Skip to content

Conversation

@wanghaoshuang
Copy link
Contributor

  1. Remove a pooling layer.
  2. Change classes_num to 94.
  3. Modify some arguments in ctc_train.py
  4. Add learning rate decay policy.
  5. Fix readme.

root added 2 commits June 19, 2018 02:40
1. Remove a pooling layer.
2. Change classes_num to 94.
3. Modify some arguments in ctc_train.py
4. Add learning rate decay policy.
@wanghaoshuang wanghaoshuang requested a review from qingqing01 June 19, 2018 03:47
return decayed_lr


def cosine_decay(learning_rate, total_step):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Remove cosine_decay?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed.

for pass_id in range(args.pass_num):
batch_id = 1
iter_num = 0
while True:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Remove while True

@wanghaoshuang wanghaoshuang merged commit db1edc2 into PaddlePaddle:develop Jun 21, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants