NVlabs/stylegan2-ada

Issues

• compatibility issue between the PyTorch version, CUDA version, and possibly the GCC version

  #120 opened 3 months ago by PavelApis
  0

• No GPU Devices Found

  #74 opened 4 years ago by shahik
  14

• Structure of a new training data set

  #117 opened 9 months ago by DanMenCas
  2

• FFHQ download script broken

  #115 opened 2 years ago by kyleliang919
  6

• Projection.py, Why the reconstruction of some images and not good wile for some images it is better

  #118 opened 8 months ago by dinusha94
  0

• tensorflow.python.framework.errors_impl.NotFoundError: /root/stylegan2_train/dnnlib/tflib/_cudacache/fused_bias_act_ec21d79f0dc288505704f796449a968e.so: undefined symbol: _ZN10tensorflow12OpDefBuilder6OutputESs

  #79 opened 4 years ago by Maglanyulan
  2

• How to recover if training is interrupted

  #116 opened a year ago by xyt000-xjj
  0

• "W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile. " & "tensorflow.python.framework.errors_impl.NotFoundError: /home/paperspace/stylegan2/dnnlib/tflib/_cudacache/fused_bias_act_afa4ff47e864043461655b92eafcdf5f.so: undefined symbol: _ZN10tensorflow12OpDefBuilder5InputESs"

  #101 opened 4 years ago by Jinyuan7
  1

• ModuleNotFoundError: No module named 'tensorflow.contrib'

  #82 opened 4 years ago by tempdeltavalue
  2

• Error: Unable to allocate 0 bytes for an array with shape

  #105 opened 3 years ago by DenkingOfficial
  2

• Sorry, but I suspect your FID is fake

  #100 opened 4 years ago by johnzlj
  8

• Don't use pickle to share weights

  #102 opened 3 years ago by unrealwill
  3

• Model conversion to tf.keras.Model (external application)

  #114 opened 2 years ago by Nikolai10
  0

• How to show real and fake loss in Colab?

  #113 opened 2 years ago by LongCao-HUST
  0

• NotImplementedError: Cannot convert a symbolic Tensor (Train_gpu0/Loss_R1/gradients/Train_gpu0/Augment_1/transform/ImageProjectiveTransformV2_grad/flat_transforms_to_matrices/strided_slice:0) to a numpy array.

  #112 opened 3 years ago by kay-aki
  0

• NVCC error. Compilation of custom CUDA ops on Windows 10 for Tensorflow 2.x

  #104 opened 3 years ago by uladzislau-varabei
  5

• Setting up TensorFlow plugin "fused_bias_act.cu": Compiling... Failed!

  #91 opened 4 years ago by heheal
  7

• ValueError: axes don't match array, images will work one run and not work the next

  #110 opened 3 years ago by lowlypalace
  0

• Continue training

  #106 opened 3 years ago by vivekbharadhwajsa
  4

• transfer learning with custom dataset has dominant influence

  #109 opened 3 years ago by Guest-01
  2

• StyleGAN2 Pickle File not working

  #108 opened 3 years ago by Thunder003
  0

• nvcc fatal

  #107 opened 3 years ago by d8oss
  0

• Unrecognized arguments

  #94 opened 4 years ago by LGTiscar
  2

• (gen_img[:, 0, 0, 0] * 0 + loss_Gpl) ... but why?

  #103 opened 3 years ago by Mwni
  1

• Training images suddenly flipped.

  #95 opened 4 years ago by Randy-H0
  2

• Legal Question: Using StyleGAN2 ADA as a public museum?

  #93 opened 4 years ago by MartinSpengler
  3

• I'm sorry, but I suspect your FID is fake

  #99 opened 4 years ago by johnzlj
  0

• Range for heuristic r_t and ADA issues

  #98 opened 4 years ago by hojaeklee
  0

• Convert custom images to TFRecord failed | invalid syntax

  #97 opened 4 years ago by wangzizhe
  0

• When "--aug" is not "noaug", the "--mirror=1" will be invalid?

  #96 opened 4 years ago by chengkeng
  0

• NVCC error compiling fused_bias_act.cpp

  #72 opened 4 years ago by arruw
  5

• TFRecords size increase

  #92 opened 4 years ago by LGTiscar
  1

• question on fid50k_full metric after resuming training on a larger dataset

  #90 opened 4 years ago by MoemaMike
  0

• broaden domain adaptation

  #89 opened 4 years ago by samurzl
  1

• dataset_tool.py create_from_images PIL.UnidentifiedImageError on Colab

  #87 opened 4 years ago by MoemaMike
  1

• crazy slowdown in processing time in stylegan2-ada/train.py --resume on Colab

  #88 opened 4 years ago by MoemaMike
  4

• learning rate schedule

  #86 opened 4 years ago by ink1
  0

• Training custom dataset from pickle - error: --res cannot exceed maximum available resolution in the dataset

  #85 opened 4 years ago by ktoksu
  2

• convert_to_uint8

  #84 opened 4 years ago by slala2121
  0

• No GPU devices found with CUDA 11.2

  #83 opened 4 years ago by pjdervan
  2

• ValueError: Too many dimensions

  #75 opened 4 years ago by ramnoob
  3

• Crashes on "Loading networks from" when run from subprocess module (cmd works fine) (WINDOWS! NOT LINUX)

  #81 opened 4 years ago by FlashlightET
  0

• enhancement - pytorch - support for microsoft / deepspeed wrapper

  #80 opened 4 years ago by johndpope
  0

• Training time is very slow with Nvidia A100

  #78 opened 4 years ago by arunraman
  2

• Generate:train afhqcat and use model to generate images

  #76 opened 4 years ago by aisdn
  0

• How to Upsample images before execute transformation?

  #77 opened 4 years ago by MindlessCoder-jtc
  0

• Need some training advice

  #69 opened 4 years ago by matthewchung74
  0

• changing batch size and timing

  #73 opened 4 years ago by ethem-kinginthenorth
  0

• NVCC error compiling fused_bias_act.cpp

  #71 opened 4 years ago by arruw
  1

• where to get ffhq pretrained models for resolution 256*256

  #70 opened 4 years ago by X-niper
  0