Scores are smaller
kopyl opened this issue · comments
Oleh commented
Hey. I converted Pytorch model to ONNX with this: https://github.com/ultralytics/ultralytics :
model.export(format="onnx")
.
Is it because.
- I need to change something in my code when using inference with your tool?
- I need to change something the code of your tool?
- It's the result of the conversion to ONNX?
Could you please help? (:
Some comparison:
ONNX (first image):
[['bear', 0.7407247424125671],
['apple', 0.5914568901062012],
['apple', 0.5120987892150879]]
Torch (first image):
[['bear', 0.8472723364830017],
['apple', 0.6253159046173096],
['apple', 0.6134308576583862]]
(second image)
ONNX: 0,6926791071891785
Torch: 0,8411726951599121
Also ONNX model on conversion is for some reason way bigger than Torch's...
Oleh commented
Fixed: #8 (comment)