|
|
--- |
|
|
library_name: pytorch |
|
|
license: other |
|
|
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](https://github.com/JaidedAI/EasyOCR). |
|
|
|
|
|
|
|
|
This repository provides scripts to run EasyOCR on Qualcomm® devices. |
|
|
More details on model performance across various devices, can be found |
|
|
[here](https://aihub.qualcomm.com/models/easyocr). |
|
|
|
|
|
|
|
|
|
|
|
### Model Details |
|
|
|
|
|
- **Model Type:** Model_use_case.image_to_text |
|
|
- **Model Stats:** |
|
|
- Model checkpoint: easyocr-small-stage1 |
|
|
- Input resolution: 680x800 |
|
|
- Number of parameters (EasyOCRDetector): 20.8M |
|
|
- Model size (EasyOCRDetector) (float): 79.2 MB |
|
|
- Number of parameters (EasyOCRRecognizer): 3.84M |
|
|
- Model size (EasyOCRRecognizer) (float): 14.7 MB |
|
|
|
|
|
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|
|
|---|---|---|---|---|---|---|---|---| |
|
|
| EasyOCRDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 275.495 ms | 16 - 51 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 271.438 ms | 0 - 37 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 69.519 ms | 16 - 65 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 78.539 ms | 6 - 53 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 43.688 ms | 9 - 133 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 39.511 ms | 6 - 19 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 39.726 ms | 1 - 99 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRDetector | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 71.785 ms | 16 - 50 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 68.865 ms | 2 - 38 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 275.495 ms | 16 - 51 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 271.438 ms | 0 - 37 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 41.37 ms | 6 - 142 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 38.682 ms | 6 - 18 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 78.437 ms | 16 - 55 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 75.743 ms | 3 - 44 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 40.829 ms | 10 - 152 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 38.835 ms | 6 - 18 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 71.785 ms | 16 - 50 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 68.865 ms | 2 - 38 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 40.739 ms | 10 - 147 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 38.418 ms | 6 - 24 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 40.036 ms | 37 - 52 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 29.891 ms | 16 - 61 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 29.54 ms | 21 - 62 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 29.435 ms | 15 - 45 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 29.197 ms | 14 - 53 MB | NPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 27.58 ms | 6 - 45 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 24.663 ms | 19 - 57 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 38.971 ms | 6 - 6 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 39.303 ms | 66 - 66 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRRecognizer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 486.11 ms | 8 - 18 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 79.645 ms | 0 - 263 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 131.131 ms | 9 - 32 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 38.043 ms | 0 - 198 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 108.948 ms | 3 - 6 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 34.476 ms | 0 - 46 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 21.923 ms | 2 - 12 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRRecognizer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 362.642 ms | 11 - 21 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 36.848 ms | 0 - 261 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 486.11 ms | 8 - 18 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 79.645 ms | 0 - 263 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 100.494 ms | 7 - 12 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 34.335 ms | 0 - 50 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 204.627 ms | 8 - 27 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 40.528 ms | 0 - 193 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 105.598 ms | 7 - 10 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 34.54 ms | 0 - 52 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 362.642 ms | 11 - 21 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 36.848 ms | 0 - 261 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 116.682 ms | 8 - 11 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 34.375 ms | 0 - 50 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 21.241 ms | 2 - 11 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRRecognizer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 97.535 ms | 9 - 28 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 25.789 ms | 0 - 264 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 15.977 ms | 4 - 30 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRRecognizer | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 107.038 ms | 14 - 30 MB | CPU | [EasyOCR.tflite](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.tflite) | |
|
|
| EasyOCRRecognizer | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 25.601 ms | 0 - 273 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 17.275 ms | 4 - 20 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
| EasyOCRRecognizer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 35.598 ms | 82 - 82 MB | NPU | [EasyOCR.dlc](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.dlc) | |
|
|
| EasyOCRRecognizer | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 18.246 ms | 0 - 0 MB | NPU | [EasyOCR.onnx.zip](https://huggingface.co/qualcomm/EasyOCR/blob/main/EasyOCR.onnx.zip) | |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## Installation |
|
|
|
|
|
|
|
|
Install the package via pip: |
|
|
```bash |
|
|
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](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.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. |
|
|
|
|
|
```bash |
|
|
python -m qai_hub_models.models.easyocr.export |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
## How does this work? |
|
|
|
|
|
This [export script](https://aihub.qualcomm.com/models/easyocr/qai_hub_models/models/EasyOCR/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.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. |
|
|
```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). |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## 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 EasyOCR's performance across various devices [here](https://aihub.qualcomm.com/models/easyocr). |
|
|
Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) |
|
|
|
|
|
|
|
|
## License |
|
|
* The license for the original implementation of EasyOCR can be found |
|
|
[here](https://github.com/JaidedAI/EasyOCR/blob/master/LICENSE). |
|
|
* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf) |
|
|
|
|
|
|
|
|
|
|
|
## References |
|
|
* [Source Model Implementation](https://github.com/JaidedAI/EasyOCR) |
|
|
|
|
|
|
|
|
|
|
|
## Community |
|
|
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) 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). |
|
|
|
|
|
|
|
|
|
