ONNX v1.9.0 is now available with exciting new features! We would like to thank everyone who contributed to this release!
You may learn more about the project, who is involved and what tools are available at the onnx.ai site.

Key Updates

• Removed Optimizers from ONNX packages #3288
• Selective schema loading by specific opset_version #3266
• Updates to external data helpers (more options to control which attributes are converted to external data and whether a model should be saved) #3280
• New adapter for opset version converter #3343

Opset version 14

• New operator:
  • HardSwish #3332
  • Trilu #3291
• Extended supported types to include uint8, int8, uint16, and int16. #3334
  • Add
  • Div
  • Mul
  • Sub
• Added allowzero attribute to Reshape operator #3113
• Allowed recurrent operations to be batchwise #3217
  • GRU
  • LSTM
  • RNN
• Expanded CumSum to float16 and bfloat16 data types #3195
• Expanded Relu to all signed data types #3141
• Added training-mode support to BatchNorm #3333

API

• onnx.OnnxParser Parser for a textual syntax of ONNX models #3194

Infrastructure

• Removed Python 3.5 in all release pipelines #3353
• Added Python 3.9 to all release pipelines #3352
• Added weekly CI: provide ONNX TestPyPI packages for verification #3283
• Reduced binary size for Linux and Mac package #3337
• Added check for uploaded/generated backend test data in release CIs #3274
• Enabled no exception build and updated exception handling for DataTypeUtils #3265

Bug fixes

• Added missing test for ConvInteger without padding #3288
• Updated Resize op test to opset 13 #3361
• Expanded ir_pb_converter to empty shape #3279

Installation

You can simply pip upgrade using the pip install onnx --upgrade or build from source following the instructions on Github.

Notes

• Be aware of protobuf version gap issue (like building onnx with protobuf>=3.12 is not compatible with older protobuf)

Contributors

Thanks to these individuals for their contributions in this release:
@jcwchen, @askhade, @postrational, @etusien, @wschin, @prasanthpul, @gramalingam, @daquexian, @BowenBao,
@pranav-prakash, @matteosal, @linkerzhang, @annajung, @neginraoof, @tianleiwu, @tomdol