Skip to content

Release 1.3.2
Compare
Choose a tag to compare
@zsdonghao zsdonghao released this 19 Jan 11:29
· 2661 commits to master since this release
1.3.2
a17229d

Recommended Update !

This is an incomplete list among the many features added.

  • Support
    • new function for file: maybe_download_or_extract by @JoelKronander
    • new layers: ExpandDimsLayer and TileLayer by @zsdonghao
    • new layer: Seq2Seq by @zsdonghao
    • new prepro functions for NLP: precess_sequences, sequences_add_start_id and sequences_get_mask by @zsdonghao
    • new prepro function for image drop by @zsdonghao
  • Update
    • tutorial_cifar10_tfrecord.py for TF12 by @JoelKronander
    • read_words for Python3.5 by @SmartAILM
    • Add path argument for tl.file.load* by @boscotsang
  • Call for Contribution
    • Seq2Seq: PeekySeq2Seq and AttentionSeq2Seq, click here
    • Import Caffe model into TensorLayer, click here
    • End-to-End Memory Network tutorial, click here
  • New Examples
    • U-Net: Convolutional Networks for Image Segmentation
    • Text-to-Image Synthesis with GAN

This version works well under TF 0.10 and 0.11 backend, it also works well with TF 0.12 in most of the case, feel free to report if you found a bug. Many thanks!

Assets 2
Loading