Dilip Parasu
Dilip Parasu
```python from nebullvm.operations.conversions.onnx import convert_onnx_to_torch import onnx onnx_model_path = '/home/venom/Downloads/mobilenetv2-12.onnx' onnx_model = onnx.load(onnx_model_path) output_file_path = '/home/venom/Downloads/model.pt' device = 'cpu' convert_onnx_to_torch(onnx_model, output_file_path, device) ``` For now the convertion works without error...
Update: Sorry for the delay ```python import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' from nebullvm.operations.conversions.onnx import convert_onnx_to_torch import onnx onnx_model_path = '/home/venom/Downloads/mobilenetv2-7.onnx' onnx_model = onnx.load(onnx_model_path) output_file_path = '/home/venom/Downloads/model.pt' device = 'cpu' outfile...
onnx2torch module, has the requirement of opset version 9 (minimum) In the above example, the model used opset7 (hence failed) Trying to convert all the models in https://github.com/onnx/models Open To...
Workaround for opset version [Onnx Version Conversion - Offical Docs](https://github.com/onnx/onnx/blob/main/docs/PythonAPIOverview.md#converting-version-of-an-onnx-model-within-default-domain-aionnx) Example ```python import onnx from onnx import version_converter import torch from onnx2torch import convert # Load the ONNX model model...
Same issue Looking further, the model is getting into CPU after going through speedster (?) Changing the model to cuda manually before inference works. But model detaching from GPU is...
It's inference Learner object I am not exactly sure how to move it, but a higher level view would be to get the model out of the inference learner, and...
I see the issue Its in the doc string, but not within the code. I guess weighted is not supported (?) https://github.com/Lightning-AI/torchmetrics/blob/a68455afb9041d1d32c1d6546897fee416abdc41/src/torchmetrics/classification/dice.py#L71 https://github.com/Lightning-AI/torchmetrics/blob/a68455afb9041d1d32c1d6546897fee416abdc41/src/torchmetrics/classification/dice.py#L158 Looks like most of the weighted code...
![image](https://user-images.githubusercontent.com/88489071/216881469-e6b98610-b6dc-4a9e-a52b-26d556c254ae.png) I have no idea where this error is being originated. Any help would be appreciated Manually invoking the conversion works, I am not sure where the input is expected...
@microsoft-github-policy-service agree
Another pruning method! https://arxiv.org/pdf/2306.11695