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

Attempt to infer the output shape for Deconvolution2D layer #4

Open
wants to merge 15 commits into
base: master
Choose a base branch
from
Open

Attempt to infer the output shape for Deconvolution2D layer #4

Changes from 1 commit
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
c797487
ENH: Infer output shape for Deconvolution2D
Jul 24, 2016
111060f
BUG: Tensor doesn't have 'shape' property, using K.shape() instead
lukovkin Jul 24, 2016
ab29be6
BUG: Fix subsample index for cols
Jul 24, 2016
b654a2a
BUG: Fix subsample index for cols
Jul 24, 2016
fcc1908
BUG: Fix subsample index for cols
Jul 24, 2016
af03021
Merge branch 'master' of https://github.com/lukovkin/keras
Jul 24, 2016
26b9c44
ENH: Update Deconvolution2D test case in order to test w and w/o outp…
Jul 24, 2016
01fda37
ENH: Update Deconvolution2D test case in order to test w and w/o outp…
lukovkin Jul 24, 2016
c117361
Merge branch 'master' of https://github.com/lukovkin/keras
Jul 24, 2016
4818bff
Merge branch 'master' of https://github.com/yaringal/keras into yarin…
lukovkin Jul 24, 2016
463a550
DOC: Reference for Deconvolution2D added
lukovkin Jul 24, 2016
9ffce28
ENH: Filter rows and cols as variables in Deconvolution2D test case
lukovkin Jul 24, 2016
5d00fb7
Create dummy
lukovkin Jul 25, 2016
5a606c6
BUG: Possible non-compliance between filter_shape passed as a paramet…
lukovkin Jul 25, 2016
810ca65
BUG: Fixed output_shape elements evaluation
lukovkin Jul 25, 2016
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
10 changes: 9 additions & 1 deletion keras/backend/theano_backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1052,7 +1052,15 @@ def deconv2d(x, kernel, output_shape, strides=(1, 1),
kernel = kernel.dimshuffle((1, 0, 2, 3))
th_border_mode = _preprocess_border_mode(border_mode)
np_kernel = kernel.eval()
filter_shape = _preprocess_filter_shape(dim_ordering, filter_shape)
filter_shape = _preprocess_filter_shape(dim_ordering, shape(kernel))
Copy link
Author

Choose a reason for hiding this comment

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

I think there was a kind of inconsistency here - we receive the filter_shape as a parameter, after that we reshape the kernel itself (shape should change) but leave filter_shape intact and pass it to the AbstractConv2d_gradInputs then.

Probably we could totally remove filter_shape from the parameters, if there are no other reasons to use it.


for v in output_shape:
try:
v = v.eval()
except AttributeError as e:
print(e.__str__())

print("imshp {} kshp {} subsample {} border_mode {} output_shape {}".format(output_shape, filter_shape, strides, th_border_mode, output_shape[2:]))

op = T.nnet.abstract_conv.AbstractConv2d_gradInputs(imshp=output_shape,
kshp=filter_shape,
Expand Down