Comments (6)
Hi, I don't understand the issue. The onnxruntime error message seems a valid error: you cannot reshape a zero-sized tensor into a tensor of size 1. So, it looks like an error in the model (or model-conversion).
from onnx.
@gramalingam I have edited the issue of input shape and requested shape.
When keeping the batch size as 32, am getting below failure.
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'/Reshape_16_output_0_ReduceMax_Reshape' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:44 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{0,1}, requested shape:{1}
When keeping the batch size as 1, am getting below failure.
[ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node. Name:'/Tile_output_0_ReduceMax_Reshape' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/tensor/reshape_helper.h:44 onnxruntime::ReshapeHelper::ReshapeHelper(const onnxruntime::TensorShape&, onnxruntime::TensorShapeVector&, bool) input_shape_size == size was false. The input tensor cannot be reshaped to the requested shape. Input shape:{1,0,1}, requested shape:{1}
from onnx.
@Priyanshu88 : You could ask in the onnxruntime repo (https://github.com/microsoft/onnxruntime/issues). It would help if you provide the onnx model and input to reproduce the error. I still think the error looks like a valid error message, so it could be an error in the model/exporter ... and maybe asking in mmlab would be more appropriate.
from onnx.
But this problem is coming up for the conversion of model from .pth to .onnx through the onnx_config i mentioned earlier. I am not yet on training or inference generation, i hope this to be the right place to ask.
from onnx.
For open-mmlab generated models, it may be a good idea to consult with developers of https://github.com/open-mmlab.
from onnx.
But this problem is coming up for the conversion of model from .pth to .onnx through the onnx_config i mentioned earlier
The onnx config you mention seems to be a feature of open-mmlab, not ONNX itself.
from onnx.
Related Issues (20)
- Squeeze-11's output shape is mistakenly inferred when input has dynamic axes and squeezing axes is not specified
- NMS Operator Output Different From Torchvision Implementation HOT 1
- n-bit data type HOT 1
- Model split failure using onnx.utils.extract_model HOT 3
- Change the example in the documentation of Transpose HOT 1
- Python 3.13 support HOT 1
- Can't reduce the version of Softmax from $13 to $12 HOT 2
- Unexpected floatBuffer output with onnxModel that substract 2 input floatBuffer HOT 1
- [Feature request] Better support for large models (>2GB) in extract_model HOT 2
- Why does SplitToSequence not allow zeros in `split` input? HOT 1
- flash-attention onnx export. HOT 3
- Try to convert LlamaForCausalLM to ONNX with input_embeds as input HOT 1
- Sonarcloud for static code analysis? HOT 4
- codeformatter / linter for yaml files? HOT 4
- ConcatFromSequence reference implementation does not respect axis when new_axis=1 HOT 1
- Error Loading ONNX Model: Invalid Node Input 'compute_STFT.window' HOT 1
- graph.input disappeared in extract_model HOT 1
- CI not compatible with ubuntu-24.04; Change the runner from ubuntu-latest to ubuntu-22.04? HOT 4
- [BUG] ROCMExecutionProvider is not in available provider names.
- Invalid protobuf error when loading successfully exported onnx model
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 onnx.