Hugging Face's logo

qualcomm
/
OpenAI-Clip

Image Classification
PyTorch
TF Lite
ONNX
foundation
android
Model card Files Community
1
OpenAI-Clip / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
163c1f3 verified
preview code
|
raw
history blame
8.64 kB
metadata
library_name: pytorch
license: mit
pipeline_tag: image-classification
tags:
  - foundation
  - android

OpenAI-Clip: Optimized for Mobile Deployment

Multi-modal foundational model for vision and language tasks like image/text similarity and for zero-shot image classification

Contrastive Language-Image Pre-Training (CLIP) uses a ViT like transformer to get visual features and a causal language model to get the text features. Both the text and visual features can then be used for a variety of zero-shot learning tasks.

This model is an implementation of OpenAI-Clip found here. This repository provides scripts to run OpenAI-Clip on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Image classification
  • Model Stats:
    • Model checkpoint: ViT-B/16
    • Image input resolution: 224x224
    • Text context length: 77
    • Number of parameters (CLIPTextEncoder): 76.0M
    • Model size (CLIPTextEncoder): 290 MB
    • Number of parameters (CLIPImageEncoder): 115M
    • Model size (CLIPImageEncoder): 437 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 15.437 ms 0 - 4 MB FP16 NPU CLIPTextEncoder.tflite
Samsung Galaxy S23 Ultra (Android 13) Snapdragon® 8 Gen 2 TFLite 126.791 ms 0 - 4 MB FP16 NPU CLIPImageEncoder.tflite
Samsung Galaxy S23 Ultra (Android 13) Snapdragon® 8 Gen 2 QNN Model Library 8.102 ms 0 - 20 MB FP16 NPU CLIPTextEncoder.so
Samsung Galaxy S23 Ultra (Android 13) Snapdragon® 8 Gen 2 QNN Model Library 50.465 ms 0 - 59 MB FP16 NPU CLIPImageEncoder.so

Installation

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

pip install "qai-hub-models[openai_clip]"

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

Sign-in to Qualcomm® AI Hub 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.

qai-hub configure --api_token API_TOKEN

Navigate to 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.

python -m qai_hub_models.models.openai_clip.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.openai_clip.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.
python -m qai_hub_models.models.openai_clip.export

Profile Job summary of CLIPTextEncoder
--------------------------------------------------
Device: Samsung Galaxy S24 (14)
Estimated Inference Time: 11.18 ms
Estimated Peak Memory Range: 0.02-210.88 MB
Compute Units: NPU (574),CPU (2) | Total (576)

Profile Job summary of CLIPImageEncoder
--------------------------------------------------
Device: Samsung Galaxy S24 (14)
Estimated Inference Time: 96.47 ms
Estimated Peak Memory Range: 0.25-827.19 MB
Compute Units: NPU (576) | Total (576)

Profile Job summary of CLIPTextEncoder
--------------------------------------------------
Device: Samsung Galaxy S24 (14)
Estimated Inference Time: 5.70 ms
Estimated Peak Memory Range: 0.01-136.97 MB
Compute Units: NPU (377) | Total (377)

Profile Job summary of CLIPImageEncoder
--------------------------------------------------
Device: Samsung Galaxy S24 (14)
Estimated Inference Time: 38.29 ms
Estimated Peak Memory Range: 0.61-217.84 MB
Compute Units: NPU (371) | Total (371)

How does this work?

This export script leverages Qualcomm® AI Hub 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.

import torch

import qai_hub as hub
from qai_hub_models.models.openai_clip 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.

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.

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.

Deploying compiled model to Android

The models can be deployed using multiple runtimes:

  • TensorFlow Lite (.tflite export): This tutorial provides a guide to deploy the .tflite model in an Android application.

  • QNN (.so export ): This sample app provides instructions on how to use the .so shared library in an Android application.

View on Qualcomm® AI Hub

Get more details on OpenAI-Clip's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

  • The license for the original implementation of OpenAI-Clip can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community