Skip to content

πŸ“„ Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.

Merge branch 'param_gpu' of github.com:RapidAI/RapidOCR into param_gpu

SWHL95a67b3032e8
diff --cc python/config.yaml
index 559a31f,e640e67..afb3ccb
--- a/python/config.yaml
+++ b/python/config.yaml
@@@ -6,8 -6,8 +6,17 @@@ Global
Det:
module_name: ch_ppocr_v2_det
class_name: TextDetector
- model_path: resources/models/ch_PP-OCRv2_det_infer.onnx
+ model_path: resources/models/ch_PP-OCRv3_det_infer.onnx
+
++ use_cuda: false
++ # Details of the params: https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html
++ CUDAExecutionProvider:
++ device_id: 0
++ arena_extend_strategy: kNextPowerOfTwo
++ # gpu_mem_limit: 2 * 1024 * 1024 * 1024
++ cudnn_conv_algo_search: EXHAUSTIVE
++ do_copy_in_default_stream: true
+
use_cuda: false
# Details of the params: https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html
CUDAExecutionProvider: