Why use ResLSTM for Offline Handwritten Chinese Text Recognition ?
ivoxx opened this issue · comments
Nice work!
I found this network architecture
(126,576)Input − 8C3 − MP2 − 32C3 − MP2 − 128C3 − MP2−5∗256C3−MP2−512C3−512C3−MP2−512C2− 3 ∗ 512ResLSTM − 7357F C − Output
in the paper for Handwritten Chinese Text Recognition.
Is it necessary for Chinese Text Recognition ?
@ivoxx Hi, I just have the same confusion, could you share your insights or comparing results? Thanks