-
the Symbols is
```python
Symbols = "'.,:;-_=()[]{}/°"
BLANK_SYMBOL = '$'
```
when I run the code I meet the error
```sh [[Node: CTCLoss = CTCLoss[ctc_merge_repeated=true, ignore_longer_outp…
-
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 …
-
Hi @Bartzi , recently I want to run the `train_text_recognization.py` and confused about the file `curriculum.json`. In your `README.md` file, it says that the template should be:
```javascript
[
…
jxlxt updated
6 years ago
-
Hi, I am running into a problem compiling TB++:
```
[ 50%] Building CXX object CMakeFiles/crnn.dir/ctc.cpp.o
/home/john/TextBoxes_plusplus/crnn/src/cpp/ctc.cpp: In instantiation of ‘int {anonymou…
-
This is an issue of NLP online service.
When run inference, the memory usage is always kept as about 6G, which is definitely larger than actually needed.
![image](https://user-images.githubuserc…
-
@TJCVRS 我用crnn训练中文，5300类别。ctc_loss一直下不去，感觉就识别率在35%左右就不动了。。如何破？有什么好的建议么？
-
你好，我在本地主机跑只有一个ＧＰＵ这是没有问题的，但是由于速度太慢我想放在服务器上跑，服务器上是四块ＧＰＵ，但是即使我没有没有做任何修改
python crnn_main.py --trainroot train --valroot train --cuda
仅仅这样运行 也会出现如下错误
AttributeError: 'module' object has no attribute 'g…
-
你好，我在运行的是master分支的那个项目，按照readme里说的生成了tf文件，用项目自带的.json文件可以成功训练和测试，但是我想训练这个网络只识别数字，所以用chinese_version_debug分支的tools下的establish_char_dict.py生成了char_dict.json和index_2_ord_map.json，把后者改成ord_map.json之后都放回了m…
-
now, I have trained a model with mnist dataset, how can I test the model?, or Is there a script ?
-
I encountered some problems when predicting using estimator with following code:
`
import argparse
import os, time
import csv
import numpy as np
try:
import better_exceptions
except Import…