Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

r50-c4 config #21

Closed
UcanSee opened this issue Nov 26, 2020 · 7 comments
Closed

r50-c4 config #21

UcanSee opened this issue Nov 26, 2020 · 7 comments
Labels
question Further information is requested

Comments

@UcanSee
Copy link

UcanSee commented Nov 26, 2020

Thanks for sharing such wonderful work!
Recently I want to try experiments on coco with r50-c4 backbone but I don't know how to set the configuration, can you share the config you used?
looking forward your reply!

@jason718
Copy link
Contributor

jason718 commented Nov 30, 2020

The current code haven't fully supported R50-C4 on COCO as we haven't include the sequential batch back-propagation module. If you run it, you may get OOM error. Sorry about this.

FYI, the config we were using looks like:

MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 
  WSOD_ON: True
  FASTER_RCNN: False
  ROI_HEADS:
    SCORE_THRESH: 0.0
    NMS: 0.3
  ROI_WEAK_HEAD:
    PREDICTOR: "MISTPredictor"
    LOSS: "RoIRegLoss"
    OICR_P: 0.15
    REGRESS_ON: True
DATASETS:
  TRAIN: ("coco_2014_train",)
  TEST: ("coco_2014_val",)
PROPOSAL_FILES:
  TRAIN: ('proposal/MCG-coco_2014_train-boxes.pkl',)
  TEST:  ('proposal/MCG-coco_2014_val-boxes.pkl',)
DATALOADER:
  SIZE_DIVISIBILITY: 32
INPUT:
  MIN_SIZE_TRAIN: (480, 576, 688, 864, 1000, 1200) 
  MAX_SIZE_TRAIN: 2000
  MIN_SIZE_TEST: 800
  MAX_SIZE_TEST: 2000
SOLVER:
  IMS_PER_BATCH: 8 
  BASE_LR: 0.01 
  WEIGHT_DECAY: 0.0001
  STEPS: (90000, 120000)
  MAX_ITER: 130000
  CHECKPOINT_PERIOD: 10000
TEST:
  BBOX_AUG:
    ENABLED: True
    HEUR: "AVG"
    H_FLIP: True
    SCALES: (480, 576, 688, 864, 1000, 1200) 
    MAX_SIZE: 2000
    SCALE_H_FLIP: True

@UcanSee
Copy link
Author

UcanSee commented Nov 30, 2020

The current code haven't fully supported R50-C4 on COCO as we haven't include the sequential batch back-propagation module. If you run it, you may get OOM error. Sorry about this.

FYI, the config we were using looks like:

MODEL:
  META_ARCHITECTURE: "GeneralizedRCNN"
  WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50" 
  WSOD_ON: True
  FASTER_RCNN: False
  ROI_HEADS:
    SCORE_THRESH: 0.0
    NMS: 0.3
  ROI_WEAK_HEAD:
    PREDICTOR: "MISTPredictor"
    LOSS: "RoIRegLoss"
    OICR_P: 0.15
    REGRESS_ON: True
DATASETS:
  TRAIN: ("coco_2014_train",)
  TEST: ("coco_2014_val",)
PROPOSAL_FILES:
  TRAIN: ('proposal/MCG-coco_2014_train-boxes.pkl',)
  TEST:  ('proposal/MCG-coco_2014_val-boxes.pkl',)
DATALOADER:
  SIZE_DIVISIBILITY: 32
INPUT:
  MIN_SIZE_TRAIN: (480, 576, 688, 864, 1000, 1200) 
  MAX_SIZE_TRAIN: 2000
  MIN_SIZE_TEST: 800
  MAX_SIZE_TEST: 2000
SOLVER:
  IMS_PER_BATCH: 8 
  BASE_LR: 0.01 
  WEIGHT_DECAY: 0.0001
  STEPS: (90000, 120000)
  MAX_ITER: 130000
  CHECKPOINT_PERIOD: 10000
TEST:
  BBOX_AUG:
    ENABLED: True
    HEUR: "AVG"
    H_FLIP: True
    SCALES: (480, 576, 688, 864, 1000, 1200) 
    MAX_SIZE: 2000
    SCALE_H_FLIP: True

thank you very much, I will try it. In addition, I want to know how the Lighting augmentation method influence the final performance because I have put the codes in the mmdetection but I got a bad result.

@jason718
Copy link
Contributor

By `Lighting augmentation method', do you mean the data augmentation?

If that's what you are referring to, we didn't try a baseline without all the data augmentations. It's unclear how will that influence the results.

@jason718 jason718 added the question Further information is requested label Jan 4, 2021
@vadimkantorov
Copy link

@jason718 Have you tried ResNet on VOC? Do I understand correctly that you haven't used Concrete DropBlock for ResNet-COCO experiments?

@vadimkantorov
Copy link

I've tried it on VOC but the results are much worse than VGG16 :(

@vadimkantorov
Copy link

Do I understand correctly FREEZE_CONV_BODY_AT=2 used for the ResNet-COCO experiments?

@jason718
Copy link
Contributor

@vadimkantorov Sorry for the late reply. When I was doing this work, I also found ResNet performing worse on VOC. The reason isn't very clear, and hence we didn't report.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants