>
+<td align="center">0.328</td>
+<td align="center">0.053</td>
+<td align="center">4.0</td>
+<td align="center">44.3</td>
+<td align="center">38.5</td>
+<td align="center">144998488</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+
+Ablations for normalization methods, and a few models trained from scratch following [Rethinking ImageNet Pre-training](https://arxiv.org/abs/1811.08883).
+(Note: The baseline uses `2fc` head while the others use [`4conv1fc` head](https://arxiv.org/abs/1803.08494))
+<!--
+./gen_html_table.py --config 'COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml' 'Misc/mask*50_FPN_3x_gn.yaml' 'Misc/mask*50_FPN_3x_syncbn.yaml' 'Misc/scratch*' --name "Baseline R50-FPN" "GN" "SyncBN" "GN (from scratch)" "GN (from scratch)" "SyncBN (from scratch)" --fields lr_sched train_speed inference_speed mem box_AP mask_AP
+   -->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">lr<br/>sched</th>
+<th valign="bottom">train<br/>time<br/>(s/iter)</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">mask<br/>AP</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: mask_rcnn_R_50_FPN_3x -->
+ <tr><td align="left"><a href="configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml">Baseline R50-FPN</a></td>
+<td align="center">3x</td>
+<td align="center">0.261</td>
+<td align="center">0.043</td>
+<td align="center">3.4</td>
+<td align="center">41.0</td>
+<td align="center">37.2</td>
+<td align="center">137849600</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_FPN_3x_gn -->
+ <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_3x_gn.yaml">GN</a></td>
+<td align="center">3x</td>
+<td align="center">0.356</td>
+<td align="center">0.069</td>
+<td align="center">7.3</td>
+<td align="center">42.6</td>
+<td align="center">38.6</td>
+<td align="center">138602888</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_gn/138602888/model_final_dc5d9e.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_gn/138602888/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: mask_rcnn_R_50_FPN_3x_syncbn -->
+ <tr><td align="left"><a href="configs/Misc/mask_rcnn_R_50_FPN_3x_syncbn.yaml">SyncBN</a></td>
+<td align="center">3x</td>
+<td align="center">0.371</td>
+<td align="center">0.053</td>
+<td align="center">5.5</td>
+<td align="center">41.9</td>
+<td align="center">37.8</td>
+<td align="center">169527823</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_syncbn/169527823/model_final_3b3c51.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/mask_rcnn_R_50_FPN_3x_syncbn/169527823/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: scratch_mask_rcnn_R_50_FPN_3x_gn -->
+ <tr><td align="left"><a href="configs/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn.yaml">GN (from scratch)</a></td>
+<td align="center">3x</td>
+<td align="center">0.400</td>
+<td align="center">0.069</td>
+<td align="center">9.8</td>
+<td align="center">39.9</td>
+<td align="center">36.6</td>
+<td align="center">138602908</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn/138602908/model_final_01ca85.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn/138602908/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: scratch_mask_rcnn_R_50_FPN_9x_gn -->
+ <tr><td align="left"><a href="configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_gn.yaml">GN (from scratch)</a></td>
+<td align="center">9x</td>
+<td align="center">N/A</td>
+<td align="center">0.070</td>
+<td align="center">9.8</td>
+<td align="center">43.7</td>
+<td align="center">39.6</td>
+<td align="center">183808979</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_9x_gn/183808979/model_final_da7b4c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_9x_gn/183808979/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: scratch_mask_rcnn_R_50_FPN_9x_syncbn -->
+ <tr><td align="left"><a href="configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_syncbn.yaml">SyncBN (from scratch)</a></td>
+<td align="center">9x</td>
+<td align="center">N/A</td>
+<td align="center">0.055</td>
+<td align="center">7.2</td>
+<td align="center">43.6</td>
+<td align="center">39.3</td>
+<td align="center">184226666</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_9x_syncbn/184226666/model_final_5ce33e.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/scratch_mask_rcnn_R_50_FPN_9x_syncbn/184226666/metrics.json">metrics</a></td>
+</tr>
+</tbody></table>
+
+
+A few very large models trained for a long time, for demo purposes. They are trained using multiple machines:
+
+<!--
+./gen_html_table.py --config 'Misc/panoptic_*dconv*' 'Misc/cascade_*152*' --name "Panoptic FPN R101" "Mask R-CNN X152" --fields inference_speed mem box_AP mask_AP PQ
+# manually add TTA results
+-->
+
+
+<table><tbody>
+<!-- START TABLE -->
+<!-- TABLE HEADER -->
+<th valign="bottom">Name</th>
+<th valign="bottom">inference<br/>time<br/>(s/im)</th>
+<th valign="bottom">train<br/>mem<br/>(GB)</th>
+<th valign="bottom">box<br/>AP</th>
+<th valign="bottom">mask<br/>AP</th>
+<th valign="bottom">PQ</th>
+<th valign="bottom">model id</th>
+<th valign="bottom">download</th>
+<!-- TABLE BODY -->
+<!-- ROW: panoptic_fpn_R_101_dconv_cascade_gn_3x -->
+ <tr><td align="left"><a href="configs/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml">Panoptic FPN R101</a></td>
+<td align="center">0.107</td>
+<td align="center">11.4</td>
+<td align="center">47.4</td>
+<td align="center">41.3</td>
+<td align="center">46.1</td>
+<td align="center">139797668</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x/139797668/model_final_be35db.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x/139797668/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv -->
+ <tr><td align="left"><a href="configs/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml">Mask R-CNN X152</a></td>
+<td align="center">0.242</td>
+<td align="center">15.1</td>
+<td align="center">50.2</td>
+<td align="center">44.0</td>
+<td align="center"></td>
+<td align="center">18131413</td>
+<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv/18131413/model_0039999_e76410.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv/18131413/metrics.json">metrics</a></td>
+</tr>
+<!-- ROW: TTA cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv -->
+ <tr><td align="left">above + test-time aug.</td>
+<td align="center"></td>
+<td align="center"></td>
+<td align="center">51.9</td>
+<td align="center">45.9</td>
+<td align="center"></td>
+<td align="center"></td>
+<td align="center"></td>
+</tr>
+</tbody></table>

