Open AnnieAbreu opened 3 months ago
Hi there, I had the same problem. The code passes all the args even the ones not compatible with the ConvNeXt module. A temporary modification that makes everything work is that: 1- Go to model_convnext.py 2- change the ConvNext init with this:
def __init__(self, in_chans=3, num_classes=1000,
depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], drop_path_rate=0.,
layer_scale_init_value=1e-6, head_init_scale=1., pretrained_cfg=None,pretrained_cfg_overlay=None
):
Then everything is working. I hope this helps you!
Hi, I encountered the issue "No such file or directory: './model/convnext_tri/opts.yaml' " when running the bash to train. Could u pls pull it up here? Thx a lot :)