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

Fixed comment on GPU_COUNT

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

config.IMAGE_RESIZE_MODE = "crop" can be used in
training only to pick random crops from training
images.

This is useful to run prediction on images of
variable sizes without resizing them to a fixed
size. While using mode=“none” is another option,
it requires that you pre-process your images to
ensure the width and height are multiples of 64.
This mode handles that automatically.

* create package mrcnn
* move notebooks to samples

A step towards supporting detection on different
image sizes.

This doesn’t change the functionality, other than
cleaning up the code to prepare for future changes
to support detection on different image sizes.

Allows using a config variable, TRAIN_NB, rather
that updating the BatchNorm class.

* Remove dropout layer. Unnecessary.
* Reduce anchor stride from 2 to 1
* Increase training proposals to 200/image
* Reduce pre-NMS limit to 6000
* Improve computing proposal post:neg ratio
* Updated COCO training schedule

Reduces odds of weight explosion.