GoogLeNetQuantized / README.md
qaihm-bot's picture
Upload README.md with huggingface_hub
2fb56fd verified
|
raw
history blame
7.8 kB
---
datasets:
- imagenet-1k
- imagenet-22k
library_name: pytorch
license: bsd-3-clause
pipeline_tag: image-classification
tags:
- quantized
- android
---
![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/googlenet_quantized/web-assets/model_demo.png)
# GoogLeNetQuantized: Optimized for Mobile Deployment
## Imagenet classifier and general purpose backbone
GoogLeNet 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 GoogLeNetQuantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/googlenet.py).
This repository provides scripts to run GoogLeNetQuantized on Qualcomm® devices.
More details on model performance across various devices, can be found
[here](https://aihub.qualcomm.com/models/googlenet_quantized).
### Model Details
- **Model Type:** Image classification
- **Model Stats:**
- Model checkpoint: Imagenet
- Input resolution: 224x224
- Number of parameters: 6.62M
- Model size: 6.55 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 | 0.296 ms | 0 - 1 MB | INT8 | NPU | [GoogLeNetQuantized.tflite](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.tflite)
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.337 ms | 0 - 4 MB | INT8 | NPU | [GoogLeNetQuantized.so](https://huggingface.co/qualcomm/GoogLeNetQuantized/blob/main/GoogLeNetQuantized.so)
## Installation
This model can be installed as a Python package via pip.
```bash
pip install "qai-hub-models[googlenet_quantized]"
```
## 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.googlenet_quantized.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.googlenet_quantized.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.googlenet_quantized.export
```
```
Profile Job summary of GoogLeNetQuantized
--------------------------------------------------
Device: Snapdragon X Elite CRD (11)
Estimated Inference Time: 0.46 ms
Estimated Peak Memory Range: 0.49-0.49 MB
Compute Units: NPU (86) | Total (86)
```
## How does this work?
This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/GoogLeNetQuantized/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.googlenet_quantized 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.googlenet_quantized.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.googlenet_quantized.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 GoogLeNetQuantized's performance across various devices [here](https://aihub.qualcomm.com/models/googlenet_quantized).
Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
## License
- The license for the original implementation of GoogLeNetQuantized 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]({deploy_license_url})
## References
* [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)
* [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/googlenet.py)
## 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).