f3c5b75e59717c017fa3779b3f29b725e4ac6d9b,tests/test_retina.py,,main,#,38
Before Change
imgs.append(torch.from_numpy(img))
imgs = Variable(torch.cat(imgs))
loc = Variable(torch.Tensor([[0., 0.], [0., 0.]]))
if TEST_GLIMPSE:
After Change
imgs = Variable(torch.cat(imgs))
loc = torch.Tensor(2, 2).uniform_(-1, 1)
loc = Variable(loc)
if TEST_GLIMPSE:
ret = retina(g=64, k=3, s=2)
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 3
Instances
Project Name: kevinzakka/recurrent-visual-attention
Commit Name: f3c5b75e59717c017fa3779b3f29b725e4ac6d9b
Time: 2018-01-24
Author: kevinarmandzakka@gmail.com
File Name: tests/test_retina.py
Class Name:
Method Name: main
Project Name: kevinzakka/recurrent-visual-attention
Commit Name: ec6113b96d65d4edb3da8aac88796bbd99fc9478
Time: 2018-01-22
Author: kevinarmandzakka@gmail.com
File Name: trainer.py
Class Name: Trainer
Method Name: train_one_epoch
Project Name: THUNLP-MT/THUMT
Commit Name: 4a471fc393aefa3c5c8e6670a900f93d6ba760cd
Time: 2018-04-08
Author: playinf@stu.xmu.edu.cn
File Name: thumt/utils/optimize.py
Class Name:
Method Name: create_train_op