-
Notifications
You must be signed in to change notification settings - Fork 1.6k
Closed
Labels
Description
-
Discuss in Slack (invited link)
-
Docs
- installation
- layers
- the links in https://github.com/tensorlayer/awesome-tensorlayer
- https://tensorlayer.readthedocs.io/en/2.0.0/user/examples.html
- https://tensorlayer.readthedocs.io/en/latest/modules/layers.html#batch-normalization batchnorm1d 2d 3d should be separated Rundi
- others
-
Layer
- Activation
actsupports string inputs e.g.,Dense(100, act='relu')Ruihai - RNN
cellsupports string inputs e.g.,cell_fn='LSTM') - Remove
as_layer() - Quantized layers should be refactored
- tl.optimizers should be refactored
- Optimize the `build' of core layer
- InstanceNorm 1d 2d 3d should be implemented Yingda
- automatically deal with
in_channels:
super(MyLayer, self).__init__(name, in_channel=in_channel) - refactor QuanConv2dWithBN and etc
- Remove below codes in layers
- Activation
self.build()
self._built = True
-
Model
- Fix model core
_construct_graphBFS. @ChrisWu1997 - Add callback features for specific layer output. @ChrisWu1997
- Fix model core
-
Visualize
- tl.vis.save_images if input is a tensor, run x.numpy() automatically.
-
Examples (Tutorial)
-
text_generation
-
text_ptb
-
database [WIP] @ChrisWu1997
-
distributed_training
-
Initializer
-
Other Examples
- https://github.com/tensorlayer/srgan
- https://github.com/tensorlayer/openpose-plus
- https://github.com/tensorlayer/adaptive-style-transfer
- https://github.com/tensorlayer/seq2seq-chatbot
- more in https://github.com/tensorlayer/awesome-tensorlayer
-
Next step
- PointCNN
- RL - ray/rllib