Release v1.0.0b1 (tf.keras) (qubvel#162)

* Support for keras and tf.keras
* Focal loss; precision and recall metrics
* New losses and metrics functionality: aggregation and multiplication by factor
* NCHW and NHWC support
* Removed pure `tf` operations to work with other keras backends
* Reduced a number of custom objects for better models serialization and deserialization

Release/v0.2.1 (qubvel#107)

 - Added `set_regularization` function  
 - Added `beta` argument to dice loss  
 - Added `threshold` argument for metrics  
 - Fixed `prerprocess_input` for mobilenets  
 - Fixed missing parameter `interpolation` in `ResizeImage` layer config  
 - Some minor improvements in docs, fixed typos

Merge pull request qubvel#53 from qubvel/release

Release 0.2.0

Merge branch 'release'

release 0.1.1

pip package