gliufetch

how to convert a finetuned student model (detection v3)

1

for a fine tuned model https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/finetune.md#22-%E6%A8%A1%E5%9E%8B%E9%80%89%E6%8B%A9 > 注意：在使用上述预训练模型的时候，需要使用文件夹中的student.pdparams文件作为预训练模型，即，仅使用学生模型。 how to convert the student model? `python3 ./converter/ch_ppocr_v3_det_converter.py --src_model_path models/ch_det_v3_student` getting error: ` File "./converter/ch_ppocr_v3_det_converter.py", line 60, in load_paddle_weights print("paddle_2: {}, {}".format(ppname,...

en_PP-OCRv3_rec convert/inference error

1

all this is about en_paddleOcr_v3_rec model: 1. convert model (https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) ``` (.venv) ➜ PaddleOCR2Pytorch git:(test) ✗ python3 ./converter/multilingual_ppocr_v3_rec_converter.py --src_model_path en_PP-OCRv3_rec_train out_channels: 97 {} {'fc_decay': 2e-05, 'in_channels': 64} model is loaded....

why is only 1st 'batch' inferred?

2

I have an ensemble model, model 1 output are 66 cropped images, model 1 is python, I manually resize/padded them to 3 batches with shape (30, 3, 48, 320), (30,...