Closed bryanlimy closed 4 months ago
Click to see where and how coverage changed
File Statements Missing Coverage Coverage
(new stmts)Lines missing
autoemulate/emulators
neural_net_torch.py
autoemulate/emulators/neural_networks
base.py
32
cnn1d.py
60-84
get_module.py
18
mlp.py
rbf.py
16, 20, 24, 28, 32, 36, 112-133, 137-168, 192-201, 222-252, 257, 262, 267, 286-303, 306, 311-333, 336
tests
test_emulators.py
Project Total
This report was generated by python-coverage-comment-action
Attention: 77 lines
in your changes are missing coverage. Please review.
Comparison is base (
31c040c
) 90.26% compared to head (4b1474a
) 87.21%. Report is 3 commits behind head on main.
:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.
RBF is added here https://github.com/alan-turing-institute/autoemulate/pull/180, closing this PR for now and will open a new one for multi-dimension input
RFBModule
from https://github.com/rssalessio/PytorchRBFLayer/tree/mainCNN1dModule
which accept 2-dimensional inputsTorchModule
has to implement functioncheck_input_size
to ensure the input dimension suit the specific model.MLPModule
doesn't accept 2d input andCNN1d
doesn't accept 1d input.module.input_size
is always store as a tuple for consistencyTorchModule
einops
for Einstein-like operations for NumPy and PyTorchaddress https://github.com/alan-turing-institute/autoemulate/issues/165 and https://github.com/alan-turing-institute/autoemulate/issues/160