Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
README.md | 2019-09-13 | 1.7 kB | |
TensorLayer 2.2.0 source code.tar.gz | 2019-09-13 | 5.0 MB | |
TensorLayer 2.2.0 source code.zip | 2019-09-13 | 5.3 MB | |
Totals: 3 Items | 10.3 MB | 0 |
TensorLayer 2.2.0 is a maintenance release. It contains numerous API improvement and bug fixes. This release is compatible with TensorFlow 2 RC1.
Added
- Support nested layer customization (#PR 1015)
- Support string dtype in InputLayer (#PR 1017)
- Support Dynamic RNN in RNN (#PR 1023)
- Add ResNet50 static model (#PR 1030)
- Add performance test code for static models (#PR 1041)
Changed
SpatialTransform2dAffine
autoin_channels
- support TensorFlow 2.0.0-rc1
- Update model weights property, now returns its copy (#PR 1010)
Fixed
- RNN updates: remove warnings, fix if seq_len=0, unitest (#PR 1033)
- BN updates: fix BatchNorm1d for 2D data, refactored (#PR 1040)
Dependencies Update
Deprecated
Fixed
- Fix
tf.models.Model._construct_graph
for list of outputs, e.g. STN case (PR [#1010]) - Enable better
in_channels
exception raise. (PR [#1015]) - Set allow_pickle=True in np.load() (#PR 1021)
- Remove
private_method
decorator (#PR 1025) - Copy original model's
trainable_weights
andnontrainable_weights
when initializingModelLayer
(#PR 1026) - Copy original model's
trainable_weights
andnontrainable_weights
when initializingLayerList
(#PR 1029) - Remove redundant parts in
model.all_layers
(#PR 1029) - Replace
tf.image.resize_image_with_crop_or_pad
withtf.image.resize_with_crop_or_pad
(#PR 1032) - Fix a bug in
ResNet50
static model (#PR 1041)
Removed
Security
Contributors
- @zsdonghao
- @luomai
- @ChrisWu1997: [#1010] [#1015] [#1025] [#1030] [#1040]
- @warshallrho: [#1017] [#1021] [#1026] [#1029] [#1032] [#1041]
- @ArnoldLIULJ: [#1023]
- @JingqingZ: [#1023]