frotms
您好,使用en_numen_number_mobile_v2.0_rec_infer.pth时会报错
按照提示都改成--rec_image_shape='3,32,100' and --rec_char_type='en' 还会报下面的错误，
Please read the FAQ：https://github.com/PaddlePaddle/PaddleOCR#faq If your model has tps module: TPS does not support variable shape. Please set --rec_image_shape='3,32,100' and --rec_char_type='en' list index out of range
命令：python3 ./tools/infer/predict_rec.py --rec_model_path ./en_number_mobile_v2.0_rec_infer.pth --rec_char_type en --rec_char_dict_path ./pytorchocr/utils/dict/en_dict.txt --image_dir ./doc/imgs_words/en
{'fc_decay': 4e-05, 'in_channels': 96} weighs is loaded. /home/ilab/anaconda3/envs/pyship/lib/python3.9/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at /opt/conda/conda-bld/pytorch_1623448255797/work/c10/core/TensorImpl.h:1156.) return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode) ERROR!!!! Please read the FAQ：https://github.com/PaddlePaddle/PaddleOCR#faq If your model has tps module: TPS does not support variable shape. Please set --rec_image_shape='3,32,100' and --rec_char_type='en' list index out of range
@libenchong 由于这里是根据PaddleOCRv2.3改的，使用en模型命令：
python3 ./tools/infer/predict_rec.py --rec_model_path ./en_number_mobile_v2.0_rec_infer.pth --rec_char_dict_path ./pytorchocr/utils/dict/en_dict.txt --image_dir ./doc/imgs_words/en
我这边没复现出问题。试一下把main函数里的try...except去掉，直接rec_res, predict_time = text_recognizer(img_list)，再运行看看会报什么错。
您好，我这边找到错误了，错误是在PaddleOCR2Pytorch-main/pytorchocr/postprocess/rec_postprocess.py第45行self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"这句代码上，它没读en_dict里面的字符，我把en_dict里面的字符里面的字符放到这句代码里面还是报错，您能重新提供一份en_dict.txt 吗？
您好，bug解决了，PaddleOCR2Pytorch-main/pytorchocr/postprocess/rec_postprocess.py第45行self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"这句代码上，它没读en_dict里面的字符，另外您提供的en_dict.txt和百度官方的不一致，可以更新一下
您好，我从您github这边看到的en_dict.txt里面是有62个字符， 在百度官方PaddleOCR/ppocr/utils/en_dict.txt里面有94个字符
您好，我从您github这边看到的en_dict.txt里面是有62个字符， 在百度官方PaddleOCR/ppocr/utils/en_dict.txt里面有94个字符
是这个en_dict.txt，不是PaddleOCR/ppocr/utils/en_dict.txt
For people suffering from same problems, I solve this problem by changing the line 29 in 'PaddleOCR2Pytorch-main/pytorchocr/postprocess/rec_postprocess.py'
from if character_dict_path is 'en': to if character_dict_path is None:
