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

[e2e][onnx][model] onnx.Pad #617

Closed
PhaneeshB opened this issue Apr 15, 2024 · 1 comment
Closed

[e2e][onnx][model] onnx.Pad #617

PhaneeshB opened this issue Apr 15, 2024 · 1 comment

Comments

@PhaneeshB
Copy link
Contributor

PhaneeshB commented Apr 15, 2024

Failing Models:

  • retinanet_resnet50_fpn_vaiq_int8
  • KeypointRCNN_vaiq_int8

Run any of there models in SHARK-TestSuite with

cd e2eshark
python run.py --torchmlirbuild /path_to/torch-mlir/build  --ireebuild /path-to/iree-build --cachedir /path-to/model-cache-dir -r test-onnx --tolerance .001 .001 --mode onnx --report --tests  onnx/models/<MODEL_NAME>

Error:

retinanet_resnet50_fpn_vaiq_int8.default.torch-onnx.mlir:1067:13: error: failed to legalize operation 'torch.operator' that was explicitly marked illegal
    %1063 = torch.operator "onnx.Pad"(%895, %1062, %none) {torch.onnx.mode = "constant"} : (!torch.vtensor<[?,?,?],f32>, !torch.vtensor<[?],si64>, !torch.none) -> !torch.vtensor<[?,?,?],f32> 
            ^
retinanet_resnet50_fpn_vaiq_int8.default.torch-onnx.mlir:1067:13: note: see current operation: %3330 = "torch.operator"(%2572, %3329, %0) <{name = "onnx.Pad"}> {torch.onnx.mode = "constant"} : (!torch.vtensor<[?,?,?],f32>, !torch.vtensor<[?],si64>, !torch.none) -> !torch.vtensor<[?,?,?],f32>

KeypointRCNN_vaiq_int8.default.torch-onnx.mlir:1365:13: error: failed to legalize operation 'torch.operator' that was explicitly marked illegal
    %1361 = torch.operator "onnx.Pad"(%1041, %1360, %none) {torch.onnx.mode = "constant"} : (!torch.vtensor<[?,?,?],f32>, !torch.vtensor<[?],si64>, !torch.none) -> !torch.vtensor<[?,?,?],f32> 
            ^
KeypointRCNN_vaiq_int8.default.torch-onnx.mlir:1365:13: note: see current operation: %4411 = "torch.operator"(%3040, %4410, %0) <{name = "onnx.Pad"}> {torch.onnx.mode = "constant"} : (!torch.vtensor<[?,?,?],f32>, !torch.vtensor<[?],si64>, !torch.none) -> !torch.vtensor<[?,?,?],f32>

@PhaneeshB
Copy link
Contributor Author

PhaneeshB commented Apr 23, 2024

llvm/torch-mlir#3214
Landed, closing the issue

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant