v0.46.1

See https://github.com/quic/ai-hub-models/releases/v0.46.1 for changelog.

DETR-ResNet101-DC5_float.dlc

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:025318cb2f9936af7bb2dd3071085ca66430cf2ae67d6a034875269063eb0d47
-size 243425316

DETR-ResNet101-DC5_float.onnx.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6189fad4f07e8873837b2feb038a228140a15071a26f7940029e7608356da5f
-size 225191617

README.md

@@ -10,234 +10,80 @@ pipeline_tag: object-detection
 
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet101_dc5/web-assets/model_demo.png)
 
-# DETR-ResNet101-DC5: Optimized for Mobile Deployment
-## Transformer based object detector with ResNet101 backbone (dilated C5 stage)
-
+# DETR-ResNet101-DC5: Optimized for Qualcomm Devices
 
 DETR is a machine learning model that can detect objects (trained on COCO dataset).
 
-This model is an implementation of DETR-ResNet101-DC5 found [here](https://github.com/facebookresearch/detr).
-
-
-This repository provides scripts to run DETR-ResNet101-DC5 on Qualcomm® devices.
-More details on model performance across various devices, can be found
-[here](https://aihub.qualcomm.com/models/detr_resnet101_dc5).
-
-
-
-### Model Details
-
-- **Model Type:** Model_use_case.object_detection
-- **Model Stats:**
-  - Model checkpoint: ResNet101-DC5
-  - Input resolution: 480x480
-  - Model size (float): 232 MB
-
-| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
-|---|---|---|---|---|---|---|---|---|
-| DETR-ResNet101-DC5 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 212.262 ms | 5 - 492 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 96.46 ms | 5 - 460 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 50.461 ms | 5 - 7 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 49.348 ms | 0 - 126 MB | NPU | [DETR-ResNet101-DC5.onnx.zip](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.onnx.zip) |
-| DETR-ResNet101-DC5 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 69.209 ms | 0 - 479 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 212.262 ms | 5 - 492 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 77.479 ms | 0 - 330 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 69.209 ms | 0 - 479 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 36.685 ms | 5 - 666 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 36.01 ms | 5 - 546 MB | NPU | [DETR-ResNet101-DC5.onnx.zip](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.onnx.zip) |
-| DETR-ResNet101-DC5 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 27.856 ms | 5 - 504 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 27.752 ms | 2 - 406 MB | NPU | [DETR-ResNet101-DC5.onnx.zip](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.onnx.zip) |
-| DETR-ResNet101-DC5 | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_DLC | 23.357 ms | 5 - 515 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 21.769 ms | 3 - 496 MB | NPU | [DETR-ResNet101-DC5.onnx.zip](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.onnx.zip) |
-| DETR-ResNet101-DC5 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 52.376 ms | 5 - 5 MB | NPU | [DETR-ResNet101-DC5.dlc](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.dlc) |
-| DETR-ResNet101-DC5 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 50.154 ms | 116 - 116 MB | NPU | [DETR-ResNet101-DC5.onnx.zip](https://huggingface.co/qualcomm/DETR-ResNet101-DC5/blob/main/DETR-ResNet101-DC5.onnx.zip) |
-
-
-
-
-## Installation
-
-
-Install the package via pip:
-```bash
-# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
-pip install "qai-hub-models[detr-resnet101-dc5]"
-```
-
-
-## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
-
-Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
-Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
-
-With this API token, you can configure your client to run models on the cloud
-hosted devices.
-```bash
-qai-hub configure --api_token API_TOKEN
-```
-Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
-
-
-
-## Demo off target
-
-The package contains a simple end-to-end demo that downloads pre-trained
-weights and runs this model on a sample input.
-
-```bash
-python -m qai_hub_models.models.detr_resnet101_dc5.demo
-```
-
-The above demo runs a reference implementation of pre-processing, model
-inference, and post processing.
-
-**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
-environment, please add the following to your cell (instead of the above).
-```
-%run -m qai_hub_models.models.detr_resnet101_dc5.demo
-```
-
-
-### Run model on a cloud-hosted device
-
-In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
-device. This script does the following:
-* Performance check on-device on a cloud-hosted device
-* Downloads compiled assets that can be deployed on-device for Android.
-* Accuracy check between PyTorch and on-device outputs.
-
-```bash
-python -m qai_hub_models.models.detr_resnet101_dc5.export
-```
+This is based on the implementation of DETR-ResNet101-DC5 found [here](https://github.com/facebookresearch/detr).
+This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/detr_resnet101_dc5) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
+Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
 
+## Getting Started
+There are two ways to deploy this model on your device:
 
-## How does this work?
+### Option 1: Download Pre-Exported Models
 
-This [export script](https://aihub.qualcomm.com/models/detr_resnet101_dc5/qai_hub_models/models/DETR-ResNet101-DC5/export.py)
-leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
-on-device. Lets go through each step below in detail:
+Below are pre-exported model assets ready for deployment.
 
-Step 1: **Compile model for on-device deployment**
+| Runtime | Precision | Chipset | SDK Versions | Download |
+|---|---|---|---|---|
+| ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet101_dc5/releases/v0.46.1/detr_resnet101_dc5-onnx-float.zip)
+| QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet101_dc5/releases/v0.46.1/detr_resnet101_dc5-qnn_dlc-float.zip)
+| TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/detr_resnet101_dc5/releases/v0.46.1/detr_resnet101_dc5-tflite-float.zip)
 
-To compile a PyTorch model for on-device deployment, we first trace the model
-in memory using the `jit.trace` and then call the `submit_compile_job` API.
+For more device-specific assets and performance metrics, visit **[DETR-ResNet101-DC5 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/detr_resnet101_dc5)**.
 
-```python
-import torch
 
-import qai_hub as hub
-from qai_hub_models.models.detr_resnet101_dc5 import Model
+### Option 2: Export with Custom Configurations
 
-# Load the model
-torch_model = Model.from_pretrained()
+Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/detr_resnet101_dc5) Python library to compile and export the model with your own:
+- Custom weights (e.g., fine-tuned checkpoints)
+- Custom input shapes
+- Target device and runtime configurations
 
-# Device
-device = hub.Device("Samsung Galaxy S25")
+This option is ideal if you need to customize the model beyond the default configuration provided here.
 
-# Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
+See our repository for [DETR-ResNet101-DC5 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/detr_resnet101_dc5) for usage instructions.
 
-pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+## Model Details
 
-# Compile model on a specific device
-compile_job = hub.submit_compile_job(
-    model=pt_model,
-    device=device,
-    input_specs=torch_model.get_input_spec(),
-)
+**Model Type:** Model_use_case.object_detection
 
-# Get target model to run on-device
-target_model = compile_job.get_target_model()
-
-```
-
-
-Step 2: **Performance profiling on cloud-hosted device**
-
-After compiling models from step 1. Models can be profiled model on-device using the
-`target_model`. Note that this scripts runs the model on a device automatically
-provisioned in the cloud.  Once the job is submitted, you can navigate to a
-provided job URL to view a variety of on-device performance metrics.
-```python
-profile_job = hub.submit_profile_job(
-    model=target_model,
-    device=device,
-)
-        
-```
-
-Step 3: **Verify on-device accuracy**
-
-To verify the accuracy of the model on-device, you can run on-device inference
-on sample input data on the same cloud hosted device.
-```python
-input_data = torch_model.sample_inputs()
-inference_job = hub.submit_inference_job(
-    model=target_model,
-    device=device,
-    inputs=input_data,
-)
-    on_device_output = inference_job.download_output_data()
-
-```
-With the output of the model, you can compute like PSNR, relative errors or
-spot check the output with expected output.
-
-**Note**: This on-device profiling and inference requires access to Qualcomm®
-AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
-
-
-
-## Run demo on a cloud-hosted device
-
-You can also run the demo on-device.
-
-```bash
-python -m qai_hub_models.models.detr_resnet101_dc5.demo --eval-mode on-device
-```
-
-**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
-environment, please add the following to your cell (instead of the above).
-```
-%run -m qai_hub_models.models.detr_resnet101_dc5.demo -- --eval-mode on-device
-```
-
-
-## Deploying compiled model to Android
-
-
-The models can be deployed using multiple runtimes:
-- TensorFlow Lite (`.tflite` export): [This
-  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
-  guide to deploy the .tflite model in an Android application.
-
-
-- QNN (`.so` export ): This [sample
-  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
-provides instructions on how to use the `.so` shared library  in an Android application.
-
-
-## View on Qualcomm® AI Hub
-Get more details on DETR-ResNet101-DC5's performance across various devices [here](https://aihub.qualcomm.com/models/detr_resnet101_dc5).
-Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+**Model Stats:**
+- Model checkpoint: ResNet101-DC5
+- Input resolution: 480x480
+- Model size (float): 232 MB
 
+## Performance Summary
+| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
+|---|---|---|---|---|---|---
+| DETR-ResNet101-DC5 | ONNX | float | Snapdragon® X Elite | 50.19 ms | 116 - 116 MB | NPU
+| DETR-ResNet101-DC5 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 36.327 ms | 7 - 634 MB | NPU
+| DETR-ResNet101-DC5 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 49.085 ms | 0 - 126 MB | NPU
+| DETR-ResNet101-DC5 | ONNX | float | Qualcomm® QCS9075 | 71.995 ms | 5 - 12 MB | NPU
+| DETR-ResNet101-DC5 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.503 ms | 2 - 406 MB | NPU
+| DETR-ResNet101-DC5 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 21.467 ms | 1 - 494 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Snapdragon® X Elite | 54.381 ms | 5 - 5 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 39.11 ms | 5 - 719 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 219.013 ms | 2 - 531 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 53.499 ms | 5 - 7 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Qualcomm® SA8775P | 72.159 ms | 2 - 528 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Qualcomm® QCS9075 | 81.376 ms | 5 - 11 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 88.126 ms | 3 - 490 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Qualcomm® SA7255P | 219.013 ms | 2 - 531 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Qualcomm® SA8295P | 76.367 ms | 0 - 338 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 28.632 ms | 5 - 558 MB | NPU
+| DETR-ResNet101-DC5 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 23.02 ms | 5 - 534 MB | NPU
 
 ## License
 * The license for the original implementation of DETR-ResNet101-DC5 can be found
   [here](https://github.com/facebookresearch/detr/blob/main/LICENSE).
 
-
-
 ## References
 * [End-to-End Object Detection with Transformers](https://arxiv.org/abs/2005.12872)
 * [Source Model Implementation](https://github.com/facebookresearch/detr)
 
-
-
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
-
-

tool-versions.yaml

@@ -1,4 +0,0 @@
-tool_versions:
-  onnx:
-    qairt: 2.37.1.250807093845_124904
-    onnx_runtime: 1.23.0