Skip to content
This repository has been archived by the owner on Oct 13, 2021. It is now read-only.

v1.5.0
Compare
Choose a tag to compare
@vinitra-zz vinitra-zz released this 10 Jun 23:12
· 339 commits to master since this release
v1.5.0
9bb6773
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

keras2onnx version 1.5.0 is now available! This version features ONNX Opset 10 support, compatibility with conversion of state-of-the-art object detection models (YoloV3), and increased test coverage.

How do I use the latest keras2onnx package?

pip install keras2onnx --upgrade
python -c "import keras2onnx"

Note: keras2onnx has been tested with Python 3.5, 3.6, and 3.7. It does not currently support Python 2.x.

Highlights since the last release

  • Updating package version to 1.5.0 (#113)
  • Add OnnxOperatorBuilder (#112)
  • Handle multiple dimensions case for BatchNormalization (#110, #106, #104)
  • Improving test coverage + documentation (#109, #107, #100, #99, #79, #72, #70)
  • Enable the dynamic batch size for the converted model (#93)
  • Bug fixes / Conversion Updates
    • Bug fix in forward and bi-directional LSTM in handling bias (#103)
    • Clean up StridedSlice opset 9 (#73)
    • Fix softmax activation in conv and dense (#69)
    • Address interpolation attribute for Keras Upsampling2D (#101)
    • Fix bidirectional output_seq=False case (#85)
  • CI Build Updates
    • keras-onnx CI support for ONNX 1.5, Python 3.7 (#78)
    • Add CI build for keras applications (#66)
    • Work around conda permission issue in linux (#102)
  • Opset 10 updates
    • Updating ThresholdedRelu and onnxconverter-common package (#96)
    • Convert Upsample using Resize op (#59)
    • Update StridedSlice (#61)
Assets 2
Loading