TypeError: forward() got an unexpected keyword argument 'c'

[c1a1o1]

D:\anaconda3\python.exe D:\work\3di2i-translation\3di2i-translation-master\run_train.py
D:\anaconda3\lib\site-packages\hydra\core\default_element.py:122: UserWarning: In 'spec/paper256': Usage of deprecated keyword in package header '# @Package group'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
warnings.warn(
D:\anaconda3\lib\site-packages\hydra\core\default_element.py:122: UserWarning: In 'model/stylenerf_afhq': Usage of deprecated keyword in package header '# @Package group'.
See https://hydra.cc/docs/next/upgrades/1.0_to_1.1/changes_to_package_header for more information
warnings.warn(
D:/work/3di2i-translation/3di2i-translation-master/output D:/work/3di2i-translation/3di2i-translation-master/output\00019-afhq-paper256-stylenerf_afhq-noaug-resumecustom-freezed9

Training options:
rank: 0
gpu: 0
num_gpus: 1
nodes: 1
world_size: 1
dist_url: env://
launcher: spawn
partition: null
comment: null
timeout: 4320
job_dir: ''
image_snapshot_ticks: 25
network_snapshot_ticks: 50
metrics:

• fid50k_full
  random_seed: 2
  training_set_kwargs:
  class_name: training.dataset.ImageFolderDataset
  path: D:/work/3di2i-translation/3di2i-translation-master/datasets/afhq.zip
  resolution: 256
  use_labels: false
  max_size: 14630
  xflip: false
  data_loader_kwargs:
  pin_memory: true
  num_workers: 1
  prefetch_factor: 2
  generation_with_image: false
  G_kwargs:
  class_name: training.networks.Generator
  z_dim: 512
  w_dim: 512
  mapping_kwargs:
  num_layers: ${spec.map}
  freeze_nerf_mappingnetwork: false
  freeze_synthesisblock_mappingnetwork: false
  synthesis_kwargs:
  num_fp16_res: ${num_fp16_res}
  channel_base: 1
  channel_max: 1024
  conv_clamp: 256
  kernel_size: 1
  architecture: skip
  upsample_mode: pixelshuffle
  z_dim_bg: 32
  z_dim: 0
  resolution_vol: 32
  resolution_start: 256
  rgb_out_dim: 64
  use_noise: false
  module_name: training.stylenerf.NeRFSynthesisNetwork
  no_bbox: true
  margin: 0
  magnitude_ema_beta: -1
  freeze_nerf: true
  freeze_img_nerf: false
  freeze_synthesisblock: false
  camera_kwargs:
  range_v:
  - 1.4157963267948965
  - 1.7257963267948966
  range_u:
  - -0.3
  - 0.3
  range_radius:
  - 1.0
  - 1.0
  depth_range:
  - 0.88
  - 1.12
  fov: 12
  gaussian_camera: true
  angular_camera: true
  depth_transform: null
  dists_normalized: false
  ray_align_corner: false
  bg_start: 0.5
  renderer_kwargs:
  n_bg_samples: 4
  n_ray_samples: 14
  abs_sigma: false
  hierarchical: true
  no_background: false
  foreground_kwargs:
  positional_encoding: normal
  downscale_p_by: 1
  use_style: StyleGAN2
  predict_rgb: true
  use_viewdirs: false
  abs_sigma: false
  final_sigmoid_activation: false
  normalized_feat: true
  background_kwargs:
  positional_encoding: normal
  hidden_size: 64
  n_blocks: 4
  downscale_p_by: 1
  skips: []
  inverse_sphere: true
  use_style: StyleGAN2
  predict_rgb: true
  use_viewdirs: false
  final_sigmoid_activation: false
  normalized_feat: true
  upsampler_kwargs:
  channel_base: ${model.G_kwargs.synthesis_kwargs.channel_base}
  channel_max: ${model.G_kwargs.synthesis_kwargs.channel_max}
  no_2d_renderer: false
  no_residual_img: true
  block_reses: null
  shared_rgb_style: false
  upsample_type: bilinear
  progressive: true
  n_reg_samples: 16
  reg_full: true
  step: step1
  D_kwargs:
  class_name: training.stylenerf.Discriminator
  epilogue_kwargs:
  mbstd_group_size: ${spec.mbstd}
  num_fp16_res: 4
  channel_base: 0.5
  channel_max: 512
  conv_clamp: 256
  architecture: skip
  progressive: true
  lowres_head: 256
  upsample_type: bilinear
  resize_real_early: true
  block_kwargs:
  freeze_layers: 9
  G_opt_kwargs:
  class_name: torch.optim.Adam
  lr: 0.0025
  betas:
  • 0
  • 0.99
    eps: 1.0e-08
    D_opt_kwargs:
    class_name: torch.optim.Adam
    lr: 0.0025
    betas:
  • 0
  • 0.99
    eps: 1.0e-08
    loss_kwargs:
    class_name: training.loss.StyleGAN2Loss
    r1_gamma: 0.5
    pl_batch_shrink: 2
    pl_decay: 0.01
    pl_weight: 2
    style_mixing_prob: 0.9
    curriculum:
  • 5000
  • 50000
    use_dive_loss: false
    spec:
    name: paper256
    ref_gpus: 8
    kimg: 25000
    mb: 64
    mbstd: 8
    fmaps: 0.5
    lrate: 0.0025
    lrate_disc: 0.0025
    gamma: 0.5
    ema: 20
    ramp: null
    map: 8
    lrate_adapted: 0.0002
    beta1: 0.5
    total_kimg: 25000
    batch_size: 64
    batch_gpu: 8
    ema_kimg: 20
    ema_rampup: null
    resume_pkl: D:/work/3di2i-translation/3di2i-translation-master/pretrained/ffhq_256.pkl
    ada_kimg: 100
    num_fp16_res: 4
    allow_tf32: false
    debug: false
    run_dir: D:/work/3di2i-translation/3di2i-translation-master/output\00019-afhq-paper256-stylenerf_afhq-noaug-resumecustom-freezed9

