Implement V2P net

Open LJQCN101 opened this issue 6 years ago • 2 comments

Implement V2P network structure according to paper "LARGE-SCALE VISUAL SPEECH RECOGNITION" (https://arxiv.org/abs/1807.05162)

Requires keras-contrib. (https://github.com/keras-team/keras-contrib)

Jun 17 '19 09:06 LJQCN101

Hi! I tried this out and had a little trouble running it,

I was wondering if you could help me!

Here is the screenshot of the error

Apr 30 '20 18:04 akouminov

Hi! I tried this out and had a little trouble running it,

I was wondering if you could help me!

Here is the screenshot of the error

Hi, according to the paper, input image size should be 128x128. Try img_w=128, img_h=128. You may want to resize the image first.

May 11 '20 08:05 LJQCN101