EasyOCR / README.md

qaihm-bot

Upload README.md with huggingface_hub

7333566 verified 9 months ago

preview code

raw

history blame

17 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	41.91 ms	10 - 141 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	38.543 ms	6 - 8 MB	FP16	NPU	EasyOCR.so
EasyOCRDetector	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	39.323 ms	19 - 110 MB	FP16	NPU	EasyOCR.onnx
EasyOCRDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	TFLITE	30.086 ms	16 - 69 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	28.126 ms	6 - 24 MB	FP16	NPU	EasyOCR.so
EasyOCRDetector	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	28.858 ms	35 - 72 MB	FP16	NPU	EasyOCR.onnx
EasyOCRDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	29.475 ms	14 - 47 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	29.547 ms	6 - 33 MB	FP16	NPU	Use Export Script
EasyOCRDetector	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	24.527 ms	39 - 74 MB	FP16	NPU	EasyOCR.onnx
EasyOCRDetector	SA7255P ADP	SA7255P	TFLITE	2114.004 ms	15 - 44 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA7255P ADP	SA7255P	QNN	2109.728 ms	2 - 11 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8255 (Proxy)	SA8255P Proxy	TFLITE	41.396 ms	11 - 147 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8255 (Proxy)	SA8255P Proxy	QNN	39.444 ms	6 - 9 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8295P ADP	SA8295P	TFLITE	78.432 ms	16 - 49 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8295P ADP	SA8295P	QNN	75.075 ms	0 - 17 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8650 (Proxy)	SA8650P Proxy	TFLITE	41.574 ms	12 - 148 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8650 (Proxy)	SA8650P Proxy	QNN	38.407 ms	6 - 8 MB	FP16	NPU	Use Export Script
EasyOCRDetector	SA8775P ADP	SA8775P	TFLITE	88.559 ms	16 - 45 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	SA8775P ADP	SA8775P	QNN	84.944 ms	1 - 11 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS8275 (Proxy)	QCS8275 Proxy	TFLITE	2114.004 ms	15 - 44 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS8275 (Proxy)	QCS8275 Proxy	QNN	2109.728 ms	2 - 11 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS8550 (Proxy)	QCS8550 Proxy	TFLITE	40.574 ms	7 - 140 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS8550 (Proxy)	QCS8550 Proxy	QNN	38.257 ms	6 - 9 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS9075 (Proxy)	QCS9075 Proxy	TFLITE	88.559 ms	16 - 45 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS9075 (Proxy)	QCS9075 Proxy	QNN	84.944 ms	1 - 11 MB	FP16	NPU	Use Export Script
EasyOCRDetector	QCS8450 (Proxy)	QCS8450 Proxy	TFLITE	76.952 ms	16 - 72 MB	FP16	NPU	EasyOCR.tflite
EasyOCRDetector	QCS8450 (Proxy)	QCS8450 Proxy	QNN	71.123 ms	6 - 36 MB	FP16	NPU	Use Export Script
EasyOCRDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	38.701 ms	6 - 6 MB	FP16	NPU	Use Export Script
EasyOCRDetector	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	40.36 ms	66 - 66 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	Samsung Galaxy S23	Snapdragon® 8 Gen 2	TFLITE	127.76 ms	2 - 4 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	Samsung Galaxy S23	Snapdragon® 8 Gen 2	QNN	23.315 ms	0 - 11 MB	FP16	NPU	EasyOCR.so
EasyOCRRecognizer	Samsung Galaxy S23	Snapdragon® 8 Gen 2	ONNX	21.538 ms	0 - 23 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	Samsung Galaxy S24	Snapdragon® 8 Gen 3	TFLITE	112.41 ms	9 - 29 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	Samsung Galaxy S24	Snapdragon® 8 Gen 3	QNN	16.967 ms	0 - 19 MB	FP16	NPU	EasyOCR.so
EasyOCRRecognizer	Samsung Galaxy S24	Snapdragon® 8 Gen 3	ONNX	15.089 ms	0 - 21 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	TFLITE	103.434 ms	20 - 35 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	18.591 ms	0 - 427 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	ONNX	14.033 ms	0 - 16 MB	FP16	NPU	EasyOCR.onnx
EasyOCRRecognizer	SA7255P ADP	SA7255P	TFLITE	558.999 ms	8 - 17 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA7255P ADP	SA7255P	QNN	281.972 ms	0 - 9 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8255 (Proxy)	SA8255P Proxy	TFLITE	112.26 ms	6 - 9 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8255 (Proxy)	SA8255P Proxy	QNN	23.271 ms	0 - 3 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8295P ADP	SA8295P	TFLITE	212.269 ms	11 - 29 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8295P ADP	SA8295P	QNN	39.146 ms	0 - 18 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8650 (Proxy)	SA8650P Proxy	TFLITE	115.66 ms	8 - 10 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8650 (Proxy)	SA8650P Proxy	QNN	23.236 ms	0 - 2 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	SA8775P ADP	SA8775P	TFLITE	408.093 ms	8 - 18 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	SA8775P ADP	SA8775P	QNN	31.5 ms	0 - 10 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS8275 (Proxy)	QCS8275 Proxy	TFLITE	558.999 ms	8 - 17 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS8275 (Proxy)	QCS8275 Proxy	QNN	281.972 ms	0 - 9 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS8550 (Proxy)	QCS8550 Proxy	TFLITE	123.177 ms	8 - 10 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS8550 (Proxy)	QCS8550 Proxy	QNN	23.274 ms	0 - 3 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS9075 (Proxy)	QCS9075 Proxy	TFLITE	408.093 ms	8 - 18 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS9075 (Proxy)	QCS9075 Proxy	QNN	31.5 ms	0 - 10 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	QCS8450 (Proxy)	QCS8450 Proxy	TFLITE	130.512 ms	6 - 24 MB	FP32	CPU	EasyOCR.tflite
EasyOCRRecognizer	QCS8450 (Proxy)	QCS8450 Proxy	QNN	36.541 ms	0 - 169 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	24.492 ms	0 - 0 MB	FP16	NPU	Use Export Script
EasyOCRRecognizer	Snapdragon X Elite CRD	Snapdragon® X Elite	ONNX	18.355 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)   : 41.9                   
Estimated peak memory usage (MB): [10, 141]              
Total # Ops                     : 42                     
Compute Unit(s)                 : NPU (42 ops)           

------------------------------------------------------------
EasyOCRRecognizer
Device                          : Samsung Galaxy S23 (13)
Runtime                         : TFLITE                 
Estimated inference time (ms)   : 127.8                  
Estimated peak memory usage (MB): [2, 4]                 
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
torch_model = Model.from_pretrained()

# Device
device = hub.Device("Samsung Galaxy S24")

# 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 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

Source Model Implementation

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.