提交 aa39ca8d 编写于 作者: Y Yu Yang 提交者: GitHub

Merge pull request #1868 from PaddlePaddle/luotao1-patch-1

Update RELEASE.md
# Release v0.10.0
## New Features
* Support rectangle input for CNN.
* Support stride pooling for seqlastin and seqfirstin.
* Expose seq_concat_layer/seq_reshape_layer in `trainer_config_helpers`.
## Improvements
* Speedup the backward of average layer on GPU.
* Reorganize the catalog of doc/ and refine several docs.
* Add Travis-CI for checking dead links.
* Add a example for explaining sparse_vector.
* Add Relu in layer_math.py
## Bug Fixes
* Add layer check for recurrent_group.
* Clang-format off on some cuda .cc files.
* Fix LogActivation which is not defined.
* Fix bug when run test_layerHelpers multiple times.
* Fix protobuf size limit on seq2seq demo.
# Release v0.9.0 # Release v0.9.0
## New Features: ## New Features:
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册