SWaltmann issues

Repositories
Issues
Comments

Results 2 issues of


                                            SWaltmann

Validation is done using the test set

In model.py, the train method of EfficientCapsNet includes the following line: [dataset_train, dataset_val = dataset.get_tf_data() ](https://github.com/EscVM/Efficient-CapsNet/blob/4b337f5bf79d70a56e4dec8b113fe54b44cfe963/models/model.py#L158) However, get_tf_data() simply calls [generate_tf_data()](https://github.com/EscVM/Efficient-CapsNet/blob/4b337f5bf79d70a56e4dec8b113fe54b44cfe963/utils/pre_process_smallnorb.py#L72), which augments and returns the **test dataset**. Was this...

Placement of EM Routing in the architecture

Hi, I was wondering why the EM routing happens after the ConvCaps and ClassCaps layer. This is consistent with the implementation of Hinton et al. (that have released their code...