LipNet
LipNet copied to clipboard
rizkiarm
Keras implementation of 'LipNet: End-to-End Sentence-level Lipreading'
if self.sentence_length > 0: AttributeError: 'Curriculum' object has no attribute 'sentence_length' Epoch 0: Curriculum(train: True, sentence_length: -1, flip_probability: 0.5, jitter_probability: 0.05)
Hello everyone, today i meet a lot of problems with LipNet deploy, such as  1. Old versions of tensorflow, matplotlib, scipy and a lot of. In this case you...
Thanks @rizkiarm for sharing this great work. but I have a question please, Is there any way to use this model on real time prediction on _webcam_ camera? or it...
I just want to use the pre-trained model on the browser with Tensorflow.js... How should I do this? I appreciate any help!
- Why is the format of prediction as well for training defined as command(4) + color(4) + preposition(4) + letter(25) + digit(10) + adverb(4). - Will it work for any...
When we pass a new video to the model for prediction with pretrained weights, I guess it comes down to this part of the [code](https://github.com/rizkiarm/LipNet/blob/master/lipnet/model2.py): ./predict evaluation/models/overlapped-weights368.h5 bbaf1n.mpg def predict(self,...
ValueError: output of generator should be a tuple `(x, y, sample_weight)` or `(x, y)`. Found: None
I face following error when i train my model on unseen speaker train.py 1- TypeError: 'threadsafe_iter' object is not an iterator 2-ValueError: output of generator should be a tuple `(x,...
Video should be 360*288 2 seconds 25frame?? If Video isn't 2sec, occur problem??
it seems that this should be run on python 2, please add in read me if so
