Fixed the Todo for matching multiple anchors with the same IOU, and setting their value to 1. The previous version only picked the first anchor that had a maximum IOU. Now, if multiple anchors had the same IOU < 0.7, all of them will be set to a foreground class.

Remove unused code

Fix https://github.com/matterport/Mask_RCNN/issues/870

In current version of log(), when you pass a zero size array, it will throw an error:
`ValueError: Unknown format code 'f' for object of type 'str'`.
This PR fixes it.

pass name=None to tf.boolean_mask will lead to ValueError: At least one of name (None) and default_name (None) must be provided.

Fix the input shape of anchors in ProposalLayer and use "num_anchors" to replace "anchors" to avoid confusing

* fix comment in DetectionTargetLayer
* fix comment of target_deltas' shape
* make parenthesis compatible

skimage generates different warnings depending on the version. This wrapper function calls skimage.tranform.resize() with the right parameter for each version.

1. fix description on window
2. fix output shape of detection layer

As discussed in: https://github.com/matterport/Mask_RCNN/issues/919

1. fix the comment on output shape in fpn_classifier_graph
2. unify NUM_CLASSES and num_classes to NUM_CLASSES
3. unify boxes, num_boxes, num_rois, roi_count to num_rois
4. use more specific POOL_SIZE and MASK_ POOL_SIZE to replace pool_height and pool_width

For PyramidROIAlign's output shape, use pool_height and pool_width instead of height and width to avoid confusion with those of feature_maps.

add IMAGE_CHANNEL_COUNT class variable to config to make it easier to use Mask_RCNN for non 3-channel images

Unified regex expression for both, Linux and Windows.

- Current implementation creates self.log_dir in set_log_dir() function,
  which creates an empty log directory if none exists. This causes
  find_last() to fail after creating a model because it finds this new
  empty directory instead of the previous training directory.
- New implementation moves log_dir creation to the train() function to
  ensure it is only created when it will be used.

Add the possibility to exclude some sources from augmentation by passing a list of sources. This is useful when you want to retrain a model having few images.

Add an optional parameter for calling a list of keras.callbacks to be add to the original list.

Improve previous commit to not break on older versions of Keras.

Raise clear error if last training weights are not foundIf using the --weights=last (or --model=last) to resume trainingbut the weights are not found now it raises a clear error message.

This allows one to set a callable in Config.BACKBONE to use a custom
backbone model.

Fix matterport/Mask_RCNN#170

Print a message when re-starting from saved epoch

fix typo

Reported here: https://github.com/matterport/Mask_RCNN/pull/500

TF replaced keep_dims with keepdims a while ago
and now shows a warning when using the old name.

Although a bug, it has no practical side-effect
because it works if the masks are square, which is
the case always during training and this code is
invoked during training.

And cleaner path split in nucleus sample.