ririya

I'm trying to run inference on the trained models with half precision. The output for the detection model is returning all nan's. Anyone tried to do this before?

Error while training LSTM

2

I've been frequently getting this error while training the net. Can someone tell me what the problem might be? Index exceeds matrix dimensions. Error in varObj>@(C)full(C(:,r)) (line 45) v =...

Running into a bug with a sequential flow. The same is not happening on 1.1.10 ``` def char_aug(data, ocr_error_dict, p_replace=0.1, p_insert=0.1, p_delete=0.1, replace_char_p=0.05, insert_char_p=0.05, delete_char_p=0.05, lowercase=False): ocr_aug = nac.OcrAug( aug_char_min=1,...