search

chenjun2hao / DDRNet.pytorch

This is the unofficial code of Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data
Other
157 stars 42 forks source link

onnxruntime error for onnx converted model #13

Open nishanthballal-9 opened 2 years ago

nishanthballal-9 commented 2 years ago

Unable to create an onnxruntime inference session from an onnx exported DDRNet-23-slim model on GPU. Can you provide some support related to this?

Getting the following error: InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Invalid model. Node input '449' is not a graph input, initializer, or output of a previous node.

Onikage3x2 commented 5 months ago

Unable to create an onnxruntime inference session from an onnx exported DDRNet-23-slim model on GPU. Can you provide some support related to this?

Getting the following error: InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Invalid model. Node input '449' is not a graph input, initializer, or output of a previous node.

did you find a solution for this? It seems, that it has something to do with the inputs that were marked as optional in the source model structure.