facebookresearch/VMZ

Issues

• performance on UCF and HMDB (split1)

  #125 opened 4 years ago by lovelyczli
  1

• Calculating weights for Gradient Blending for new datasets

  #133 opened 3 years ago by AntiLibrary5
  1

• can I download IG65M dataset?

  #132 opened 3 years ago by pritamqu
  2

• Please publish a lightweight video model, such as X3D /TSM or R(2+1)18 etc....

  #136 opened 3 years ago by dragen1860
  0

• Do we have tutorial or coding tutorial on how to use VMZ?

  #121 opened 4 years ago by JonathanSum
  4

• questions about input

  #135 opened 3 years ago by paden118
  1

• Some questions about GPU and clip_length?

  #120 opened 4 years ago by zhuimenghx
  2

• ir_csn_152 size mismatch: Error(s) in loading state_dict for VideoResNet

  #129 opened 4 years ago by KhHTran
  5

• Not able to reproduce reported results on Pytorch

  #134 opened 3 years ago by hoonkai
  0

• torchvision video_reader video backend is not available

  #130 opened 4 years ago by richardkxu
  0

• ucf101 ip_csn_152 training/test dataset config

  #131 opened 4 years ago by richardkxu
  0

• Converting IR-CSN-50 Caffe2 to PyTorch + more IR-CSN backbone sizes

  #128 opened 4 years ago by tchang1997
  2

• VMZ. Pytorch models

  #117 opened 4 years ago by jaypatravali
  8

• Broken links in PyTorch model zoo (+ fixes)

  #126 opened 4 years ago by tchang1997
  1

• Facing errors-> 'VideoResNet' object has no attribute 'compile' 'add' 'summary' 'fit'

  #127 opened 4 years ago by amandeep25
  0

• Feature extraction fails with [E video_decoder.cc:151] Insufficient data to determine video format

  #110 opened 5 years ago by R2D2oid
  5

• DistributedDataParallel error when train the model in one server with multi-gpus?

  #124 opened 4 years ago by chunniunai220ml
  1

• Feature extraction tutorial error

  #123 opened 4 years ago by WurmD
  3

• about the C3D model size

  #103 opened 4 years ago by bairw660606
  5

• Script for training ip-csn-152 from scratch on Kinetics

  #108 opened 4 years ago by huangjun12
  4

• Unrecognized arguments --pretrained_model in the script finetune_ucf101.sh

  #113 opened 4 years ago by lcskrishna
  1

• Does VMZ work with opencv 4.0+

  #114 opened 4 years ago by XinliYu
  1

• Tutorial for pytorch feature extraction

  #116 opened 4 years ago by NemioLipi
  1

• [logistics] proposing new labels

  #122 opened 4 years ago by bjuncek
  1

• How to generate kinetics_val_list

  #111 opened 4 years ago by nassimaNoufail
  0

• R(2+1)D training time on Kinetics

  #118 opened 4 years ago by elv-zhiyun
  1

• Error when run scripts/test_irCSN_152_kinetics.sh: input.numel() > 0

  #112 opened 5 years ago by huangjun12
  1

• About video list for feature extraction

  #104 opened 5 years ago by suminlee94
  1

• Finetuned model

  #99 opened 5 years ago by Jinyong-Huang
  0

• Could you update the clip level accuracy on Kinetics of those models?

  #96 opened 5 years ago by zkqiu
  2

• training ir-csn152 with ucf-101

  #88 opened 5 years ago by Jinyong-Huang
  7

• are there any preprocessing in video clips ?

  #109 opened 5 years ago by FesianXu
  1

• can not find opencv-3.4.0.zip

  #107 opened 5 years ago by 123liluky
  0

• Windows 10 environment?

  #106 opened 5 years ago by mnbv7581
  0

• model zoo link error?

  #105 opened 5 years ago by leemengxing
  0

• Converting model to pytorch.

  #102 opened 5 years ago by sanchit2843
  1

• Completely incapable of getting the installation requirements working

  #101 opened 5 years ago by kwende
  2

• How does jitter_scales parameter actually work?

  #100 opened 5 years ago by Granitevilian
  0

• Can't connect dropbox

  #98 opened 5 years ago by JameesWang
  1

• svm

  #97 opened 5 years ago by oLIVIa-Ld
  0

• TypeError: '/home/data/initial_training/training/clip1.avi' has type str, but expected one of: bytes

  #90 opened 5 years ago by ThatIndianCoder
  3

• frame rate for instagram models

  #95 opened 5 years ago by albanie
  5

• [E video_decoder.cc:751] The video seems faulty and we could not decode enough frames: 31 VS 32

  #93 opened 5 years ago by ThatIndianCoder
  1

• finetune ir-csn with my own dataset

  #91 opened 5 years ago by oLIVIa-Ld
  5

• Out of memory

  #92 opened 5 years ago by harshit-jain-git
  1

• Missing links

  #87 opened 5 years ago by bjuncek
  3

• Can we use the features extracted by the R(2+1)D-34 caffe model as input for a classifier built in Keras?

  #86 opened 5 years ago by ThatIndianCoder
  8

• Wrong number of midplanes in r(2+1)d model's downsampling basic blocks (layer 2,3,4)

  #89 opened 5 years ago by daniel-j-h
  1

• [E video_decoder.h:269] Error opening video file

  #85 opened 5 years ago by ThatIndianCoder
  2

• error for video format when training kinetics from scratch

  #84 opened 5 years ago by InwoongLee
  3