-
### Proposal:
Add a utility to validate and adjust input shapes for convolutional models.
### Description:
Currently, the project does not provide a way to check whether an input shape is compa…
-
### What happened?
For the given MLIR
```mlir
module {
func.func @main_graph( %arg0: !torch.vtensor, %arg1: !torch.vtensor) -> !torch.vtensor attributes {torch.onnx_meta.ir_version = 7 : si64, t…
-
我试着将pt文件转为onnx文件，代码出现以下报错
Traceback (most recent call last):
File "/home/server/YHG/PET_main/pth_onnx.py", line 100, in
convert_pth_to_onnx(args)
File "/home/server/YHG/PET_main/pth_onnx.…
-
The goal of this refactor is to remove all static shape inference within the `onnx-ir` module and focus solely on rank inference. This shift aims to:
1. **Simplify the Shape Inference Process**:
…
-
### Describe the issue
According to [TensorRT EP docs](https://onnxruntime.ai/docs/execution-providers/TensorRT-ExecutionProvider.html) one should do symbolic shape inference before executing the mod…
maaft updated
3 weeks ago
-
Greetings,
I've tested the models on an M1 Mac & it works perfectly fine using the CPU. (Gets extremely slow for images with res higher than 512*512 though which I think is expected...)
I plan to …
-
I have full code
```{python}
import torch
from diffusers import StableDiffusionXLPipeline
from PIL import Image
from ip_adapter import IPAdapterPlusXL
from ip_adapter.custom_pipelines import S…
-
### What happened + What you expected to happen
When using the predict_insample() method on an NHITS model with a DataFrame containing multiple timeseries of varying lengths, the following error oc…
-
### OpenVINO Version
openvino_2024.4.0
### Operating System
Other (Please specify in description)
### Device used for inference
NPU
### Framework
PyTorch
### Model used
resnet50-binary-0001.x…
-
### 🐛 Describe the bug
Torch-TensorRT model successfully compiles and can be saved as ExportedProgram. But it fails to load.
Here is the full error log
```py
WARNING:py.warnings:/home/dperi/…