You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
, the HSNLayer modules are checked to be instances of torch.nn.Conv2d. However, none of them are, since the layer consists of only Aggregation (from topomodelx.base.aggregation) and Conv from (topomodelx.base.conv).
Thus, the test will be passed without actually checking the parameter reset.
(The test itself is incorrect: after resetting, the parameters of a torch.nn.Conv2d layer are compared to zeros
Hi!
In
test_reset_parameters()
TopoModelX/test/nn/simplicial/test_hsn_layer.py
Line 34 in ed4bd96
HSNLayer
modules are checked to be instances oftorch.nn.Conv2d
. However, none of them are, since the layer consists of onlyAggregation
(fromtopomodelx.base.aggregation
) andConv
from (topomodelx.base.conv
).Thus, the test will be passed without actually checking the parameter reset.
(The test itself is incorrect: after resetting, the parameters of a
torch.nn.Conv2d
layer are compared to zerosTopoModelX/test/nn/simplicial/test_hsn_layer.py
Line 36 in ed4bd96
The text was updated successfully, but these errors were encountered: