Ayden K

I have discovered that this issue is caused by my training input resolution, which was 640x360. Is it possible to use a custom resolution and convert to ONNX?

Image size must be a multiple of 32. 512x288 will convert.

I'm experiencing this exact problem as well, using this docker container `paddlepaddle/paddle:2.3.2-gpu-cuda11.2-cudnn8 `. The output of tools/infer_rec.py when running my trained model on a test set is almost perfect. The...

@chengchenng I noticed a difference between the resize function from tools/infer_rec.py and the eval script. I had to set the infer_mode = False during the ops creation to match the...

To follow up from @chengchenng comment, I've noticed two issues with the current ppocr issue. 1. The call method in predict_rec.py checks to see if the algorithm matches "SVTR" to...