Upload README.md with huggingface_hub

3f18a5c verified over 2 years ago

7.89 kB

---
library_name: pytorch
license: other
pipeline_tag: image-to-image
tags:
- android

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

# QuickSRNetLarge: Optimized for Mobile Deployment
## Upscale images and remove image noise

QuickSRNet Large is designed for upscaling images on mobile platforms to sharpen in real-time.

This model is an implementation of QuickSRNetLarge found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet).
This repository provides scripts to run QuickSRNetLarge on Qualcomm® devices.
More details on model performance across various devices, can be found
[here](https://aihub.qualcomm.com/models/quicksrnetlarge).


### Model Details

- **Model Type:** Super resolution
- **Model Stats:**
  - Model checkpoint: quicksrnet_large_4x_checkpoint_float32
  - Input resolution: 128x128
  - Number of parameters: 436K
  - Model size: 1.67 MB


| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
| ---|---|---|---|---|---|---|---|
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.492 ms | 0 - 8 MB | FP16 | NPU |  [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) 
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.101 ms | 0 - 5 MB | FP16 | NPU |  [QuickSRNetLarge.so](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.so) 


## Installation

This model can be installed as a Python package via pip.

```bash
pip install qai-hub-models
```


## 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.quicksrnetlarge.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.quicksrnetlarge.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.quicksrnetlarge.export
```

```
Profile Job summary of QuickSRNetLarge
--------------------------------------------------
Device: QCS8550 (Proxy) (12)
Estimated Inference Time: 2.48 ms
Estimated Peak Memory Range: 0.03-1.67 MB
Compute Units: NPU (28),CPU (3) | Total (31)
Profile Job summary of QuickSRNetLarge
--------------------------------------------------
Device: QCS8550 (Proxy) (12)
Estimated Inference Time: 2.10 ms
Estimated Peak Memory Range: 0.21-12.43 MB
Compute Units: NPU (31) | Total (31)
```
## How does this work?

This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/QuickSRNetLarge/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.quicksrnetlarge import Model
# Load the model
torch_model = Model.from_pretrained()
torch_model.eval()
# Device
device = hub.Device("Samsung Galaxy S23")
# 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).


## Run demo on a cloud-hosted device

You can also run the demo on-device.

```bash
python -m qai_hub_models.models.quicksrnetlarge.demo --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.quicksrnetlarge.demo -- --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 QuickSRNetLarge's performance across various devices [here](https://aihub.qualcomm.com/models/quicksrnetlarge).
Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
## License
- The license for the original implementation of QuickSRNetLarge can be found
  [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
## References
* [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)
* [Source Model Implementation](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet)
## Community
* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) 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
	pipeline_tag: image-to-image
	tags:
	- android

	---

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

	# QuickSRNetLarge: Optimized for Mobile Deployment
	## Upscale images and remove image noise

	QuickSRNet Large is designed for upscaling images on mobile platforms to sharpen in real-time.

	This model is an implementation of QuickSRNetLarge found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet).
	This repository provides scripts to run QuickSRNetLarge on Qualcomm® devices.
	More details on model performance across various devices, can be found
	[here](https://aihub.qualcomm.com/models/quicksrnetlarge).


	### Model Details

	- Model Type: Super resolution
	- Model Stats:
	- Model checkpoint: quicksrnet_large_4x_checkpoint_float32
	- Input resolution: 128x128
	- Number of parameters: 436K
	- Model size: 1.67 MB


	\| Device \| Chipset \| Target Runtime \| Inference Time (ms) \| Peak Memory Range (MB) \| Precision \| Primary Compute Unit \| Target Model
	\| ---\|---\|---\|---\|---\|---\|---\|---\|
	\| Samsung Galaxy S23 Ultra (Android 13) \| Snapdragon® 8 Gen 2 \| TFLite \| 2.492 ms \| 0 - 8 MB \| FP16 \| NPU \| [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite)
	\| Samsung Galaxy S23 Ultra (Android 13) \| Snapdragon® 8 Gen 2 \| QNN Model Library \| 2.101 ms \| 0 - 5 MB \| FP16 \| NPU \| [QuickSRNetLarge.so](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.so)


	## Installation

	This model can be installed as a Python package via pip.

	```bash
	pip install qai-hub-models
	```


	## 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.quicksrnetlarge.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.quicksrnetlarge.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.quicksrnetlarge.export
	```

	```
	Profile Job summary of QuickSRNetLarge
	--------------------------------------------------
	Device: QCS8550 (Proxy) (12)
	Estimated Inference Time: 2.48 ms
	Estimated Peak Memory Range: 0.03-1.67 MB
	Compute Units: NPU (28),CPU (3) \| Total (31)

	Profile Job summary of QuickSRNetLarge
	--------------------------------------------------
	Device: QCS8550 (Proxy) (12)
	Estimated Inference Time: 2.10 ms
	Estimated Peak Memory Range: 0.21-12.43 MB
	Compute Units: NPU (31) \| Total (31)


	```
	## How does this work?

	This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/QuickSRNetLarge/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.quicksrnetlarge import Model

	# Load the model
	torch_model = Model.from_pretrained()
	torch_model.eval()

	# Device
	device = hub.Device("Samsung Galaxy S23")

	# 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).


	## Run demo on a cloud-hosted device

	You can also run the demo on-device.

	```bash
	python -m qai_hub_models.models.quicksrnetlarge.demo --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.quicksrnetlarge.demo -- --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 QuickSRNetLarge's performance across various devices [here](https://aihub.qualcomm.com/models/quicksrnetlarge).
	Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)

	## License
	- The license for the original implementation of QuickSRNetLarge can be found
	[here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
	- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})

	## References
	* [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)
	* [Source Model Implementation](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet)

	## Community
	* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) 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).