-
python train.py with config3.json
...
INFO:tensorflow:Saving checkpoints for 1101 into ./model3/model.ckpt.
INFO - tensorflow - Saving checkpoints for 1101 into ./model3/model.ckpt.
INFO:tensorflo…
-
#comment: Although all images in test/ directory are of the same size i.e. (100, 32), still I am getting following error, any help?
error(detailed):
CRNN_Tensorflow$ python3 tools/write_text_fe…
-
I built a 1-layer bidirectional RNN with 128 hidden nodes using the `output = tf.nn.bidirectional_dynamic_rnn(forward_cell, backward_cell, inputs, seqlens, tf.float32, is_tuple=True, time_major=True)`…
-
您好，请问这个错误是什么原因呢？感谢感谢！
Traceback (most recent call last):
File "drive/GoogleAI/CRNN_Tensorflow-master/tools/demo_shadownet.py", line 107, in
recognize(image_path=args.image_path, weights_pa…
-
I want to run several search instances in parallel. For this I want to use the multiprocessing module. However, all subprocesses timeout after 0.1s. I am sure, this is because in `initThreadJoinHack()…
-
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…
-
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…
-
Hello, when I intend to test model, I type 'python tools/test_shadownet.py --dataset_dir data/ --weights_path model/shadownet/shadownet_2017-09-29-19-16-33.ckpt-39999' and I encounter an error which s…
-
请问我哪里弄错了？
-
I just clone the CRNN_Tensorflow-chinese_version and execute the test_shadownet.py, at first I found the tfrecords_list(which is defined in data_utils.py)=[]. so I changed the name of test_feature.tfr…