Closed ArnoldLIULJ closed 5 years ago
Update the model with deeper structure n_units->256, n_layers->3(for both encoding and decoding)
FIX multilayer RNN bugs. states propagation. ADD inference test
PACK multiple layers into a list layers with self-defined layers CHANGE batch_size to decoder_length ADD top_n method at inference time
Update model compatible with TensorLayer2.0. Rewrite the loss. cross_entropy_seq_with_mask and cross_entropy_seq. Need to run to see if it converges and produce desirable results