locuslab/deq

Issues

• How does DEQ use less memory compared to explicit network?

  #33 opened 2 months ago by SeminKim
  0

• Hyperparameters for MDEQ-XL on ImageNet

  #32 opened a year ago by cmohri
  0

• Mismatch between a pretrained ImageNet model and a config file

  #31 opened 2 years ago by metodj
  1

• Expected a 'cuda' device type for generator but found 'cpu'

  #30 opened 2 years ago by dorazhiyuyang
  2

• UserWarning: resource_tracker: There appear to be 14 leaked semaphore objects to clean up at shutdown

  #29 opened 2 years ago by yj373
  4

• Broyden defeats the purpose of DEQs?

  #28 opened 2 years ago by polo5
  6

• UnboundLocalError: local variable 'lowest_xest' referenced before assignment

  #26 opened 2 years ago by wang-zm18
  4

• Higher order derivatives

  #25 opened 3 years ago by brunompacheco
  0

• Question about Remove Hook

  #24 opened 3 years ago by QiyaoWei
  6

• RuntimeError: Only Tensors created explicitly by the user (graph leaves) support the deepcopy protocol at the moment

  #23 opened 3 years ago by QiyaoWei
  2

• Expected a 'cuda' device type for generator (related to speed issues?)

  #22 opened 3 years ago by polo5
  5

• I'd like to ask if anderson can't be used normally sometimes

  #20 opened 3 years ago by Maybe2022
  11

• Does MDEQ have different inference results for different batch sizes?

  #21 opened 3 years ago by undercutspiky
  6

• Test ImageNet Pre-trained Model

  #14 opened 3 years ago by HieuPhan33
  10

• DEQ for Vision Transformer

  #18 opened 3 years ago by wyvernbai
  2

• Memory consumption on CIFAR-10

  #19 opened 3 years ago by WinterPan2017
  4

• RuntimeError: einsum(): the number of subscripts in the equation (3) does not match the number of dimensions (4) for operand 0 and no ellipsis was given

  #17 opened 3 years ago by QiyaoWei
  1

• Segmentation fault after removing hook

  #15 opened 3 years ago by tesfaldet
  3

• CIFAR-10 Reproduction

  #13 opened 3 years ago by HieuPhan33
  6

• Segmentation Fault when Loss Backward CIFAR cls_mdeq_LARGE_reg

  #12 opened 3 years ago by HieuPhan33
  10

• Two slightly different process for Deq

  #11 opened 3 years ago by SamChen
  2

• Can I train my custom MLP model with DEQ in tutorial page?

  #10 opened 4 years ago by san9569
  3

• Updated code with load_state_dict

  #9 opened 4 years ago by sarthmit
  4

• TrellisNetDEQModule class inheritence

  #8 opened 4 years ago by kevinliang888
  1

• Why copy weight manually instead of using 'load_state_dict'?

  #7 opened 4 years ago by LuChengTHU
  1

• Any progress for pytorch 1.5?

  #6 opened 4 years ago by LuChengTHU
  4

• Simple Model Training Issue

  #4 opened 5 years ago by Diego-Bit-0
  4

• Language modeling inference complexity and training objective?

  #3 opened 5 years ago by se4u
  6

• License?

  #2 opened 5 years ago by kmsquire
  2

• why use weight norm?

  #1 opened 5 years ago by gaopengcuhk
  2