杜渺

where to find the dataset, would you provide a download link?

because the best path decode method is not work well in long term , please change another ctc decode method

you can try Prefix Search Decoding or other decoding method.

[Here is my implement](https://github.com/sequence-labeling/transducer_greed_decoder) for greed decoder. you may need some change for your lstm decoder network.

I have used your MDLSTM code in your stackoverflow answer. But it seems not converge in my task. Have you test successfully in your task ?

@johnsmithm Is this right? ``` w,h = int(shape[1]/sh[0]),int(shape[2]/sh[1]) features = sh[1]*sh[0]*shape[3] batch_size = shape[0] x = tf.reshape(input_data, [batch_size,h,w, features]) ``` I know MDLSTM need input to split to blocks, But...

Good, have you test it in your image task? If you test it successfully, please tell me.

I haven't found a mdlstm of tensorflow version work well so far, I hope it works! And I will test it also.