search

mpc001 / end-to-end-lipreading

Pytorch code for End-to-End Audiovisual Speech Recognition
173 stars 51 forks source link

About the ResNet ! #15

Open CXiaoDing opened 5 years ago

CXiaoDing commented 5 years ago

@mpc001 Thank you for your code ! I want to run your code, and I found that in your code , you write the ResNet34 yourself while the Pytorch provide the pretrained ResNet34. I want to know is there any diffirences between your written ResNet34 and the provided ResNet34 by Pytorch? Thank you very much!

mpc001 commented 5 years ago

Hi,

We replaced the first layer of ResNet34 with 3D convolutions to capture local temporal dynamics.

CXiaoDing commented 5 years ago

Thank you! Could you please tell me how many epochs did each state take respectively？