Upload README.md with huggingface_hub

9ab46db verified over 1 year ago

16.1 kB

---
library_name: pytorch
license: other
tags:
- backbone
- android
pipeline_tag: video-classification

---
![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/web-assets/model_demo.png)

# ResNet-Mixed-Convolution: Optimized for Mobile Deployment
## Sports and human action recognition in videos


ResNet Mixed Convolutions is a network with a mixture of 2D and 3D convolutions used for video understanding.

This model is an implementation of ResNet-Mixed-Convolution found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py).


This repository provides scripts to run ResNet-Mixed-Convolution on Qualcomm® devices.
More details on model performance across various devices, can be found
[here](https://aihub.qualcomm.com/models/resnet_mixed).


### Model Details

- **Model Type:** Model_use_case.video_classification
- **Model Stats:**
  - Model checkpoint: Kinectics-400
  - Input resolution: 112x112
  - Number of parameters: 11.7M
  - Model size (float): 44.7 MB
  - Model size (w8a8): 11.7 MB
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| ResNet-Mixed-Convolution | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 344.111 ms | 31 - 56 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 98.863 ms | 2 - 12 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 154.441 ms | 31 - 66 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 28.201 ms | 2 - 61 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 143.843 ms | 31 - 42 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 14.264 ms | 2 - 5 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 155.844 ms | 31 - 58 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 26.115 ms | 2 - 16 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 344.111 ms | 31 - 56 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 98.863 ms | 2 - 12 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 141.757 ms | 31 - 41 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 14.362 ms | 2 - 4 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 168.047 ms | 31 - 56 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 27.611 ms | 0 - 18 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 140.214 ms | 8 - 36 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 14.204 ms | 2 - 5 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 155.844 ms | 31 - 58 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 26.115 ms | 2 - 16 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 142.618 ms | 8 - 28 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 14.188 ms | 3 - 26 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 14.028 ms | 0 - 92 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
| ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 106.526 ms | 31 - 67 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 10.242 ms | 2 - 69 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.654 ms | 2 - 64 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
| ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 133.514 ms | 30 - 58 MB | NPU | [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) |
| ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 10.207 ms | 2 - 67 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 10.355 ms | 2 - 56 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
| ResNet-Mixed-Convolution | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 14.916 ms | 2 - 2 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.896 ms | 23 - 23 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) |
| ResNet-Mixed-Convolution | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.364 ms | 1 - 10 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 6.402 ms | 1 - 55 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 4.174 ms | 1 - 3 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 4.531 ms | 1 - 15 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 24.061 ms | 1 - 12 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN | 14.364 ms | 1 - 10 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 4.162 ms | 1 - 4 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN | 7.624 ms | 1 - 18 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 4.181 ms | 1 - 3 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN | 4.531 ms | 1 - 15 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 4.145 ms | 0 - 14 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.026 ms | 0 - 35 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) |
| ResNet-Mixed-Convolution | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 3.014 ms | 1 - 53 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.678 ms | 0 - 57 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) |
| ResNet-Mixed-Convolution | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 2.755 ms | 1 - 42 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.111 ms | 1 - 46 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) |
| ResNet-Mixed-Convolution | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.542 ms | 1 - 1 MB | NPU | Use Export Script |
| ResNet-Mixed-Convolution | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.327 ms | 12 - 12 MB | NPU | [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) |
## Installation
Install the package via pip:
```bash
pip install "qai-hub-models[resnet-mixed]"
```
## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
Sign-in to [Qualcomm® AI Hub](https://app.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://app.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.resnet_mixed.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.resnet_mixed.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.resnet_mixed.export
