fenglinglwb/MAT

Issues

• Are there model pre-trained model for Places with resolution 256?

  #125 opened 3 months ago by xiaolai2020
  0

• Different inputs

  #124 opened 4 months ago by lipenghuai
  0

• #训练问题

  #105 opened a year ago by zhangshilong2000
  2

• 如何测试任意分辨率的图像？

  #114 opened a year ago by ljjcoder
  4

• 训练问题

  #103 opened a year ago by zhangshilong2000
  1

• how to install pyspng? use wheel?

  #123 opened 5 months ago by simple23212
  0

• Is there a way to run inference on rectangle images?

  #122 opened 5 months ago by karatuno
  0

• Not working that good on real world images

  #121 opened 7 months ago by Zihan-Liu-westlake
  0

• 效果真的可以

  #117 opened 9 months ago by Ma-Weijian
  0

• pretrained/CelebA-HQ_512.pkl _pickle.UnpicklingError: pickle data was truncated

  #120 opened 8 months ago by 136LYJ
  0

• About the frequency of snapshots

  #76 opened 2 years ago by kdavidlp123
  2

• RuntimeError: Given groups=1, weight of size [32, 5, 1, 1], expected input[8, 4, 512, 512] to have 5 channels, but got 4 channels instead

  #119 opened 8 months ago by 136LYJ
  1

• 512x512 image training error

  #78 opened 2 years ago by shyoon87
  1

• AssertionError: Generator.synthesis.dec.Dec_16x16.conv1.noise_const

  #116 opened 9 months ago by danielanojan
  0

• Problems in custom dataset training

  #113 opened a year ago by qwexacc
  2

• ImportError: No module name upfirdn2d_plugin "

  #104 opened a year ago by WJDNJSDJ
  3

• AssertionError on custom trained model inference

  #108 opened a year ago by Runzil
  1

• how to fine tune the model?

  #110 opened a year ago by Abbsalehi
  0

• Production of data sets

  #111 opened a year ago by qwexacc
  0

• RuntimeError: The size of tensor a (814) must match the size of tensor b (815) at non-singleton dimension 3

  #112 opened a year ago by abhishek7467
  3

• How to fine tune

  #107 opened a year ago by anntonio99
  2

• image paint

  #87 opened 2 years ago by lijain
  5

• 有没有简化版本的模型

  #109 opened a year ago by rubbish001
  0

• AssertionError

  #96 opened 2 years ago by clcllllll
  1

• Where in the code is the use of Conv-Unet for fine-tuning？

  #106 opened a year ago by MIAODRB
  0

• Application in Medical images

  #91 opened 2 years ago by javak87
  1

• training for 1024*512 images

  #94 opened 2 years ago by javak87
  1

• Training for 1024*1024 resolution took too much time

  #98 opened 2 years ago by javak87
  1

• How distributed training affects performance？

  #102 opened 2 years ago by tanbuzheng
  4

• There is a problem with the training program， torch.utils.cpp_extension.load(name=module_name, verbose=verbose_build, sources=sources, **build_kwargs)

  #101 opened 2 years ago by guangyhuang
  0

• About the evaluation of U-IDS/P-IDS

  #86 opened 2 years ago by Haoru
  16

• Is style manipulation also works for text?

  #100 opened 2 years ago by Xijieupenn
  0

• The difference between FID_metrics and evaluation script

  #99 opened 2 years ago by kdavidlp123
  0

• generate more plausible images

  #97 opened 2 years ago by javak87
  0

• Mask input in transformer blocks

  #95 opened 2 years ago by manuelaceron
  0

• Problem with grayscale image training

  #93 opened 2 years ago by javak87
  2

• train from scratch a gray scale with intensity between 0-2000

  #92 opened 2 years ago by javak87
  0

• Apply path length regularization

  #90 opened 2 years ago by lijain
  0

• How to export jit script or onnx

  #89 opened 2 years ago by casm-ahb
  0

• more gpus

  #83 opened 2 years ago
  1

• about Pluralistic Generation

  #88 opened 2 years ago by yumengWang112
  3

• image size train

  #85 opened 2 years ago by lijain
  3

• Getting a non-pluralistic inpainting

  #84 opened 2 years ago by Ash920
  2

• Error when using pretrained weights for 512*512 with cond=True

  #81 opened 2 years ago by yisakk
  0

• Error "CUDA Out of Memory" ):

  #82 opened 2 years ago by shyoon87
  0

• Something Dataloader error during training process.

  #80 opened 2 years ago by chencc5956
  1

• Error when testing without GPU on Colab

  #79 opened 2 years ago by MiladGhorbaniG
  0

• Place365-Standard dataset?

  #77 opened 2 years ago by wennycooper
  2

• How to determine the token is valid or invalid by mask?

  #75 opened 2 years ago by wennycooper
  2

• Train model for 50M images on Places365-Standard??

  #74 opened 2 years ago by wennycooper
  2