Feng Wang
Could you provide your command? If you want a reproducible code, the following [gist](https://gist.github.com/ihoromi4/b681a9088f348942b01711f251e5f964) might help you. ```python3 def seed_everything(seed: int): import random, os import numpy as np import torch...
from your log: ```shell File "/data/private/codes/YOLOX/yolox/data/datasets/coco.py", line 225, in pull_item id_ = self.ids[index] IndexError: list index out of range ``` It's might caused by wrong data format. Code to check...
What if you execute `pip install onnx` in your cli ?
@azimjonn Thanks for your advice! I will check py3.10 and see what's behind the installing error.
@fedyhajali You are using a old version whl, try clone YOLOX and install it with `pip install -v -e .`, after we releasing a new package, you may install yolox...
@korkland YOLOX requires `BGR` input image, and I also try `RGB` image, it doesn't effect the final performance too much. @nahidalam I double check the `augment_hsv` function, it's correct and...
Maybe we should add more docstring for our code related to data augmentation @Joker316701882 .
What type of issue are your facing now? I could not get your point, plz provide more info.
1. Yes, you could and you will train 200epoch started at 100e. 2. It's warning due to API change in pytorch, don't worry.
Any exception trace log @66Kevin ?