```
```
Profiling Results
------------------------------------------------------------
ResNet-Mixed-Convolution
Device                          : cs_8275 (ANDROID 14)                
Runtime                         : TFLITE                              
Estimated inference time (ms)   : 344.1                               
Estimated peak memory usage (MB): [31, 56]                            
Total # Ops                     : 57                                  
Compute Unit(s)                 : npu (53 ops) gpu (0 ops) cpu (4 ops)
```
## How does this work?
This [export script](https://aihub.qualcomm.com/models/resnet_mixed/qai_hub_models/models/ResNet-Mixed-Convolution/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.resnet_mixed import Model
# Load the model
torch_model = Model.from_pretrained()
# Device
device = hub.Device("Samsung Galaxy S24")
# 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. [Sign up for access](https://myaccount.qualcomm.com/signup).




## 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 ResNet-Mixed-Convolution's performance across various devices [here](https://aihub.qualcomm.com/models/resnet_mixed).
Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
## License
* The license for the original implementation of ResNet-Mixed-Convolution can be found
  [here](https://github.com/pytorch/vision/blob/main/LICENSE).
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
## References
* [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://arxiv.org/abs/1711.11248)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.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).

	---
	library_name: pytorch
	license: other
	tags:
	- backbone
	- android
	pipeline_tag: video-classification

	---

	![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/resnet_mixed/web-assets/model_demo.png)

	# ResNet-Mixed-Convolution: Optimized for Mobile Deployment
	## Sports and human action recognition in videos


	ResNet Mixed Convolutions is a network with a mixture of 2D and 3D convolutions used for video understanding.

	This model is an implementation of ResNet-Mixed-Convolution found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.py).


	This repository provides scripts to run ResNet-Mixed-Convolution on Qualcomm® devices.
	More details on model performance across various devices, can be found
	[here](https://aihub.qualcomm.com/models/resnet_mixed).


	### Model Details

	- Model Type: Model_use_case.video_classification
	- Model Stats:
	- Model checkpoint: Kinectics-400
	- Input resolution: 112x112
	- Number of parameters: 11.7M
	- Model size (float): 44.7 MB
	- Model size (w8a8): 11.7 MB

	\| Model \| Precision \| Device \| Chipset \| Target Runtime \| Inference Time (ms) \| Peak Memory Range (MB) \| Primary Compute Unit \| Target Model
	\|---\|---\|---\|---\|---\|---\|---\|---\|---\|
	\| ResNet-Mixed-Convolution \| float \| QCS8275 (Proxy) \| Qualcomm® QCS8275 (Proxy) \| TFLITE \| 344.111 ms \| 31 - 56 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| QCS8275 (Proxy) \| Qualcomm® QCS8275 (Proxy) \| QNN \| 98.863 ms \| 2 - 12 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| QCS8450 (Proxy) \| Qualcomm® QCS8450 (Proxy) \| TFLITE \| 154.441 ms \| 31 - 66 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| QCS8450 (Proxy) \| Qualcomm® QCS8450 (Proxy) \| QNN \| 28.201 ms \| 2 - 61 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| QCS8550 (Proxy) \| Qualcomm® QCS8550 (Proxy) \| TFLITE \| 143.843 ms \| 31 - 42 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| QCS8550 (Proxy) \| Qualcomm® QCS8550 (Proxy) \| QNN \| 14.264 ms \| 2 - 5 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| QCS9075 (Proxy) \| Qualcomm® QCS9075 (Proxy) \| TFLITE \| 155.844 ms \| 31 - 58 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| QCS9075 (Proxy) \| Qualcomm® QCS9075 (Proxy) \| QNN \| 26.115 ms \| 2 - 16 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| SA7255P ADP \| Qualcomm® SA7255P \| TFLITE \| 344.111 ms \| 31 - 56 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| SA7255P ADP \| Qualcomm® SA7255P \| QNN \| 98.863 ms \| 2 - 12 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| SA8255 (Proxy) \| Qualcomm® SA8255P (Proxy) \| TFLITE \| 141.757 ms \| 31 - 41 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| SA8255 (Proxy) \| Qualcomm® SA8255P (Proxy) \| QNN \| 14.362 ms \| 2 - 4 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| SA8295P ADP \| Qualcomm® SA8295P \| TFLITE \| 168.047 ms \| 31 - 56 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| SA8295P ADP \| Qualcomm® SA8295P \| QNN \| 27.611 ms \| 0 - 18 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| SA8650 (Proxy) \| Qualcomm® SA8650P (Proxy) \| TFLITE \| 140.214 ms \| 8 - 36 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| SA8650 (Proxy) \| Qualcomm® SA8650P (Proxy) \| QNN \| 14.204 ms \| 2 - 5 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| SA8775P ADP \| Qualcomm® SA8775P \| TFLITE \| 155.844 ms \| 31 - 58 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| SA8775P ADP \| Qualcomm® SA8775P \| QNN \| 26.115 ms \| 2 - 16 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| Samsung Galaxy S23 \| Snapdragon® 8 Gen 2 Mobile \| TFLITE \| 142.618 ms \| 8 - 28 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| Samsung Galaxy S23 \| Snapdragon® 8 Gen 2 Mobile \| QNN \| 14.188 ms \| 3 - 26 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| Samsung Galaxy S23 \| Snapdragon® 8 Gen 2 Mobile \| ONNX \| 14.028 ms \| 0 - 92 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) \|
