-
logits = tf.transpose(logits, (1, 0, 2)) why? the original order is [batch time class]
self.__seq_len: [self.__max_char_count] * self.__data_manager.batch_size why? I think seq should be a varient …
-
问题一：
在将v1的模型转换成v3的模型的时候，由于新增的op 只是用于预测，，没有反向的逻辑，所以需要去掉上图中注释的地方。
:
File "/home/jxf/CRNN_Attention_OCR-master/train.py", line 24, in
img,label=cfg.read_data(cfg.train_dir)
File "/home/jxf/CRNN_Attention_OCR-master/config.…
-
您好, 我按照train.txt生成了数据，然后修改了一下代码，但是发现预测结果总是 '的', 是因为训练的次数不够多 还是我改的代码有问题？
```
[+] epoch:0, batch:371, loss:3.7565720081329346, acc:0.0,
train_decode:['，的的的的的的的的的', '，，的的的的的的的的', '，，的的的的的的的的', '，…
-
```
docker run --rm -it -v `pwd`:/opt/ctpn/CTPN/demo_images -p 8888:8888 dc/ctpn
docker run --rm -it -v `pwd`:/opt/ctpn/CTPN/demo_images dc/ctpn /bin/bash
root@8a1d73be4cbc:/opt/ctpn/CTPN#…
-
Hello,
I was googling into current research on OCR and scene detection using a deep neural network, came across CRNN and STN-OCR.
I tried `demo.py` given in this project, which works well on a s…