-
你好,这个代码我有研究过,有两个问题想请教下:
1. train_code中提供了crnn训练的三个代码,ctc,ctcV2,与torch版的CTC,请问,实际训练时用的哪个代码?
2. 我自己也写过类似的工程,但是训练出的模型在识别英文整段语句时,单词和单词之间是相连的,也就没法识别出单词间的空格,我尝试过网上大多数模型在识别英文时也存在这个问题,不过你文中的CRNN-1010.pth这个模…
-
兄弟,在数据集上进行了验证没?stn加与不加的性能对比,麻烦告诉一下吧
-
咱们这个框架的crnn部分,train.py train_python_ctc.py keys.py recognizer.py 麻烦大家解释一下这几个的用法呀,我在训练中文的时候出现损失特别大
-
你好,用作者给的train data 训练ocr,还是用自己做的数据集训练ocr, loss 一直在降,但是predict的结果一直为空,准确率为0,请问是为什么呢?感谢!
-
Error log:
```
File "/home/users/***/lib/python2.7/site-packages/paddle/fluid/parallel_executor.py", line 260, in run
self.executor.run(fetch_list, fetch_var_name)
paddle.fluid.core.Enforc…
-
训练速度要低很多
-
-
When I create lmdb dataset with custom data(e.g. with trdg create multi words in per image), I followed the guide to create dataset, and I trained with below code:
`CUDA_VISIBLE_DEVICES=0,1,2,3 pytho…
-
I have some variable saved from crnn-pytorch, which runs on gpu and uses warp-ctc. Then I use those variables in my code, I can run it on cpu and the results are correct. But when I run it on gpu, I g…
-
When I use command ` python train.py --use_gpu False --parallel=False --total_step 5 --save_model_period 5 --save_model_dir ./models`, I got below information. Could you have a look into it?
`[chua…