Skip to content

Instantly share code, notes, and snippets.

@soumith
Created April 18, 2018 18:52
Show Gist options
  • Save soumith/3494c1b60efc6c2e6efba1318839bd3b to your computer and use it in GitHub Desktop.
Save soumith/3494c1b60efc6c2e6efba1318839bd3b to your computer and use it in GitHub Desktop.
https://github.com/pytorch/pytorch/pull/6651 Export onnx protobuf bindings to python
https://github.com/pytorch/pytorch/pull/6574 Follow the change of ONNX Cast operator "to" attribute
https://github.com/pytorch/pytorch/pull/6560 Create CODEOWNERS entry for torch/onnx
https://github.com/pytorch/pytorch/pull/6331 Fix the c2-onnx exporter bug on Gemm
https://github.com/pytorch/pytorch/pull/6243 fix broadcast export to onnx
https://github.com/pytorch/pytorch/pull/6220 Support export torch.max(input, dim) and torch.min(input, dim) to ONNX
https://github.com/pytorch/pytorch/pull/6101 Fix a bug in ONNX symbolic of average 3d pooling op
https://github.com/pytorch/pytorch/pull/6016 Experimental support for different ONNX export types
https://github.com/pytorch/pytorch/pull/5972 Update no_unions flag for nanopb gen and update ONNX proto files
https://github.com/pytorch/pytorch/pull/5935 Specify outputs number in embedding_bag onnx export
https://github.com/pytorch/pytorch/pull/5759 Add symbolic for relu to support exporting to ONNX
https://github.com/pytorch/pytorch/pull/5753 bugfix in onnx export of batch_first = True
https://github.com/pytorch/pytorch/pull/5734 add some onnx exported supports
https://github.com/pytorch/pytorch/pull/5654 Add missing ONNX symbolics and fix fusible expand logic
https://github.com/pytorch/pytorch/pull/5652 Print source location when ONNX export fails for a node
https://github.com/pytorch/pytorch/pull/5639 rename onnx/utils/__init__.py -> onnx/utils.py
https://github.com/pytorch/pytorch/pull/5360 support batch-first in ONNX export of padded sequences
https://github.com/pytorch/pytorch/pull/5359 add a third output in LSTM onnx export
https://github.com/pytorch/pytorch/pull/5120 Bidirectional Elman RNN export to ONNX
https://github.com/pytorch/pytorch/pull/4695 Handle sequence lengths correctly when exporting RNNs to ONNX
https://github.com/pytorch/pytorch/pull/4626 Add onnx support for InstanceNorm
https://github.com/pytorch/pytorch/pull/4613 add Elman RNN export to ONNX
https://github.com/pytorch/pytorch/pull/4592 Add more check on softmax ONNX exporting logic
https://github.com/pytorch/pytorch/pull/4583 Support output_padding in ConvTranspose while doing ONNX exporting
https://github.com/pytorch/pytorch/pull/4579 [ONNX] export sum, prod, sqrt improve log_softmax.
https://github.com/pytorch/pytorch/pull/4524 Fix tracking of tracing scopes during ONNX pass
https://github.com/pytorch/pytorch/pull/4471 Hot patch ONNX _run_symbolic_function
https://github.com/pytorch/pytorch/pull/4446 Fix _trace function in torch.onnx (clean up of #4436)
https://github.com/pytorch/pytorch/pull/4390 support GRU export to ONNX
https://github.com/pytorch/pytorch/pull/4263 Fix onnx export of replication/reflection pad
https://github.com/pytorch/pytorch/pull/4014 Fix segfault during ONNX export
https://github.com/pytorch/pytorch/pull/4004 Make pool export compliant with onnx spec
https://github.com/pytorch/pytorch/pull/3977 Add more ONNX symbolics
https://github.com/pytorch/pytorch/pull/3957 ONNX updates
https://github.com/pytorch/pytorch/pull/3956 Add ONNX symbolics for several ops
https://github.com/pytorch/pytorch/pull/3913 Fix exporting HalfTensor to ONNX
https://github.com/pytorch/pytorch/pull/3889 Fix padding according to https://github.com/onnx/onnx/issues/261
https://github.com/pytorch/pytorch/pull/3708 Fix export for recent changes in ONNX
https://github.com/pytorch/pytorch/pull/3698 Remove dilations for pooling in onnx export and other small fixes
https://github.com/pytorch/pytorch/pull/3691 Hotfix for ONNX BatchNorm export
https://github.com/pytorch/pytorch/pull/3484 Update ONNX IR we emit to version 0.0.2 (attribute discriminators) / fix Permute export
https://github.com/pytorch/pytorch/pull/3453 Add ONNX symbolic for Elu
https://github.com/pytorch/pytorch/pull/3450 Add ONNX symbolic for UpsamplingNearest2d
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment