Hugging Face's logo

qualcomm
/
LaMa-Dilated

Image-to-Image
PyTorch
TF Lite
backbone
android
Model card Files Community
LaMa-Dilated / README.md
qaihm-bot's picture
qaihm-bot
Upload README.md with huggingface_hub
92302a3 verified
preview code
|
raw
history blame contribute delete
9.91 kB
metadata
library_name: pytorch
license: apache-2.0
pipeline_tag: image-to-image
tags:
  - backbone
  - android

LaMa-Dilated: Optimized for Mobile Deployment

High resolution image in-painting on-device

LaMa-Dilated is a machine learning model that allows to erase and in-paint part of given input image.

This model is an implementation of LaMa-Dilated found here.

This repository provides scripts to run LaMa-Dilated on Qualcomm® devices. More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Image editing
  • Model Stats:
    • Model checkpoint: Dilated CelebAHQ
    • Input resolution: 512x512
    • Number of parameters: 45.6M
    • Model size: 174 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
LaMa-Dilated Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 74.667 ms 3 - 132 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 70.735 ms 3 - 33 MB FP16 NPU LaMa-Dilated.so
LaMa-Dilated Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 51.204 ms 0 - 259 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 50.382 ms 4 - 89 MB FP16 NPU LaMa-Dilated.so
LaMa-Dilated Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 40.487 ms 0 - 159 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 37.959 ms 1 - 87 MB FP16 NPU Use Export Script
LaMa-Dilated QCS8550 (Proxy) QCS8550 Proxy TFLITE 74.739 ms 3 - 132 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated QCS8550 (Proxy) QCS8550 Proxy QNN 70.259 ms 4 - 5 MB FP16 NPU Use Export Script
LaMa-Dilated SA8255 (Proxy) SA8255P Proxy TFLITE 74.969 ms 3 - 132 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated SA8255 (Proxy) SA8255P Proxy QNN 70.339 ms 4 - 6 MB FP16 NPU Use Export Script
LaMa-Dilated SA8775 (Proxy) SA8775P Proxy TFLITE 74.691 ms 3 - 131 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated SA8775 (Proxy) SA8775P Proxy QNN 70.627 ms 4 - 5 MB FP16 NPU Use Export Script
LaMa-Dilated SA8650 (Proxy) SA8650P Proxy TFLITE 74.674 ms 3 - 132 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated SA8650 (Proxy) SA8650P Proxy QNN 70.337 ms 4 - 6 MB FP16 NPU Use Export Script
LaMa-Dilated SA8295P ADP SA8295P TFLITE 115.932 ms 3 - 89 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated SA8295P ADP SA8295P QNN 103.935 ms 1 - 7 MB FP16 NPU Use Export Script
LaMa-Dilated QCS8450 (Proxy) QCS8450 Proxy TFLITE 105.359 ms 3 - 161 MB FP16 NPU LaMa-Dilated.tflite
LaMa-Dilated QCS8450 (Proxy) QCS8450 Proxy QNN 103.357 ms 4 - 44 MB FP16 NPU Use Export Script
LaMa-Dilated Snapdragon X Elite CRD Snapdragon® X Elite QNN 71.83 ms 4 - 4 MB FP16 NPU Use Export Script

Installation

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

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

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.lama_dilated.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.lama_dilated.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.lama_dilated.export

Profiling Results
------------------------------------------------------------
LaMa-Dilated
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 74.7                   
Estimated peak memory usage (MB): [3, 132]               
Total # Ops                     : 343                    
Compute Unit(s)                 : NPU (343 ops)

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.lama_dilated import 

# Load the model

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

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.

Run demo on a cloud-hosted device

You can also run the demo on-device.

python -m qai_hub_models.models.lama_dilated.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.lama_dilated.demo -- --on-device

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 LaMa-Dilated's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community