Jakub

*added a tutorial/evaluation post about Scikit-Optimize library for hyperparameter optimization

* added a link to a post about 24 evaluation metrics for binary classification

* added a link to downloadable pdf with 24 binary classification metrics

when training finishes it hits the memory error

2

Running train crashes when the pipelines are collating results from running transform on the entire dataset.

Multipath Refinenet from this papar https://arxiv.org/abs/1611.06612 Example implementation here https://github.com/thomasjpfan/pytorch_refinenet/blob/master/pytorch_refinenet/refinenet/refinenet_4cascade.py

This and some other architectures implemented here: https://github.com/zijundeng/pytorch-semantic-segmentation

Distance loader does ```python Di = self.load_joblib(distance_filepath) Di = Di.astype(np.uint8) Si = self.load_joblib(size_filepath).astype(np.uint16) Si = np.sqrt(Si).astype(np.uint16) ``` This should have been done at creation of Di and Si not here...

MulticlassLabeler returns different shapes

1

MulticlassLabeler usually (almost always) returns: `(2,300,300)` but sometimes you get `(1,300,300)` which of course causes trouble. It happens because of the `mask.max()` in the following implementation. ``` def label_multiclass_image(mask): labeled_channels...