You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The decentralized onnx weight inference result exported by pytorch is correct, but the inference result is wrong after saving it as a single weight file using onnx.
[ONNXRuntimeError] : 1 : FAIL : Load model from ./onnxmodel1/unet.onnx failed:Node (/Unsqueeze) Op (Unsqueeze) [ShapeInferenceError] Cannot parse data from external tensors. Please load external data into raw data for tensor: /Constant_2_output_0
The decentralized onnx weight inference result exported by pytorch is correct, but the inference result is wrong after saving it as a single weight file using onnx.
==================
model link:
https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main/unet/diffusion_pytorch_model.safetensors
code link:
https://github.com/cloneofsimo/minDiffusion/tree/master/mindiffusion/unet.py
test code:
[ONNXRuntimeError] : 1 : FAIL : Load model from ./onnxmodel1/unet.onnx failed:Node (/Unsqueeze) Op (Unsqueeze) [ShapeInferenceError] Cannot parse data from external tensors. Please load external data into raw data for tensor: /Constant_2_output_0
The text was updated successfully, but these errors were encountered: