MCG-NJU/TDN

Issues

• visualization

  #52 opened 2 years ago by Traveler-Pass
  2

• visualization

  #73 opened 5 months ago by fengjingchehu
  0

• train new dataset with pretrained model

  #69 opened 2 years ago by sanwei111
  3

• Hello, is there a processed kenetics dataset, can you send me a copy.

  #72 opened a year ago by DSdsasg
  0

• decord._ffi.base.DECORDError: [16:56:24] /github/workspace/src/video/video_reader.cc:151: Check failed: st_nb >= 0 (-1381258232 vs. 0) ERROR cannot find video stream with wanted index: -1

  #24 opened 3 years ago by NEUdeep
  6

• About using pre-trained models

  #71 opened a year ago by Manav2906
  0

• about the beginning index of the annotations

  #70 opened 2 years ago by sanwei111
  0

• frames*crops*clips and train_log

  #68 opened 2 years ago by sanwei111
  0

• Frames x Crops x Clips

  #67 opened 2 years ago by sanwei111
  1

• about how to train

  #65 opened 2 years ago by sanwei111
  1

• about data input

  #66 opened 2 years ago by sanwei111
  1

• Sudden slowdown in training

  #63 opened 2 years ago by tss35
  0

• About hmdb51 Dataset

  #64 opened 2 years ago by yyhyyh17
  0

• 训练数据集为什么不打乱？

  #62 opened 2 years ago by Turing77
  2

• something something V2's fps

  #61 opened 2 years ago by pudding126
  1

• Would you share the checkpoints of UCF101 and HMDB51?

  #60 opened 2 years ago by nationalflag
  1

• The hyperparameters of training resnet101 on Something-V1

  #58 opened 2 years ago by withbrightmoon
  1

• 训练效果很差

  #59 opened 2 years ago by tzynzs
  1

• BatchSize How to set in a single card？

  #39 opened 3 years ago by anfengmin100
  7

• How to rerun this project in ucf101?

  #56 opened 2 years ago by sja9527
  1

• Problem of testing

  #55 opened 2 years ago by xiaofengWang-CCNU
  4

• Problems related to model performance

  #51 opened 2 years ago by jwfanDL
  10

• can't find file

  #54 opened 2 years ago by Brasiletto
  1

• Question of setting of 'new_length' in dataset.py

  #48 opened 2 years ago by dy1998
  1

• Backward and forward in L-TDM module

  #50 opened 2 years ago by aikuniverse
  1

• model testing file does not consider the situation of dense sample

  #53 opened 2 years ago by AlbertZW
  1

• Can't reproduce kinetic400 result

  #49 opened 2 years ago by sean186
  2

• Fine tuning of UCF101 and HMDB51

  #28 opened 3 years ago by LV0913
  5

• Some confusion

  #46 opened 3 years ago by wanlmq6165163
  2

• How does clip_index affect the sampling results?

  #47 opened 3 years ago by RongchangLi
  1

• About the reproduction of the hmdb51 dataset

  #45 opened 3 years ago by Brasiletto
  2

• Question about pretrained kinetic400 model accuracy?

  #44 opened 3 years ago by sean186
  3

• dataset.py 'new_length'

  #42 opened 3 years ago by zhanggj821
  2

• About memory of training on sthv1

  #43 opened 3 years ago by Oldyin1012
  1

• TypeError: 'Compose' object is not iterable

  #41 opened 3 years ago by venje-zhu
  1

• Question about TSM accuracy in ablation study

  #40 opened 3 years ago by jinhaoduan
  3

• Batch_Size H欧文、 to set size in a single card

  #38 opened 3 years ago by anfengmin100
  0

• Confusion about the baseline

  #37 opened 3 years ago by wei666666
  1

• sth官网没了，能否分享一下sth-sth-v1的原始csv格式的label文件呢？

  #36 opened 3 years ago by takfate
  1

• Visualization wtih Grad-CAM

  #35 opened 3 years ago by wei666666
  1

• 关于LTDM的代码

  #34 opened 3 years ago by HUAFOR
  0

• A question about testing

  #33 opened 3 years ago by Brasiletto
  1

• When testing on sth-sth-v1, which checkpoint should be used, 'best.pth' or '60_epoch_ckpt_pth'?

  #31 opened 3 years ago by withbrightmoon
  2

• CUDA out of memory, even when batch_size=1

  #32 opened 3 years ago by fightingaaa
  0

• Question about processing of HMDB51 dataset

  #29 opened 3 years ago by MonkeyKing-KK
  1

• Pretrained models

  #27 opened 3 years ago by LV0913
  6

• How long did the model converge in Kinetics400 on 8 V100?

  #26 opened 3 years ago by SCZwangxiao
  5

• What's the meaning of Frames, Crops, and Clips reqpectvely?

  #25 opened 3 years ago by SCZwangxiao
  1

• questions about batchnorm in DistributedDataParallel

  #22 opened 3 years ago by ZGCTroy
  1

• questions about ShiftModule used in BottleneckShift

  #23 opened 3 years ago by ZGCTroy
  1