search

rizkiarm / LipNet

Keras implementation of 'LipNet: End-to-End Sentence-level Lipreading'
MIT License
628 stars 224 forks source link

What is the significance of the parameters in train(run_name, 0, 5000, 3, 100, 50, 75, 32, 50). #53

Closed kpkool1995 closed 6 years ago

kpkool1995 commented 6 years ago

Hi All, Can someone point out what is the significance of the parameters in train(run_name, 0, 5000, 3, 100, 50, 75, 32, 50) training/unseen_speakers/train.py.

Thanks in advance :)

kokosowygosc commented 6 years ago

train(run_name, start_epoch, stop_epoch, img_c, img_w, img_h, frames_n, absolute_max_string_len, minibatch_size) :)

rizkiarm commented 6 years ago

I will close this issue. Please re-open the issue (or create a new one) if you have some more problems.

kpkool1995 commented 6 years ago

Hey, Reopening the issue and rephrasing my question further. What is the significance of parameters in train(run_name, 0, 5000, 3, 100, 50, 75, 32, 50). I meant if I need my own training videos, what these parameters would be?

Thanks for the reply, hope I will get the apt reply this time.

rizkiarm commented 6 years ago

Please read https://github.com/rizkiarm/LipNet#prerequisites, and specify the properties of your new training dataset to the train method according to this specification:

train(run_name, start_epoch, stop_epoch, img_c, img_w, img_h, frames_n, absolute_max_string_len, minibatch_size)