Comments (9)
I was able to reproduce it, the problem is in the PyTorch tracing mechanism. The fastest and simplest solution is to update your PyTorch to 1.13.x (if it possible for you).
Many Thanks @senysenyseny16,
I updated the PyTorch to 1.13.1 to solve this problem.
from onnx2torch.
I temporarily set spatial rank to 2 and solved my problem. But this is obviously a temporary solution and I am looking for options to solve it.
from onnx2torch.
I've just looked at #121 and this seems to be the same issue.
from onnx2torch.
Hi @JohnMasoner
Could you check conversion with onnx2torch==1.5.6
?
pip install onnx2torch==1.5.6
from onnx2torch.
Hi @JohnMasoner
Could you check conversion with
onnx2torch==1.5.6
?pip install onnx2torch==1.5.6
Thank you @senysenyseny16
I still got the same bug.
from onnx2torch.
I was able to reproduce it, the problem is in the PyTorch tracing mechanism.
The fastest and simplest solution is to update your PyTorch to 1.13.x (if it possible for you).
from onnx2torch.
Also, I think the torch.export in PyTorch 1.12.x slightly breaks the model:
❯ python3 /venv39/lib/python3.9/site-packages/onnxruntime/tools/symbolic_shape_infer.py --input monai_1_12.onnx --output monai_1_12_infer.onnx
Traceback (most recent call last):
File ".../symbolic_shape_infer.py", line 2411, in <module>
out_mp = SymbolicShapeInference.infer_shapes(
File ".../symbolic_shape_infer.py", line 2347, in infer_shapes
raise Exception("Incomplete symbolic shape inference")
Exception: Incomplete symbolic shape inference
On PyTorch 1.13.x shape inference works as expected.
from onnx2torch.
Hello, I am facing a similar issue. But following the above discussion is not working. This is the error I am getting:
NotImplementedError: BatchNorm operation with spatial rank == -2 is not implemented
please let me know what could be done to resolve the issue. Thank you.
from onnx2torch.
Hello, I am facing a similar issue. But following the above discussion is not working. This is the error I am getting: NotImplementedError: BatchNorm operation with spatial rank == -2 is not implemented
please let me know what could be done to resolve the issue. Thank you.
Have you find a solution?
from onnx2torch.
Related Issues (20)
- Failed to convert SSDLite with MobileNetV2 backbone
- Unable to successfully convert retinanet R50 HOT 1
- Circular import HOT 1
- Key error 'flow/flow.6/enc/Mul_output_0
- add piper-tts onnx to torch
- Clip convert error: Dynamic value of min/max is not implemented HOT 8
- NotImplementedError: Converter is not implemented (OperationDescription(domain='', operation_type='BatchNormalization', version=7))
- PermissionError: [Errno 13] Permission denied: 'E:\\onnx2torch\\tmptf9fub_u' HOT 3
- Optimizer got an empty parameter list.
- What is the difference with onnx2pytorch?
- running float16 model on the CPU
- NotImplementedError: Average pool operation with spatial rank == -2 is not implemented
- NotImplementedError: AvgPool with non symmetrical padding is not implemented.
- NotImplementedError: Converter is not implemented (OperationDescription(domain='', operation_type='Loop', version=13)) HOT 1
- Does onnx2torch support dynamic input shape?
- onnx2torch incorrectly omits one weight layer when converting onnx into pytorch.
- NotImplementedError: Converter is not implemented (OperationDescription(domain='', operation_type='If', version=11))
- Problem with input shape
- Not working with yolov5 6.2 and yolov8
- how to transform torch.fx.GraphModule to nn.module?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnx2torch.