er-muyue/DeFRCN

Issues

• About the fine tune problems

  #70 opened 2 years ago by tangkail
  1

• FloatingPointError: Predicted boxes or scores contain Inf/NaN. Training has diverged.

  #37 opened 3 years ago by xiaohei1001
  6

• RuntimeError: CUDA error: no kernel image is available for execution on the device

  #74 opened 7 months ago by 75391fwh
  0

• OutOfMemoryError with PrototypicalCalibrationBlock

  #73 opened 9 months ago by gladdduck
  5

• Out of memory error during evaluation but training works fine!

  #65 opened 2 years ago by suryasid09
  3

• How to used in the customer dataset?

  #43 opened 3 years ago by jo-dean
  8

• fine-tuning on my cutsomized dataset

  #72 opened a year ago by sea190
  0

• About PCB module

  #29 opened 3 years ago by liaorongfan
  1

• Why final checkpoint is removed in run_voc.sh script?

  #67 opened 2 years ago by suryasid09
  1

• 可视化

  #57 opened a year ago by Zhengzkang
  0

• cuda version

  #69 opened a year ago by lyxdlut
  2

• main.py: error: unrecognized arguments: --opts MODEL.WEIGHTS /public/home/jd_fky/project/DeFRCN/data/ImageNetPretrained/MSRA/R-101.pkl OUTPUT_DIR checkpoints/coco/defrcn/defrcn_det_r101_base 3 I don't know why running main.py causes this problem

  #71 opened a year ago by fky07
  1

• How do I find your core code of GDL and PCB?

  #44 opened a year ago by dreamwish1998
  2

• mAP

  #46 opened a year ago by salehnia
  1

• What does 'if final, 10 -> 1 2 3 5 10' in run_voc.sh mean?

  #49 opened a year ago by CrapbagMo
  1

• Why TFA links point to cvpods？

  #50 opened a year ago by IceHowe
  1

• COCO EVAL

  #53 opened a year ago by jjxt10
  2

• argument 'alpha' must be Number, not NoneType

  #56 opened a year ago by Yxt1212
  2

• AssertionError: Checkpoint checkpoints/voc/mydefrcn/defrcn_det_r101_base1/model_reset_remove.pth not found!

  #58 opened a year ago by yewanzhuo
  6

• TypeError: init() got an unexpected keyword argument 'first_stride'

  #63 opened a year ago by Decade-Li
  2

• the code to find the similarity

  #36 opened a year ago by liliwannian
  1

• Importance of w,w/o FPN in DeFRCN

  #26 opened a year ago by buncybunny
  3

• Question about ground truth boxes which are used in training and PrototypicalCalibrationBlock

  #54 opened 2 years ago by leesb7426
  4

• Unable to reproduce the results

  #35 opened 3 years ago by fenghuo-cao
  9

• Why the different number of images on inference?

  #59 opened 2 years ago by ZhiXianZ
  0

• running Inference on model

  #66 opened 2 years ago by suryasid09
  0

• Do we need to give support image during inference?

  #68 opened 2 years ago by suryasid09
  1

• Guide on Fine Tuning

  #62 opened 2 years ago by suryasid09
  0

• Where is pascal VOC metasplit located?

  #64 opened 2 years ago by suryasid09
  0

• how can I get detection results?

  #39 opened 3 years ago by binyisu
  3

• Help with multi-GPU training in Google Colab

  #61 opened 2 years ago by suryasid09
  1

• How to reproduce the results in Figure4(b)?

  #60 opened 2 years ago by ry-jojo
  1

• How can I customize new hyperparameters in detectron2

  #55 opened 2 years ago by dreamwish1998
  0

• RuntimeError: The server socket has failed to listen on any local network address. The server socket has failed to bind to [::]:50153 (errno: 98 - Address already in use). The server socket has failed to bind to ?UNKNOWN? (errno: 98 - Address already in use).

  #45 opened 3 years ago by MALLI7622
  1

• Experimental setting is different from TFA and FSRW

  #52 opened 2 years ago by 1179021477
  0

• The training paradigm seems is quite different from TFA & FSCE etc. classic FSOD method.

  #51 opened 2 years ago by RuoyuChen10
  1

• Results of the VOC dataset

  #48 opened 3 years ago by Stlve
  0

• purpose of the 'class dropout'

  #47 opened 3 years ago by mandal4
  0

• Json file

  #42 opened 3 years ago by Jxt5671
  0

• Difference Between ’Remove‘ and ’Randinit‘

  #41 opened 3 years ago by xiaohei1001
  1

• ablation experiment 消融实验

  #40 opened 3 years ago by liliwannian
  0

• When using other pretrained ResNet backbone to train DeFRCN, the performance of novel classes few-shot detection drops a lot

  #38 opened 3 years ago by miznchimaki
  0

• visualization

  #27 opened 3 years ago by alphacyp
  2

• problem in Running novels

  #28 opened 3 years ago by salehnia
  3

• AssertionError: Checkpoint checkpoints/voc/defrcn/defrcn_det_r101_base3/model_reset_surgery.pth not found

  #25 opened 3 years ago by zhengfang1997
  4

• k-shot采样策略

  #30 opened 3 years ago by liliwannian
  2

• could you share the checkpoint files?

  #31 opened 3 years ago by mandal4
  1

• Question about Figure 4 in the Paper

  #33 opened 3 years ago by michaelku1
  1

• A simple question abount the coco dataset images configuration

  #34 opened 3 years ago by miznchimaki
  1

• The weight of Affine Matrix

  #32 opened 3 years ago by MartinYYYYan
  1