-
When running CRNN-CTC inference using C-API and `AnalysisPredictor`, I have to declare the network inputs (`pixel` and `label`) as `PaddleTensor`s of type either `PaddleDType::FLOAT` or `PaddleDType::…
-
https://github.com/Belval/CRNN/blob/063349508bd95e8dfb6b2e1135a7f8d8dd1fbc39/CRNN/crnn.py#L167
acutually, i think you shoud set the param merge_repeated to False, so the result will keep the repeat…
-
Hello,
I trained your model with mjsynth dataset and default parameter settings over 1000000 steps.
I found that the model often wrongly recognizes character 'u'.
It seems as if there is no 'u' c…
kojit updated
5 years ago
-
### Description
CRNN-CTC from the newest models developo branch crashes during training when ran with newest paddle version from develop branch ().
Models commit hash: 4c6882ab55fbf9b03c405d2fce2b…
-
Hi, I want to recognize more characters more than just English alphabet (numbers, special Unicode utf-8 characters, etc.). Suppose I have enough dataset, what is the modification I need to train/predi…
-
Saved model to: ./output/models/model_186000.
Time: 1541876304.23; Iter[187000]; Avg Warp-CTC loss: 1.017; Avg seq err: 0.138
Time: 1541876684.59; Iter[188000]; Avg Warp-CTC loss: 0.914; Avg seq…
-
# CRNN-CTC train error
During training crnn model (ocr_recognition) an errors occurs which most probably is placed in the paddle source.
> Traceback (most recent call last):
> File "/root/model…
-
### 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 …
-
连续两个相同的字符会漏掉一个:
例如: aaby识别为aby, 887y识别为87y
chyun updated
6 years ago
-
tf.contrib.seq2seq.LuongAttention(num_units=cfg.RNN_UNITS, memory=memory)这里的memory是什么意思？我看代码是把encode的输出当作memory的，另外我把tf.contrib.seq2seq.BasicDecoder(
cell=attn_cell, helper=helper,
…