v0.51.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.51.0 for changelog.

Files changed (6) hide show

README.md +100 -224
Swin-Tiny_float.onnx.zip +0 -3
Swin-Tiny_float.tflite +0 -3
Swin-Tiny_w8a16.onnx.zip +0 -3
release_assets.json +46 -0
tool-versions.yaml +0 -4

README.md CHANGED Viewed

@@ -11,242 +11,118 @@ pipeline_tag: image-classification
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/web-assets/model_demo.png)
-# Swin-Tiny: Optimized for Mobile Deployment
-## Imagenet classifier and general purpose backbone
 SwinTiny is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
-This model is an implementation of Swin-Tiny found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py).
-This repository provides scripts to run Swin-Tiny on Qualcomm® devices.
-More details on model performance across various devices, can be found
-[here](https://aihub.qualcomm.com/models/swin_tiny).
-### Model Details
-- **Model Type:** Model_use_case.image_classification
-- **Model Stats:**
-  - Model checkpoint: Imagenet
-  - Input resolution: 224x224
-  - Number of parameters: 28.8M
-  - Model size (float): 110 MB
-  - Model size (w8a16): 29.9 MB
-| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
-|---|---|---|---|---|---|---|---|---|
-| Swin-Tiny | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.049 ms | 0 - 303 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 15.486 ms | 0 - 355 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 10.29 ms | 0 - 4 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.81 ms | 0 - 66 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.onnx.zip) |
-| Swin-Tiny | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 51.611 ms | 0 - 303 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 23.049 ms | 0 - 303 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 14.973 ms | 0 - 296 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 51.611 ms | 0 - 303 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 6.802 ms | 0 - 369 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.749 ms | 1 - 328 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.onnx.zip) |
-| Swin-Tiny | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 5.178 ms | 0 - 297 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.447 ms | 0 - 257 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.onnx.zip) |
-| Swin-Tiny | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | TFLITE | 4.141 ms | 0 - 304 MB | NPU | [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) |
-| Swin-Tiny | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 3.806 ms | 0 - 482 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.onnx.zip) |
-| Swin-Tiny | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.231 ms | 57 - 57 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.onnx.zip) |
-| Swin-Tiny | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® QCM6690 | ONNX | 216.307 ms | 104 - 121 MB | CPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-| Swin-Tiny | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | ONNX | 402.27 ms | 97 - 115 MB | CPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-| Swin-Tiny | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 92.895 ms | 33 - 55 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-| Swin-Tiny | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 75.47 ms | 34 - 311 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-| Swin-Tiny | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 62.948 ms | 20 - 228 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-| Swin-Tiny | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | ONNX | 197.88 ms | 107 - 126 MB | CPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-| Swin-Tiny | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 58.349 ms | 44 - 243 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-| Swin-Tiny | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 68.431 ms | 62 - 62 MB | NPU | [Swin-Tiny.onnx.zip](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny_w8a16.onnx.zip) |
-## Installation
-Install the package via pip:
-```bash
-pip install qai-hub-models
-```
-## 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.swin_tiny.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.swin_tiny.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.swin_tiny.export
-```
-## How does this work?
-This [export script](https://aihub.qualcomm.com/models/swin_tiny/qai_hub_models/models/Swin-Tiny/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:
-Step 1: **Compile model for on-device deployment**
-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.
-```python
-import torch
-import qai_hub as hub
-from qai_hub_models.models.swin_tiny import Model
-# Load the model
-torch_model = Model.from_pretrained()
-# Device
-device = hub.Device("Samsung Galaxy S25")
-# Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
-pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
-# Compile model on a specific device
-compile_job = hub.submit_compile_job(
-    model=pt_model,
-    device=device,
-    input_specs=torch_model.get_input_spec(),
-)
-# 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.swin_tiny.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.swin_tiny.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 Swin-Tiny's performance across various devices [here](https://aihub.qualcomm.com/models/swin_tiny).
-Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
 * The license for the original implementation of Swin-Tiny can be found
   [here](https://github.com/pytorch/vision/blob/main/LICENSE).
 ## References
 * [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
 * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py)
 ## 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).

