kjunelee/MetaOptNet

Issues

• tieredImageNet dataset not available

  #59 opened 5 months ago by woreom
  2

• How do I know what the real category of tieredImagenet is?

  #56 opened 3 years ago by 541124010
  2

• Overlapping between meta-training classes and meta-testing classes

  #55 opened 3 years ago by tuananhbui89
  1

• Project dependencies may have API risk issues

  #58 opened 2 years ago by PyDeps
  0

• Pretrained model

  #57 opened 3 years ago by gyr0104
  0

• qpth error

  #20 opened 5 years ago by zstbackcourt
  6

• Thanks and some questions

  #54 opened 3 years ago by jwdnjwdn
  0

• could you tell me the link which about the miniImageNet_category_split_train_phase_train.pickle ?

  #53 opened 3 years ago by jwdnjwdn
  0

• qpth Error: Cannot perform LU factorization on Q.

  #37 opened 5 years ago by Ze-Yang
  4

• the parameters config for the cifarfs,the accuracy is only 63%

  #52 opened 4 years ago by xue19890510
  1

• Parameters for ProtoNet using ResNet12 as backbone

  #51 opened 4 years ago by ruizhaoz
  0

• Protonet re-implementation details

  #50 opened 4 years ago by ars22
  3

• Question about meta-validation and meta-testing

  #49 opened 4 years ago by LoveMiki
  4

• what is the difference between novel categories and base category?

  #48 opened 4 years ago by seyeeet
  1

• question about "--episodes-per-batch"

  #45 opened 5 years ago by yxgnahz
  2

• About"TypeError: btrisolve() takes 3 positional arguments but 4 were given"

  #47 opened 5 years ago by By-he
  0

• Keep-rate scheduling of DropBlock in a multi-GPU environment

  #41 opened 5 years ago by kyleahn
  2

• Meta gradient Computation

  #46 opened 5 years ago by ars22
  3

• Does the performance of different SVM heads vary largely?

  #44 opened 5 years ago by 1zb
  1

• Couldn't repeat your results [Instance Norm/Batch Norm]

  #38 opened 5 years ago by lucastononrodrigues
  2

• About accuracy in CIFAR_FS 5-way 5-shot and how to implement MetaOptNet-SVM-trainval

  #40 opened 5 years ago by WHQ1111
  2

• Can this code be used for MetaOptNet-SVM-trainval?

  #18 opened 5 years ago by AceChuse
  4

• Where is the parameter gamma

  #43 opened 5 years ago by 1zb
  1

• Why the accuracy of the Prototypical Network is higher than the reported version in paper?

  #42 opened 5 years ago by WHQ1111
  1

• Some questions about MetaOptNetHead_Ridge

  #39 opened 5 years ago by WHQ1111
  2

• Why dual formulation in Bertinetto's regression solver?

  #36 opened 5 years ago by arxrean
  1

• RuntimeError with qpth

  #35 opened 5 years ago by lhfowl
  2

• Why the SVM implemented by yourself is better than that in sklearn

  #34 opened 5 years ago by DamonAtSjtu
  1

• MiniImageNet 5way1shot acc

  #33 opened 5 years ago by chmxu
  8

• Formula (11) in your paper.

  #32 opened 5 years ago by LYF14020510036
  1

• def MetaOptNetHead_Ridge()

  #31 opened 5 years ago by LYF14020510036
  3

• Pretrained model

  #30 opened 5 years ago by hytseng0509
  2

• qpth warning: Returning an inaccurate and potentially incorrect solutino.

  #29 opened 5 years ago by LYF14020510036
  2

• Reproducability about ProtoNet on mini-ImageNet

  #25 opened 5 years ago by hankook
  2

• cannot repeat paper's results

  #27 opened 5 years ago by robotzheng
  1

• Questions on layer1&2 's dropblock

  #28 opened 5 years ago by tao0420
  1

• ResNet-12 channels is different to TADAM

  #26 opened 5 years ago by yinboc
  2

• Accuracy of CIFAR-FS

  #24 opened 5 years ago by SivanDoveh
  3

• Loading qpth fails on Enum

  #23 opened 5 years ago by iandreariley
  1

• TypeError: btrisolve() takes 3 positional arguments but 4 were given

  #21 opened 5 years ago by robotzheng
  1

• The results on miniImageNet

  #22 opened 5 years ago by AceChuse
  2

• How can I use this code to do predict on custom dataset without ground truth labels?

  #16 opened 5 years ago by PacteraKun
  2

• there is error when the network is Resnet and the head is SVM.

  #11 opened 5 years ago by suengah
  4

• The number of val-shot choice.

  #17 opened 5 years ago by AceChuse
  2

• Is Label smoothing for SVM only used in miniImageNet?

  #19 opened 5 years ago by AceChuse
  3

• val and test set in FC100

  #15 opened 5 years ago by AceChuse
  2

• some questions about the paper and code

  #12 opened 5 years ago by GuChenghs
  3

• about input data (pickle files)

  #13 opened 6 years ago by xmengli
  3

• Error in the SVM Head

  #10 opened 6 years ago by goldblum
  2

• Reproduced results on miniImagenet with prototypical network with 4-layer network

  #9 opened 6 years ago by kikyou123
  2