name: b) New feature
about: Select this if you're adding a new feature to libra.
labels: feature
This pull request closes #267
**- Supporting different model architectures for CNNs
**- Added architecture parameter to convolutional_query() in queries.py and convolutional() in feedforward_nn.py,
If architecture is not None, model is initialized with this architecture. By default, weights are randomly initialized. Can later add a a parameter on whether to include pretrained imagenet weights.
- How to verify it
[ ] I updated the docs.
This pull request adds a new feature to libra. @Palashio, could you please take a look at it?
name: b) New feature about: Select this if you're adding a new feature to libra. labels: feature
This pull request closes #267
**- Supporting different model architectures for CNNs
**- Added architecture parameter to convolutional_query() in queries.py and convolutional() in feedforward_nn.py, If architecture is not None, model is initialized with this architecture. By default, weights are randomly initialized. Can later add a a parameter on whether to include pretrained imagenet weights.
- How to verify it
This pull request adds a new feature to libra. @Palashio, could you please take a look at it?