Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

assertion fails when exporting to onnx #16895

Closed
rajarsheem opened this issue Feb 8, 2019 · 1 comment
Closed

assertion fails when exporting to onnx #16895

rajarsheem opened this issue Feb 8, 2019 · 1 comment
Labels
module: onnx Related to torch.onnx

Comments

@rajarsheem
Copy link

rajarsheem commented Feb 8, 2019

I am using pytorch nightly and when I am trying to export my model to ONNX, I get the following error. Can you please help? Please let me know if you want to know anything.

File "/home/ramitra2/.conda/envs/deep/lib/python3.6/site-packages/torch/onnx/symbolic.py", line 562, in softmax
dim = input.type().dim() + dim
RuntimeError: r ASSERT FAILED at /opt/conda/conda-bld/pytorch-nightly_1549566607935/work/aten/src/ATen/core/jit_type.h:135, please report a bug to PyTorch. (expect at /opt/c
onda/conda-bld/pytorch-nightly_1549566607935/work/aten/src/ATen/core/jit_type.h:135)
frame #0: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x45 (0x7fb75ebe29e5 in /home/ramitra2/.conda/envs/deep/lib/python3.6/site-packages/torch/lib/libc10.s
o)
frame #1: std::shared_ptr<c10::DimensionedTensorType const> c10::Type::expectc10::DimensionedTensorType() const + 0x207 (0x7fb782410e87 in /home/ramitra2/.conda/envs/deep/
lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #2: + 0x39e5c7 (0x7fb78247a5c7 in /home/ramitra2/.conda/envs/deep/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #3: + 0x113e26 (0x7fb7821efe26 in /home/ramitra2/.conda/envs/deep/lib/python3.6/site-packages/torch/lib/libtorch_python.so)

frame #26: + 0x177ac4 (0x7fb782253ac4 in /home/ramitra2/.conda/envs/deep/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #27: torch::jit::BlockToONNX(torch::jit::Block*, torch::jit::Block*, torch::onnx::OperatorExportTypes, std::unordered_map<torch::jit::Value*, torch::jit::Value*, std::
hashtorch::jit::Value*, std::equal_totorch::jit::Value*, std::allocator<std::pair<torch::jit::Value* const, torch::jit::Value*> > >) + 0x4a0 (0x7fb782455000 in /home/ram
itra2/.conda/envs/deep/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #28: torch::jit::ToONNX(std::shared_ptrtorch::jit::Graph&, torch::onnx::OperatorExportTypes) + 0x406 (0x7fb782456246 in /home/ramitra2/.conda/envs/deep/lib/python3.6
/site-packages/torch/lib/libtorch_python.so)
frame #29: + 0x375b19 (0x7fb782451b19 in /home/ramitra2/.conda/envs/deep/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #30: + 0x113e26 (0x7fb7821efe26 in /home/ramitra2/.conda/envs/deep/lib/python3.6/site-packages/torch/lib/libtorch_python.so)
frame #61: __libc_start_main + 0xf5 (0x7fb79d283f45 in /lib/x86_64-linux-gnu/libc.so.6)
frame #62: python() [0x4009e9]

@pytorchbot pytorchbot added the module: onnx Related to torch.onnx label Feb 8, 2019
@ngimel
Copy link
Collaborator

ngimel commented Aug 17, 2021

Closing due to age

@ngimel ngimel closed this as completed Aug 17, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
module: onnx Related to torch.onnx
Projects
None yet
Development

No branches or pull requests

3 participants