Skip to content

AE: check lens of stride and channel match #1372

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
wyli merged 3 commits into from
Dec 16, 2020
Merged

AE: check lens of stride and channel match #1372

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f8570b5
AE: check lens of stride and channel match
rijobro Dec 16, 2020
2f440df
Merge branch 'master' into check_AE_chan_stride
rijobro Dec 16, 2020
9008352
[MONAI] python code formatting
monai-bot Dec 16, 2020
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
4 changes: 4 additions & 0 deletions monai/networks/nets/autoencoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,10 @@ def __init__(
self.inter_channels = inter_channels if inter_channels is not None else list()
self.inter_dilations = list(inter_dilations or [1] * len(self.inter_channels))

# The number of channels and strides should match
if len(channels) != len(strides):
raise ValueError("Autoencoder expects matching number of channels and strides")

self.encoded_channels = in_channels
decode_channel_list = list(channels[-2::-1]) + [out_channels]

Expand Down
13 changes: 13 additions & 0 deletions tests/test_autoencoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,15 @@
CASES = [TEST_CASE_0, TEST_CASE_1, TEST_CASE_2, TEST_CASE_3]


TEST_CASE_FAIL = { # 2-channel 2D, should fail because of stride/channel mismatch.
"dimensions": 2,
"in_channels": 2,
"out_channels": 2,
"channels": (4, 8, 16),
"strides": (2, 2),
}


class TestAutoEncoder(unittest.TestCase):
@parameterized.expand(CASES)
def test_shape(self, input_param, input_shape, expected_shape):
Expand All @@ -76,6 +85,10 @@ def test_script(self):
test_data = torch.randn(2, 1, 32, 32)
test_script_save(net, test_data)

def test_channel_stride_difference(self):
with self.assertRaises(ValueError):
net = AutoEncoder(**TEST_CASE_FAIL)


if __name__ == "__main__":
unittest.main()