Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixed incorrect tensor size annotation #262

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fixed incorrect tensor size annotation #262

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions models/crnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,20 +45,20 @@ def convRelu(i, batchNormalization=False):
nn.LeakyReLU(0.2, inplace=True))
else:
cnn.add_module('relu{0}'.format(i), nn.ReLU(True))

#if input: nc x 32 x 128
convRelu(0)
cnn.add_module('pooling{0}'.format(0), nn.MaxPool2d(2, 2)) # 64x16x64
convRelu(1)
cnn.add_module('pooling{0}'.format(1), nn.MaxPool2d(2, 2)) # 128x8x32
convRelu(2, True)
convRelu(3)
cnn.add_module('pooling{0}'.format(2),
nn.MaxPool2d((2, 2), (2, 1), (0, 1))) # 256x4x16
nn.MaxPool2d((2, 2), (2, 1), (0, 1))) # 256x4x17
convRelu(4, True)
convRelu(5)
cnn.add_module('pooling{0}'.format(3),
nn.MaxPool2d((2, 2), (2, 1), (0, 1))) # 512x2x16
convRelu(6, True) # 512x1x16
nn.MaxPool2d((2, 2), (2, 1), (0, 1))) # 512x2x18
convRelu(6, True) # 512x1x17

self.cnn = cnn
self.rnn = nn.Sequential(
Expand Down