PPOCR_v6

PPOCR_v6

English | 中文

This version of PPOCR_v6 has been converted to run on AXERA NPU with w8a16 quantization.

Conversion Tool Links

If you are interested in model conversion, you can export axmodel through the following links:

• ax-samples-github, other interesting samples

• Pulsar2 Documentation, ONNX to axmodel conversion

Supported Platforms

• AX650
  • M4N-Dock (AXERA Pi Pro)
  • M.2 Accelerator Card
• AX630C
  • AXERA Pi 2
  • Module-LLM
  • LLM630 Compute Kit
• AX615
  • AX615 IPC SoC

Performance Benchmarks

Benchmarking command:

ax_run_model -w 10 -r 100 -m xx.axmodel

Recognition and detection ONNX model sources: small-det-onnx and small-rec-onnx from PaddlePaddle/PP-OCRv6

Text direction classifier: AXERA-TECH/PPOCR_v5

Usage

Download all files from this repository to your device.

PPOCR_v6# tree -L 1
.
|-- 11.jpg          # Test image
|-- README-zh.md
|-- README.md
|-- axmodel         # Axmodel files for each version
|-- cls.json        # Text direction classifier axmodel conversion config
|-- dataset         # Quantization dataset & test dataset
|-- det.json        # Detection model axmodel conversion config
|-- fonts           # Rendering fonts
|-- onnx            # Original ONNX files for each model
|-- ppocrv6_ax.py   # Axmodel inference pipeline
|-- ppocrv6_onnx.py # ONNX inference pipeline
|-- rec.json        # Recognition model axmodel conversion config
|-- res-ax.jpg      # Axmodel inference result
|-- res-onnx.jpg    # ONNX inference result
|-- run_det_ax.py   # Detection axmodel accuracy test script
|-- run_det_onnx.py # Detection ONNX accuracy test script
|-- run_rec_ax.py   # Recognition axmodel accuracy test script
`-- run_rec_onnx.py # Recognition ONNX accuracy test script

Conversion

cd dataset 
sh download_quant_dataset.sh
sh download_val_dataset.sh
cd ..
pulsar2 build --config det.json 
pulsar2 build --config cls.json 
pulsar2 build --config rec.json 

Testing

Detection

python3 run_det_onnx.py --resize_mode letterbox   # resize_mode options: letterbox (default), stretch (official)
"""
  Images:       50
  GT boxes:     201
  DET boxes:    151
  Matched:      77
  Precision:    0.5099 (50.99%)
  Recall:       0.3831 (38.31%)
  Hmean (F1):   0.4375
"""
python3 run_det_ax.py --resize_mode letterbox   # resize_mode options: letterbox (default), stretch (official)
"""
  Images:       50
  GT boxes:     201
  DET boxes:    150
  Matched:      75
  Precision:    0.5000 (50.00%)
  Recall:       0.3731 (37.31%)
  Hmean (F1):   0.4274
"""

Note: When resize_mode is stretch, it follows the official approach of directly resizing to the model input size. When resize_mode is letterbox, it pads the bottom-right corner, which has a smaller gap from the dynamic-input ONNX model and achieves better metrics in this test. You can download the inference.onnx with dynamic input shape from small-det-onnx for comparison.

Recognition

python3 run_rec_onnx.py
"""
  Total samples:         2077
  Correct (exact match): 1563
  Accuracy:              0.7525 (75.25%)
  Norm Edit Distance:    0.8947
"""
python3 run_rec_ax.py
"""
  Total samples:         2077
  Correct (exact match): 1518
  Accuracy:              0.7309 (73.09%)
  Norm Edit Distance:    0.8781
"""

Inference

Run inference on AX650 host, such as M4N-Dock (AXERA Pi Pro).

Input image:

python3 ppocrv6_onnx.py --use_angle_cls --visualize --image 11.jpg
python3 ppocrv6_ax.py --use_angle_cls --visualize --image 11.jpg

Output image:

Others

The tiny recognition model has a large quantization error. Metrics are as follows:

onnx-preds:
  Total samples:         2077
  Correct (exact match): 1271
  Accuracy:              0.6119 (61.19%)
  Norm Edit Distance:    0.8263

ax-w8a16-preds:
  Total samples:         2077
  Correct (exact match): 1178
  Accuracy:              0.5672 (56.72%)
  Norm Edit Distance:    0.7941

TODO

• ax630c performance benchmark
• ax615 performance benchmark