Tianshu Yin

Just change the code between CNN -> RNN in cnn_lstm_otc_ocr.py, make sure the shape of the input of RNN is [batch_size, max_stepsize, num_features].

Good job~

@anubhavrohatgi make sure the maxlength of label in your dataset must

@anubhavrohatgi @kstys make sure you understand how the framework "CNN + RNN + CTC" work and there are some bugs in this code.You should not only change the "maxsteps" in...

you can pay attention to the" dynamic_rnn" function in tf

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

just a few hours

```python dense_decoded,lastbatch_err , lr = \ sess.run([model.dense_decoded, model.lrn_rate], val_feed) ``` sees.run() only return two values,you just need to remove "lastbatch_err ",good luck

Why not~？Just do it

[Here](https://github.com/opconty/pytorch_ctpn/edit/master/readme.md#L15)