llvm / llvm/torch-mlir

./torch-mlir-opt --torchscript-module-to-torch-backend-pipeline error

Open
#762 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
1.9k
Forks
736
Avg merge
5d 22h
Merged PRs (30d)
15

Description

TODO setp 2 convert torch.nn.Module to torch.jit

input_shape = [1,3,224,224]
input_data = torch.randn(input_shape)
alex_script = torch.jit.script(alex_model)
torch.jit.save(alex_script,"./torch_mlir.txt")

then perform
./torch-mlir-opt --torchscript-module-to-torch-backend-pipeline ../../../../py_project/test_torch_mlir/torch_mlir.txt was
error information
../../../../py_project/test_torch_mlir/torch_mlir.txt:1:3: error: unexpected character
PKtorch_mlir/data/0FB

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the torch.jit.save example and the torch-mlir-opt --torchscript-module-to-torch-backend-pipeline entry point, then inspect how the input file is parsed. Reproduce the reported unexpected-character error with torch_mlir.txt and determine the expected artifact format; done means the documented TorchScript conversion invocation runs without this parsing error.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, python, pytorch
Domain
compilers
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.