Keras v2.2.5 Release Notes
Release Date: 2019-08-22 // over 4 years ago-
๐ Keras 2.2.5 is the last release of Keras that implements the 2.2.* API. It is the last release to only support TensorFlow 1 (as well as Theano and CNTK).
๐ The next release will be 2.3.0, which makes significant API changes and add support for TensorFlow 2.0. The 2.3.0 release will be the last major release of multi-backend Keras. Multi-backend Keras is superseded by
tf.keras
.๐ At this time, we recommend that Keras users who use multi-backend Keras with the TensorFlow backend switch to
tf.keras
in TensorFlow 2.0.tf.keras
is better maintained and has better integration with TensorFlow features.API Changes
- โ Add new Applications:
ResNet101
,ResNet152
,ResNet50V2
,ResNet101V2
,ResNet152V2
. - Callbacks: enable callbacks to be passed in
evaluate
andpredict
.- Add
callbacks
argument (list of callback instances) inevaluate
andpredict
. - Add callback methods
on_train_batch_begin
,on_train_batch_end
,on_test_batch_begin
,on_test_batch_end
,on_predict_batch_begin
,on_predict_batch_end
, as well ason_test_begin
,on_test_end
,on_predict_begin
,on_predict_end
. Methodson_batch_begin
andon_batch_end
are now aliases foron_train_batch_begin
andon_train_batch_end
.
- Add
- Allow file pointers in
save_model
andload_model
(in place of the filepath) - โ Add
name
argument in Sequential constructor - Add
validation_freq
argument infit
, controlling the frequency of validation (e.g. settingvalidation_freq=3
would run validation every 3 epochs) - ๐ Allow Python generators (or Keras Sequence objects) to be passed in
fit
,evaluate
, andpredict
, instead of having to use*_generator
methods.- Add generator-related arguments
max_queue_size
,workers
,use_multiprocessing
to these methods.
- Add generator-related arguments
- โ Add
dilation_rate
argument in layerDepthwiseConv2D
. - MaxNorm constraint: rename argument
m
tomax_value
. - โ Add
dtype
argument in base layer (default dtype for layer's weights). - Add Google Cloud Storage support for model.save_weights and model.load_weights.
- โ Add JSON-serialization to the
Tokenizer
class. - Add
H5Dict
andmodel_to_dot
to utils. - ๐ Allow default Keras path to be specified at startup via environment variable KERAS_HOME.
- Add arguments
expand_nested
,dpi
toplot_model
. - โ Add
update_sub
,stack
,cumsum
,cumprod
,foldl
,foldr
to CNTK backend - Add
merge_repeated
argument toctc_decode
in TensorFlow backend
๐ Thanks to the 89 committers who contributed code to this release!
- โ Add new Applications: