search

mousecpn / DMC-Domain-Generalization-for-Underwater-Object-Detection

[Neurocomputing 2023] An official implementation of Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning
MIT License
26 stars 0 forks source link

Code reproduction failed due to missing model or code #2

Open bilityniu opened 1 year ago

bilityniu commented 1 year ago

Hello, this is a wonderful work and I want to reproduce the results. But it seems that some pre-trained model or code is missing and the compilation fails. The details are as follows:

  1. /mmdet/models/detectors/faster_rcnn.py: line 24 and 201, the class FasterRCNN(TwoStageDetector): is repeated. line 763-765 : self.WT = WaterTransfer(model_path="/home/dailh/Joint-Bilateral-Learning/checkpoints/epoch_6style_7.pth",style_num=14) .The model is missed.
  2. /mmdet/models/roi_heads/bbox_heads/init.py: line 9-11: from .tr_bbox_head import TrBBoxHead, MLPBBoxHead from .paa_bbox_head import PAABBoxHead from .amsoftmax_bbox_head import AMSoftmaxBBoxHead three file is miss: tr_bbox_head, paa_bbox_head, and amsoftmax_bbox_head.
  3. configs/base/datasets/suodac_detection_coco.py : line 8: The model LoadImageFromUODAC is missed, which is KeyError: "CocoDataset: 'LoadImageFromUODAC is not in the pipeline registry'"

It could also be my own carelessness, expecting answers or updates from the author. Thank you!!!

mousecpn commented 1 year ago

Hello, this is a wonderful work and I want to reproduce the results. But it seems that some pre-trained model or code is missing and the compilation fails. The details are as follows:

  1. /mmdet/models/detectors/faster_rcnn.py: line 24 and 201, the class FasterRCNN(TwoStageDetector): is repeated. line 763-765 : self.WT = WaterTransfer(model_path="/home/dailh/Joint-Bilateral-Learning/checkpoints/epoch_6style_7.pth",style_num=14) .The model is missed.
  2. /mmdet/models/roi_heads/bbox_heads/init.py: line 9-11: from .tr_bbox_head import TrBBoxHead, MLPBBoxHead from .paa_bbox_head import PAABBoxHead from .amsoftmax_bbox_head import AMSoftmaxBBoxHead three file is miss: tr_bbox_head, paa_bbox_head, and amsoftmax_bbox_head.
  3. configs/base/datasets/suodac_detection_coco.py : line 8: The model LoadImageFromUODAC is missed, which is KeyError: "CocoDataset: 'LoadImageFromUODAC is not in the pipeline registry'"

It could also be my own carelessness, expecting answers or updates from the author. Thank you!!!

Thanks for following our work. We are busy with the major revision now. When we finish our revision, we will clean up our code and submit it again.