EasyOCR / README.md

qaihm-bot

Upload README.md with huggingface_hub

216b476 verified 10 months ago

preview code

raw

history blame

18.1 kB

metadata

library_name: pytorch
license: apache-2.0
tags:
  - android
pipeline_tag: image-to-text

EasyOCR: Optimized for Mobile Deployment

Ready-to-use OCR with 80+ supported languages and all popular writing scripts

EasyOCR is a machine learning model that can recognize text in images. It supports 80+ supported languages and all popular writing scripts.

This model is an implementation of EasyOCR found here.

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

Model Details

Model Type: Image to text
Model Stats:
- Model checkpoint: easyocr-small-stage1
- Input resolution: 384x384
- Number of parameters (EasyOCRDetector): 20.8M
- Model size (EasyOCRDetector): 79.2 MB
- Number of parameters (EasyOCRRecognizer): 3.84M
- Model size (EasyOCRRecognizer): 14.7 MB

Model	Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
EasyOCRDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	TFLITE	41.189 ms	0 - 136 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	39.017 ms	6 - 9 MB	FP16	NPU	EasyOCR.so
EasyOCRDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	40.015 ms	34 - 181 MB	FP16	NPU	EasyOCR.onnx
EasyOCRDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	TFLITE	30.181 ms	14 - 45 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	29.323 ms	6 - 25 MB	FP16	NPU	EasyOCR.so
EasyOCRDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	29.584 ms	38 - 75 MB	FP16	NPU	EasyOCR.onnx
EasyOCRDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	28.753 ms	15 - 45 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	24.26 ms	6 - 36 MB	FP16	NPU	Use Export Script
EasyOCRDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	28.097 ms	43 - 78 MB	FP16	NPU	EasyOCR.onnx
EasyOCRDetector	SA7255P ADP	SA7255P	TFLITE	2113.678 ms	3 - 28 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA7255P ADP	SA7255P	QNN	2111.684 ms	0 - 8 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8255 (Proxy)	SA8255P Proxy	TFLITE	41.731 ms	0 - 97 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8255 (Proxy)	SA8255P Proxy	QNN	38.998 ms	6 - 8 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8295P ADP	SA8295P	TFLITE	78.45 ms	16 - 42 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8295P ADP	SA8295P	QNN	76.549 ms	0 - 11 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8650 (Proxy)	SA8650P Proxy	TFLITE	42.824 ms	0 - 145 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8650 (Proxy)	SA8650P Proxy	QNN	40.764 ms	6 - 8 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8775P ADP	SA8775P	TFLITE	88.536 ms	16 - 41 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8775P ADP	SA8775P	QNN	86.522 ms	1 - 9 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS8275 (Proxy)	QCS8275 Proxy	TFLITE	2113.678 ms	3 - 28 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS8275 (Proxy)	QCS8275 Proxy	QNN	2111.684 ms	0 - 8 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS8550 (Proxy)	QCS8550 Proxy	TFLITE	41.678 ms	0 - 126 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS8550 (Proxy)	QCS8550 Proxy	QNN	39.278 ms	6 - 8 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS9075 (Proxy)	QCS9075 Proxy	TFLITE	88.536 ms	16 - 41 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS9075 (Proxy)	QCS9075 Proxy	QNN	86.522 ms	1 - 9 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS8450 (Proxy)	QCS8450 Proxy	TFLITE	80.295 ms	16 - 48 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS8450 (Proxy)	QCS8450 Proxy	QNN	69.9 ms	6 - 37 MB	FP16	NPU	Use Export Script
EasyOCRDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	39.87 ms	6 - 6 MB	FP16	NPU	Use Export Script
EasyOCRDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	41.319 ms	66 - 66 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	Samsung Galaxy S23	Snapdragon® 8 Gen 2	TFLITE	109.812 ms	6 - 8 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	20.483 ms	0 - 3 MB	FP16	NPU	EasyOCR.so
EasyOCRRecognizer	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	21.731 ms	0 - 24 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	Samsung Galaxy S24	Snapdragon® 8 Gen 3	TFLITE	108.852 ms	2 - 20 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	14.237 ms	0 - 16 MB	FP16	NPU	EasyOCR.so
EasyOCRRecognizer	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	16.212 ms	1 - 24 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	107.149 ms	14 - 30 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	20.63 ms	0 - 346 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	17.677 ms	0 - 18 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	SA7255P ADP	SA7255P	TFLITE	565.404 ms	9 - 17 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA7255P ADP	SA7255P	QNN	285.155 ms	0 - 8 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8255 (Proxy)	SA8255P Proxy	TFLITE	124.344 ms	9 - 11 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8255 (Proxy)	SA8255P Proxy	QNN	20.321 ms	0 - 3 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8295P ADP	SA8295P	TFLITE	214.709 ms	8 - 18 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8295P ADP	SA8295P	QNN	30.834 ms	0 - 12 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8650 (Proxy)	SA8650P Proxy	TFLITE	101.784 ms	7 - 11 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8650 (Proxy)	SA8650P Proxy	QNN	20.407 ms	0 - 3 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8775P ADP	SA8775P	TFLITE	415.153 ms	6 - 14 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8775P ADP	SA8775P	QNN	29.021 ms	0 - 7 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS8275 (Proxy)	QCS8275 Proxy	TFLITE	565.404 ms	9 - 17 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS8275 (Proxy)	QCS8275 Proxy	QNN	285.155 ms	0 - 8 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS8550 (Proxy)	QCS8550 Proxy	TFLITE	108.193 ms	7 - 10 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS8550 (Proxy)	QCS8550 Proxy	QNN	20.315 ms	0 - 3 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS9075 (Proxy)	QCS9075 Proxy	TFLITE	415.153 ms	6 - 14 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS9075 (Proxy)	QCS9075 Proxy	QNN	29.021 ms	0 - 7 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS8450 (Proxy)	QCS8450 Proxy	TFLITE	210.333 ms	9 - 25 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS8450 (Proxy)	QCS8450 Proxy	QNN	34.309 ms	0 - 151 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	21.364 ms	0 - 0 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	19.37 ms	0 - 0 MB	FP16	NPU	EasyOCR.onnx