model/SCHP/mhp_extension/detectron2/README.md

@@ -0,0 +1,56 @@
+<img src=".github/Detectron2-Logo-Horz.svg" width="300" >
+
+Detectron2 is Facebook AI Research's next generation software system
+that implements state-of-the-art object detection algorithms.
+It is a ground-up rewrite of the previous version,
+[Detectron](https://github.com/facebookresearch/Detectron/),
+and it originates from [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark/).
+
+<div align="center">
+  <img src="https://user-images.githubusercontent.com/1381301/66535560-d3422200-eace-11e9-9123-5535d469db19.png"/>
+</div>
+
+### What's New
+* It is powered by the [PyTorch](https://pytorch.org) deep learning framework.
+* Includes more features such as panoptic segmentation, densepose, Cascade R-CNN, rotated bounding boxes, etc.
+* Can be used as a library to support [different projects](projects/) on top of it.
+  We'll open source more research projects in this way.
+* It [trains much faster](https://detectron2.readthedocs.io/notes/benchmarks.html).
+
+See our [blog post](https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/)
+to see more demos and learn about detectron2.
+
+## Installation
+
+See [INSTALL.md](INSTALL.md).
+
+## Quick Start
+
+See [GETTING_STARTED.md](GETTING_STARTED.md),
+or the [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5).
+
+Learn more at our [documentation](https://detectron2.readthedocs.org).
+And see [projects/](projects/) for some projects that are built on top of detectron2.
+
+## Model Zoo and Baselines
+
+We provide a large set of baseline results and trained models available for download in the [Detectron2 Model Zoo](MODEL_ZOO.md).
+
+
+## License
+
+Detectron2 is released under the [Apache 2.0 license](LICENSE).
+
+## Citing Detectron2
+
+If you use Detectron2 in your research or wish to refer to the baseline results published in the [Model Zoo](MODEL_ZOO.md), please use the following BibTeX entry.
+
+```BibTeX
+@misc{wu2019detectron2,
+  author =       {Yuxin Wu and Alexander Kirillov and Francisco Massa and
+                  Wan-Yen Lo and Ross Girshick},
+  title =        {Detectron2},
+  howpublished = {\url{https://github.com/facebookresearch/detectron2}},
+  year =         {2019}
+}
+```

model/SCHP/mhp_extension/detectron2/configs/Base-RCNN-C4.yaml

@@ -0,0 +1,18 @@
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  RPN:
+    PRE_NMS_TOPK_TEST: 6000
+    POST_NMS_TOPK_TEST: 1000
+  ROI_HEADS:
+    NAME: "Res5ROIHeads"
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  TEST: ("coco_2017_val",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.02
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2