Closed wkhunter closed 6 years ago
The number of hidden layers may impact the performance of a model with a large number of output characters. However, strictly speaking it is only the value of the parameter num_classes
to model.rnn_layers
that needs to be changed to control the output layer's dimensionality.
OK, I changed model-crnn to Resnet and problem solved!
Layer Op KrnSz Stride(v,h) OutDim H W PadOpt 1 Conv 3 1 64 30 30 valid 2 Conv 3 1 64 30 30 same Pool 2 2 64 15 15
3 Conv 3 1 128 15 15 same 4 Conv 3 1 128 15 15 same Pool 2 2,1 128 7 14
5 Conv 3 1 256 7 14 same 6 Conv 3 1 256 7 14 same Pool 2 2,1 256 3 13
7 Conv 3 1 512 3 13 same 8 Conv 3 1 512 3 13 same Pool 3 3,1 512 1 13
9 LSTM 512
10 LSTM 512
if I want to train more than 3000+ chars, how to modify the model. cnn layer more deeper, change to maxpooling layer or what?