Installation

Install the package via pip:

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

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.easyocr.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.easyocr.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.easyocr.export

Profiling Results
------------------------------------------------------------
EasyOCRDetector
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 41.2                   
Estimated peak memory usage (MB): [0, 136]               
Total # Ops                     : 42                     
Compute Unit(s)                 : NPU (42 ops)           

------------------------------------------------------------
EasyOCRRecognizer
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 109.8                  
Estimated peak memory usage (MB): [6, 8]                 
Total # Ops                     : 136                    
Compute Unit(s)                 : CPU (136 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.easyocr import Model

# Load the model
model = Model.from_pretrained()
detector_model = model.detector
recognizer_model = model.recognizer

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

# Trace model
detector_input_shape = detector_model.get_input_spec()
detector_sample_inputs = detector_model.sample_inputs()

traced_detector_model = torch.jit.trace(detector_model, [torch.tensor(data[0]) for _, data in detector_sample_inputs.items()])

# Compile model on a specific device
detector_compile_job = hub.submit_compile_job(
    model=traced_detector_model ,
    device=device,
    input_specs=detector_model.get_input_spec(),
)

# Get target model to run on-device
detector_target_model = detector_compile_job.get_target_model()
# Trace model
recognizer_input_shape = recognizer_model.get_input_spec()
recognizer_sample_inputs = recognizer_model.sample_inputs()

traced_recognizer_model = torch.jit.trace(recognizer_model, [torch.tensor(data[0]) for _, data in recognizer_sample_inputs.items()])

# Compile model on a specific device
recognizer_compile_job = hub.submit_compile_job(
    model=traced_recognizer_model ,
    device=device,
    input_specs=recognizer_model.get_input_spec(),
)

# Get target model to run on-device
recognizer_target_model = recognizer_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.

detector_profile_job = hub.submit_profile_job(
    model=detector_target_model,
    device=device,
)
recognizer_profile_job = hub.submit_profile_job(
    model=recognizer_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.

detector_input_data = detector_model.sample_inputs()
detector_inference_job = hub.submit_inference_job(
    model=detector_target_model,
    device=device,
    inputs=detector_input_data,
)
detector_inference_job.download_output_data()
recognizer_input_data = recognizer_model.sample_inputs()
recognizer_inference_job = hub.submit_inference_job(
    model=recognizer_target_model,
    device=device,
    inputs=recognizer_input_data,
)
recognizer_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 EasyOCR's performance across various devices here. Explore all available models on Qualcomm® AI Hub

License

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

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.