facebookresearch/swav

Issues

• train models with multicrops

  #122 opened a year ago by lxysl
  0

• how to prepare the training data?

  #110 opened 2 years ago by wmingdao
  1

• Missing "resnet50w5" linear config in eval_linear.py

  #121 opened a year ago by zeyuanyin
  0

• Imagenet performance reproduction problem with swav pretrain weights in torch hub

  #74 opened 3 years ago by seominseok0429
  5

• About the loss

  #120 opened a year ago by zhangtzq
  1

• loss behaviour

  #88 opened 3 years ago by chinmay5
  4

• Slow Training with Swav on 2 GPUs using torch.distributed

  #119 opened a year ago by doms-17
  1

• A question about batch_size and nmb prototypes

  #118 opened a year ago by mrFocusXin
  1

• About Loss function.

  #117 opened a year ago by AndrewTalYeah
  1

• ImageNet pretraining size

  #116 opened 2 years ago by slahrichi
  0

• About SwAV_ver2

  #114 opened 2 years ago by dbsdmlgus50
  0

• Qualitative aspects of the learned cluster

  #73 opened 3 years ago by dssrgu
  1

• How to get the correct answer

  #113 opened 2 years ago by limbo520
  0

• A question about dataloader setting : `shufflu`?

  #103 opened 2 years ago by Classmate-Huang
  2

• Is it possible to use a pretrained ResNet50 for SWAV for custom dataset?

  #102 opened 3 years ago by sarmientoj24
  2

• Question about loss and hyperparameters

  #69 opened 3 years ago by TopTea1
  4

• urllib.error.HTTPError: HTTP Error 403: Forbidden

  #111 opened 2 years ago by GDzhu01
  0

• question of loading pre-trained model in eval_linear.py and eval_semisup.py

  #109 opened 2 years ago by zhawhjw
  0

• image segmentation

  #108 opened 2 years ago by Hejarshahabi
  0

• About the format of dataset

  #107 opened 2 years ago by GSusan
  0

• instability with prediction while using resnet 50 pretrained model

  #105 opened 2 years ago by knitemblazor
  1

• How can I load DeepCluster-v2?

  #104 opened 2 years ago by keyuchen21
  0

• Question about the training dataset

  #91 opened 3 years ago by rover5056
  1

• [Discussion] Can I use DeepClusterV2 for the sole purpose of learning to cluster unlabelled dataset?

  #101 opened 3 years ago by timothylimyl
  1

• Swav for video

  #99 opened 3 years ago by DoublePan-Oh
  1

• Pre-training on a small dataset to learn image similarity

  #77 opened 3 years ago by thecooltechguy
  1

• Degraded DCv2 Training Loss

  #100 opened 3 years ago by gorkaydemir
  0

• Is this a reasonable graph for the losses?

  #98 opened 3 years ago by sarmientoj24
  0

• Removing dependency on NVIDIA apex

  #96 opened 3 years ago by RylanSchaeffer
  1

• Cannot load the pretrained model with torch.hub.load

  #95 opened 3 years ago by TuanDTr
  0

• Why setting two kinds of codes (Q, P)?

  #72 opened 3 years ago by zhujiagang
  3

• How to use Torchvision R50 for unsupervised pretraining

  #94 opened 3 years ago by sarmientoj24
  0

• why the prototype are normalized?

  #82 opened 3 years ago by coderSkyChen
  1

• install pandas

  #92 opened 3 years ago by anic46
  1

• Why matrix multiplication when using queue?

  #93 opened 3 years ago by karray
  0

• How to pre-train Faster RCNN ResNet 50 Caffe and retrieve the weights?

  #90 opened 3 years ago by sarmientoj24
  0

• How to use SwAV for videos?

  #89 opened 3 years ago by vaibhavmsharechat
  0

• multiple GPUs

  #87 opened 3 years ago by AziMtmd
  0

• Question on KMeans clustering in deepclusterv2

  #83 opened 3 years ago by cheneeheng
  2

• Error 404 on torch.hub.load('facebookresearch/swav', 'resnet50')

  #86 opened 3 years ago by MikaData57
  1

• Can DeepCluster be trained without using data augmentation?

  #85 opened 3 years ago by adnan1306
  0

• Parameters for training on the small dataset on GPU

  #78 opened 3 years ago by ghalib2021
  1

• Different weight size between pretrained model and the model trained on my own datasets of deepclusterv2

  #84 opened 3 years ago by xgyyao
  0

• Why using the hyperparameter "freeze_prototypes_niters"?

  #76 opened 3 years ago by xuChenSJTU
  1

• Changes to standard ResNet

  #81 opened 3 years ago by kshen6
  2

• What's performance in deeper model

  #80 opened 3 years ago by NickChang97
  1

• ImageNet-21K Pretrained model?

  #79 opened 3 years ago by BIGBALLON
  1

• question in running eval_linear.py

  #70 opened 3 years ago by libingDY
  4

• load_state_dict() got an unexpected keyword argument 'strict'

  #75 opened 3 years ago by Hfhstrive
  2

• Surprising but interesting duplicated clusters

  #71 opened 3 years ago by Jiawei-Yang
  1