	\| ResNet-Mixed-Convolution \| float \| Samsung Galaxy S24 \| Snapdragon® 8 Gen 3 Mobile \| TFLITE \| 106.526 ms \| 31 - 67 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| Samsung Galaxy S24 \| Snapdragon® 8 Gen 3 Mobile \| QNN \| 10.242 ms \| 2 - 69 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| Samsung Galaxy S24 \| Snapdragon® 8 Gen 3 Mobile \| ONNX \| 10.654 ms \| 2 - 64 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) \|
	\| ResNet-Mixed-Convolution \| float \| Snapdragon 8 Elite QRD \| Snapdragon® 8 Elite Mobile \| TFLITE \| 133.514 ms \| 30 - 58 MB \| NPU \| [ResNet-Mixed-Convolution.tflite](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.tflite) \|
	\| ResNet-Mixed-Convolution \| float \| Snapdragon 8 Elite QRD \| Snapdragon® 8 Elite Mobile \| QNN \| 10.207 ms \| 2 - 67 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| Snapdragon 8 Elite QRD \| Snapdragon® 8 Elite Mobile \| ONNX \| 10.355 ms \| 2 - 56 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) \|
	\| ResNet-Mixed-Convolution \| float \| Snapdragon X Elite CRD \| Snapdragon® X Elite \| QNN \| 14.916 ms \| 2 - 2 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| float \| Snapdragon X Elite CRD \| Snapdragon® X Elite \| ONNX \| 14.896 ms \| 23 - 23 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution.onnx) \|
	\| ResNet-Mixed-Convolution \| w8a8 \| QCS8275 (Proxy) \| Qualcomm® QCS8275 (Proxy) \| QNN \| 14.364 ms \| 1 - 10 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| QCS8450 (Proxy) \| Qualcomm® QCS8450 (Proxy) \| QNN \| 6.402 ms \| 1 - 55 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| QCS8550 (Proxy) \| Qualcomm® QCS8550 (Proxy) \| QNN \| 4.174 ms \| 1 - 3 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| QCS9075 (Proxy) \| Qualcomm® QCS9075 (Proxy) \| QNN \| 4.531 ms \| 1 - 15 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| RB3 Gen 2 (Proxy) \| Qualcomm® QCS6490 (Proxy) \| QNN \| 24.061 ms \| 1 - 12 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| SA7255P ADP \| Qualcomm® SA7255P \| QNN \| 14.364 ms \| 1 - 10 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| SA8255 (Proxy) \| Qualcomm® SA8255P (Proxy) \| QNN \| 4.162 ms \| 1 - 4 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| SA8295P ADP \| Qualcomm® SA8295P \| QNN \| 7.624 ms \| 1 - 18 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| SA8650 (Proxy) \| Qualcomm® SA8650P (Proxy) \| QNN \| 4.181 ms \| 1 - 3 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| SA8775P ADP \| Qualcomm® SA8775P \| QNN \| 4.531 ms \| 1 - 15 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Samsung Galaxy S23 \| Snapdragon® 8 Gen 2 Mobile \| QNN \| 4.145 ms \| 0 - 14 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Samsung Galaxy S23 \| Snapdragon® 8 Gen 2 Mobile \| ONNX \| 5.026 ms \| 0 - 35 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Samsung Galaxy S24 \| Snapdragon® 8 Gen 3 Mobile \| QNN \| 3.014 ms \| 1 - 53 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Samsung Galaxy S24 \| Snapdragon® 8 Gen 3 Mobile \| ONNX \| 3.678 ms \| 0 - 57 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Snapdragon 8 Elite QRD \| Snapdragon® 8 Elite Mobile \| QNN \| 2.755 ms \| 1 - 42 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Snapdragon 8 Elite QRD \| Snapdragon® 8 Elite Mobile \| ONNX \| 3.111 ms \| 1 - 46 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Snapdragon X Elite CRD \| Snapdragon® X Elite \| QNN \| 4.542 ms \| 1 - 1 MB \| NPU \| Use Export Script \|
	\| ResNet-Mixed-Convolution \| w8a8 \| Snapdragon X Elite CRD \| Snapdragon® X Elite \| ONNX \| 5.327 ms \| 12 - 12 MB \| NPU \| [ResNet-Mixed-Convolution.onnx](https://huggingface.co/qualcomm/ResNet-Mixed-Convolution/blob/main/ResNet-Mixed-Convolution_w8a8.onnx) \|




	## Installation


	Install the package via pip:
	```bash
	pip install "qai-hub-models[resnet-mixed]"
	```


	## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device

	Sign-in to [Qualcomm® AI Hub](https://app.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://app.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.resnet_mixed.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.resnet_mixed.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.resnet_mixed.export
	```
	```
	Profiling Results
	------------------------------------------------------------
	ResNet-Mixed-Convolution
	Device : cs_8275 (ANDROID 14)
	Runtime : TFLITE
	Estimated inference time (ms) : 344.1
	Estimated peak memory usage (MB): [31, 56]
	Total # Ops : 57
	Compute Unit(s) : npu (53 ops) gpu (0 ops) cpu (4 ops)
	```


	## How does this work?

	This [export script](https://aihub.qualcomm.com/models/resnet_mixed/qai_hub_models/models/ResNet-Mixed-Convolution/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.resnet_mixed import Model

	# Load the model
	torch_model = Model.from_pretrained()

	# Device
	device = hub.Device("Samsung Galaxy S24")

	# 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. [Sign up for access](https://myaccount.qualcomm.com/signup).




	## 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 ResNet-Mixed-Convolution's performance across various devices [here](https://aihub.qualcomm.com/models/resnet_mixed).
	Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)


	## License
	* The license for the original implementation of ResNet-Mixed-Convolution can be found
	[here](https://github.com/pytorch/vision/blob/main/LICENSE).
	* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)



	## References
	* [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://arxiv.org/abs/1711.11248)
	* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/video/resnet.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).