tascj / kaggle-hubmap-hacking-the-human-vasculature Goto Github PK

Congratulations! Thanks for your sharing!
when I run the code in kaggle notebook

from mmengine.config import Config
from mmdet.apis import init_detector, inference_detector
cfg = Config.fromfile("/kaggle/input/rtdet-mask/config.py")
checkpoint_file = "/kaggle/input/rtdet-mask/iter_22400.pth"
model = init_detector(cfg, checkpoint=checkpoint_file, device="cuda:0")
result = inference_detector(model, imgs=path_list)

The above config file is the same as you shared
I'm confused which file or config needs to be adjusted. Looking forward to your suggestion.

Hi @tascj ,

Congratulations! Really nice work!

Would it be possible for you to point out the code for this implementation?

I trained with a batch size of 8, comprising 3 images from dataset1 and 5 images from dataset2