Luke Manuel Daely

In the directory where you installed PPOCRLabel: 1. open `PPOCRLabel.py`. 2. Delete this lines https://github.com/PaddlePaddle/PaddleOCR/blob/76fefd56f86f2809a6e8f719220746442fbab9f3/PPOCRLabel/PPOCRLabel.py#L2371-L2391 3. And replace it with these ```python try: os.startfile(os.path.normpath(excel_path)) except: print("CANNOT OPEN .xlsx. It could...

> Well, that's a bit overly general and it's hard for a developer to get into the new user mindset properly. Perhaps you could help though. Could you try to...

> > Well, that's a bit overly general and it's hard for a developer to get into the new user mindset properly. Perhaps you could help though. Could you try...

@tlikhomanenko My LexiconDecoder got error when I run `decoder = LexiconDecoder(options, trie, lm, sil_idx, blank_idx, unk_idx, transitions, is_token_lm)`. When I checked the error, it said transitions parameter expecting `List[float]` variable....

Seconded this, without concrete demo it's really hard to test. When I tried it using google-colab, turns out the packages dependencies is a mess, and I ended up reinstalled some...

@Kromtar not only conversion to onnx already discussed many times since two years ago, easyocr already provide the script to export the model into onnx format. What's the difference between...

This is what chatgpt spews out when I asked it to also consider dict and configs: ```python import onnx # Define the output ONNX file path output_path = 'model.onnx' #...

@samiechan Onnx image_width is not dynamic, if our input image width exceeds it it'll get an error. Is there a way to make it dynamic?

I've also had the same problem trying to convert easyocr recognizer. Seems like torch2trt doesn't support LSTM right out the bat. I'm not tried it yet, but maybe this issue...

I find that the model is less accurate when the text is tightly fitted within the cell borders. And it can't be fixed with padding.