-
crnn can recognize line of charactors by my understading, but images of yours appears to be 2 lines.
is my understand right?
-
Currently TRTIS only allows the first dimension of an input/output tensor to be variable sized and only when that dimension represents batching. TRTIS should allow variable-sized dimensions in other c…
-
1. 在models/fluid/PaddleCV/ocr_recognition, 我想使用train.py的def test()里添加以下下面的代码来保存crnn_ctc的__model__文件
fluid.io.save_inference_model(args.save_model_dir,["image","label"],test_seq_error,exe,main_progr…
ghost updated
5 years ago
-
当我尝试运行这份代码时，test.py 有以下报错信息，疑惑？
我添加了map_location='cpu' 是这个原因吗？
model.load_state_dict(torch.load(crnn_model_path,map_location='cpu'))
报错信息：
>> python test.py ****
loading pretrained model from …
-
请问会公开yolo3的训练code么，
yolo3除了在时效上优于ctpn, 准确度上有改进吗
-
Hi 哥哥
今天把那个CRNN_TensorFlow clone下来的时候，然后在PyCharm中运行那个
测试图片ocr的时候报错，是不是github上面那个模型不好使呀？需要自己训练呀？
:
File "", line 1, in
File "…
-
### Model
Original Model: https://github.com/PaddlePaddle/models/blob/develop/fluid/ocr_recognition/crnn_ctc_model.py
- Since the inference model will do fuse batch norm, thus, we can easily change …