 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/web-assets/model_demo.png)
+# Swin-Tiny: Optimized for Qualcomm Devices
 SwinTiny is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
+This is based on the implementation of Swin-Tiny found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py).
+This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/swin_tiny) 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:
+### Option 1: Download Pre-Exported Models
+Below are pre-exported model assets ready for deployment.
+| Runtime | Precision | Chipset | SDK Versions | Download |
+|---|---|---|---|---|
+| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-onnx-float.zip)
+| ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-onnx-w8a16.zip)
+| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-qnn_dlc-float.zip)
+| QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-qnn_dlc-w8a16.zip)
+| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-tflite-float.zip)
+For more device-specific assets and performance metrics, visit **[Swin-Tiny on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_tiny)**.
+### Option 2: Export with Custom Configurations
+Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/swin_tiny) 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
+This option is ideal if you need to customize the model beyond the default configuration provided here.
+See our repository for [Swin-Tiny on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/swin_tiny) for usage instructions.
+## Model Details
+**Model Type:** Model_use_case.image_classification
+**Model Stats:**
+- Model checkpoint: Imagenet
+- Input resolution: 224x224
+- Number of parameters: 28.8M
+- Model size (float): 110 MB
+- Model size (w8a16): 29.9 MB
+## Performance Summary
+| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
+|---|---|---|---|---|---|---
+| Swin-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.071 ms | 1 - 254 MB | NPU
+| Swin-Tiny | ONNX | float | Snapdragon® X2 Elite | 4.398 ms | 61 - 61 MB | NPU
+| Swin-Tiny | ONNX | float | Snapdragon® X Elite | 10.97 ms | 60 - 60 MB | NPU
+| Swin-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.896 ms | 0 - 315 MB | NPU
+| Swin-Tiny | ONNX | float | Qualcomm® QCS8550 (Proxy) | 10.279 ms | 0 - 74 MB | NPU
+| Swin-Tiny | ONNX | float | Qualcomm® QCS9075 | 12.34 ms | 0 - 4 MB | NPU
+| Swin-Tiny | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.027 ms | 1 - 216 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.432 ms | 0 - 248 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 3.678 ms | 33 - 33 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 8.831 ms | 34 - 34 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.445 ms | 0 - 348 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS6490 | 423.954 ms | 96 - 112 MB | CPU
+| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.315 ms | 0 - 44 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS9075 | 10.077 ms | 0 - 3 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Qualcomm® QCM6690 | 217.014 ms | 107 - 123 MB | CPU
+| Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.357 ms | 0 - 289 MB | NPU
+| Swin-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 199.597 ms | 107 - 124 MB | CPU
+| Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.849 ms | 0 - 424 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 4.433 ms | 1 - 1 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Snapdragon® X Elite | 10.433 ms | 1 - 1 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 6.278 ms | 0 - 594 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 22.039 ms | 1 - 440 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 9.571 ms | 1 - 2 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Qualcomm® SA8775P | 10.93 ms | 1 - 182 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS9075 | 11.969 ms | 1 - 3 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 15.33 ms | 0 - 244 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 22.039 ms | 1 - 440 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 14.292 ms | 1 - 435 MB | NPU
+| Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.777 ms | 1 - 418 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.829 ms | 0 - 441 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.423 ms | 0 - 0 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 10.929 ms | 0 - 0 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.536 ms | 0 - 509 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 17.481 ms | 0 - 438 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 9.967 ms | 0 - 190 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8775P | 10.561 ms | 0 - 446 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 11.794 ms | 0 - 2 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 40.36 ms | 0 - 519 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.481 ms | 0 - 438 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.944 ms | 0 - 436 MB | NPU
+| Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.679 ms | 0 - 427 MB | NPU
+| Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.095 ms | 0 - 203 MB | NPU
+| Swin-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.861 ms | 0 - 281 MB | NPU
+| Swin-Tiny | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 23.322 ms | 0 - 209 MB | NPU
+| Swin-Tiny | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 10.613 ms | 0 - 3 MB | NPU
+| Swin-Tiny | TFLITE | float | Qualcomm® SA8775P | 11.662 ms | 0 - 209 MB | NPU
+| Swin-Tiny | TFLITE | float | Qualcomm® QCS9075 | 12.887 ms | 0 - 60 MB | NPU
+| Swin-Tiny | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 15.623 ms | 0 - 266 MB | NPU
+| Swin-Tiny | TFLITE | float | Qualcomm® SA7255P | 23.322 ms | 0 - 209 MB | NPU
+| Swin-Tiny | TFLITE | float | Qualcomm® SA8295P | 15.204 ms | 0 - 208 MB | NPU
+| Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.146 ms | 0 - 199 MB | NPU
 ## License
 * The license for the original implementation of Swin-Tiny can be found
   [here](https://github.com/pytorch/vision/blob/main/LICENSE).
 ## References
 * [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030)
 * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py)
 ## 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).

Swin-Tiny_float.onnx.zip DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b676c362776aefe606232197cb18c2e7fc866ed5e4d02c7c3ab2b1434b5e231d
-size 105339415

Swin-Tiny_float.tflite DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:30aa63ba1bd105871670dd0873b16c92b474dc2fc596a48f0857b4762278ebdd
-size 115345012

Swin-Tiny_w8a16.onnx.zip DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0788192f2fdbadec66ce7be44374bf9fdaff1697fcda451542721d1ef83ce60b
-size 97056770

release_assets.json ADDED Viewed

	@@ -0,0 +1,46 @@

+{
+    "version": "0.51.0",
+    "precisions": {
+        "w8a16": {
+            "universal_assets": {
+                "qnn_dlc": {
+                    "tool_versions": {
+                        "qairt": "2.45.0.260326154327"
+                    },
+                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-qnn_dlc-w8a16.zip"
+                },
+                "onnx": {
+                    "tool_versions": {
+                        "qairt": "2.42.0.251225135753_193295",
+                        "onnx_runtime": "1.24.3"
+                    },
+                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-onnx-w8a16.zip"
+                }
+            }
+        },
+        "float": {
+            "universal_assets": {
+                "tflite": {
+                    "tool_versions": {
+                        "qairt": "2.45.0.260326154327",
+                        "litert": "1.4.2"
+                    },
+                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-tflite-float.zip"
+                },
+                "qnn_dlc": {
+                    "tool_versions": {
+                        "qairt": "2.45.0.260326154327"
+                    },
+                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-qnn_dlc-float.zip"
+                },
+                "onnx": {
+                    "tool_versions": {
+                        "qairt": "2.42.0.251225135753_193295",
+                        "onnx_runtime": "1.24.3"
+                    },
+                    "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.51.0/swin_tiny-onnx-float.zip"
+                }
+            }
+        }
+    }
+}

tool-versions.yaml DELETED Viewed

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