Skip to content

Added the mode "bilinear" in the upscaling2D layer. #10994

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

Merged
merged 15 commits into from
Aug 30, 2018
Merged

Added the mode "bilinear" in the upscaling2D layer. #10994

Changes from 1 commit
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
0855745
bilinear upsampling initial implementation
ahundt Feb 4, 2018
4b03e6a
bilinear interpolation docstrings added
ahundt Feb 4, 2018
b7c10bd
thano_backend.py fix bilinear interpolation ratio
ahundt Feb 5, 2018
104f209
theano_backend.py pep8 & padding fix
ahundt Feb 6, 2018
73f0311
theano_backend.py remove border_mode as per review
ahundt Feb 14, 2018
dcc9dfb
Merge branch 'bilinear_upsampling' of github.com:ahundt/keras into up…
gabrieldemarmiesse Aug 25, 2018
bd1b3b4
Added the mode "bilinear" in the upscaling2D layer. Theano only supports
gabrieldemarmiesse Aug 25, 2018
2833ee4
Added some details about what was possible with bilinear interpolation.
gabrieldemarmiesse Aug 25, 2018
8b6baf3
Made the lines shorted in the resize implementation of tensorflow.
gabrieldemarmiesse Aug 25, 2018
c4b781e
Added a more meaningful error message for bilinear and CNTK.
gabrieldemarmiesse Aug 26, 2018
9d155e2
Used ' instead of " for consistency.
gabrieldemarmiesse Aug 26, 2018
7770684
Parametrized the bilinear test.
Aug 27, 2018
2528906
Removed unused import.
Aug 27, 2018
70654da
Fix error messages.
fchollet Aug 28, 2018
dac12e9
Parametrized tests.
Aug 29, 2018
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
Prev Previous commit
Parametrized tests.
  • Loading branch information
gabrieldemarmiesse committed Aug 29, 2018
commit dac12e983c66f75cd24b8845054a108359a8df72
57 changes: 29 additions & 28 deletions tests/keras/layers/convolutional_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -864,41 +864,42 @@ def test_upsampling_2d():

@pytest.mark.skipif((K.backend() == 'cntk'),
Copy link
Collaborator

@fchollet fchollet Aug 28, 2018

Choose a reason for hiding this comment

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

Please make this test parameterized (see #10975)

reason='cntk does not support it yet')
def test_upsampling_2d_bilinear():
@pytest.mark.parametrize('data_format',
['channels_first', 'channels_last'])
def test_upsampling_2d_bilinear(data_format):
num_samples = 2
stack_size = 2
input_num_row = 11
input_num_col = 12

for data_format in ['channels_first', 'channels_last']:
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_num_row,
input_num_col)
else: # tf
inputs = np.random.rand(num_samples, input_num_row, input_num_col,
stack_size)
if data_format == 'channels_first':
inputs = np.random.rand(num_samples, stack_size, input_num_row,
input_num_col)
else: # tf
inputs = np.random.rand(num_samples, input_num_row, input_num_col,
stack_size)

# basic test
layer_test(convolutional.UpSampling2D,
kwargs={'size': (2, 2),
'data_format': data_format,
'interpolation': 'bilinear'},
input_shape=inputs.shape)
# basic test
layer_test(convolutional.UpSampling2D,
kwargs={'size': (2, 2),
'data_format': data_format,
'interpolation': 'bilinear'},
input_shape=inputs.shape)

for length_row in [2]:
for length_col in [2, 3]:
layer = convolutional.UpSampling2D(
size=(length_row, length_col),
data_format=data_format)
layer.build(inputs.shape)
outputs = layer(K.variable(inputs))
np_output = K.eval(outputs)
if data_format == 'channels_first':
assert np_output.shape[2] == length_row * input_num_row
assert np_output.shape[3] == length_col * input_num_col
else: # tf
assert np_output.shape[1] == length_row * input_num_row
assert np_output.shape[2] == length_col * input_num_col
for length_row in [2]:
for length_col in [2, 3]:
layer = convolutional.UpSampling2D(
size=(length_row, length_col),
data_format=data_format)
layer.build(inputs.shape)
outputs = layer(K.variable(inputs))
np_output = K.eval(outputs)
if data_format == 'channels_first':
assert np_output.shape[2] == length_row * input_num_row
assert np_output.shape[3] == length_col * input_num_col
else: # tf
assert np_output.shape[1] == length_row * input_num_row
assert np_output.shape[2] == length_col * input_num_col


@pytest.mark.skipif((K.backend() == 'cntk'),
Expand Down