tensorrt_inference icon indicating copy to clipboard operation
tensorrt_inference copied to clipboard

Published 20 hours ago • verified publisher icon linghu8812

ONNX conversion warning [CAN'T RECORD THE DATA FLOW OF PYTHON VALUES]

Open bobbilichandu opened this issue 4 years ago • 5 comments

Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs! if self.grid[i].shape[2:4] != x[i].shape[2:4]:

facing this issue every time I try to convert model to onnx. Can this be ignored?

bobbilichandu avatar Dec 26 '20 13:12 bobbilichandu

please try to use https://github.com/linghu8812/ScaledYOLOv4 to export ONNX model, the yolo.py file is different.

linghu8812 avatar Dec 28 '20 00:12 linghu8812

Used the same[cloned the modified repository by you], but still facing the same issue. Will it affect the trt performance?

bobbilichandu avatar Dec 28 '20 12:12 bobbilichandu

this may caused by these lines: https://github.com/linghu8812/ScaledYOLOv4/blob/b584a70b27a75e01ab5710b7743ca325f81aa443/models/yolo.py#L46-L47

linghu8812 avatar Dec 29 '20 02:12 linghu8812

@chandu1263 did it have an impect on the trt performance ?

pepijnko avatar Apr 02 '21 14:04 pepijnko

Nope. You can ignore that actually.

bobbilichandu avatar Apr 02 '21 14:04 bobbilichandu