Output directory: D:/work/3di2i-translation/3di2i-translation-master/output\00019-afhq-paper256-stylenerf_afhq-noaug-resumecustom-freezed9
Training data: D:/work/3di2i-translation/3di2i-translation-master/datasets/afhq.zip
Training duration: 25000 kimg
Number of images: 14630
Image resolution: 256
Conditional model: False
Dataset x-flips: False

Creating output directory...
Launching processes...
wandb: W&B API key is configured. Use wandb login --relogin to force relogin
wandb: wandb version 0.16.4 is available! To upgrade, please run:
wandb: $ pip install wandb --upgrade
wandb: Tracking run with wandb version 0.13.3
wandb: Run data is saved locally in D:\work\3di2i-translation\3di2i-translation-master\outputs\2024-03-21\18-04-50\wandb\run-20240321_180457-ogrh0eit
wandb: Run wandb offline to turn off syncing.
wandb: Syncing run hopeful-plant-18
wandb: View project at https://wandb.ai/c1a1p1/StyleNeRF
wandb: View run at https://wandb.ai/c1a1p1/StyleNeRF/runs/ogrh0eit
Loading training set...

Num images: 14630
Image shape: [3, 256, 256]
Label shape: [0]

Constructing networks...
Resuming from "D:/work/3di2i-translation/3di2i-translation-master/pretrained/ffhq_256.pkl"
Setting up PyTorch plugin "bias_act_plugin"... Done.
D:\anaconda3\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\TensorShape.cpp:3484.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Setting up PyTorch plugin "upfirdn2d_plugin"... Done.

Generator Parameters Buffers Output shape Datatype

---

mapping_nerf.fc0 262656 - [8, 512] float32
mapping_nerf.fc1 262656 - [8, 512] float32
mapping_nerf.fc2 262656 - [8, 512] float32
mapping_nerf.fc3 262656 - [8, 512] float32
mapping_nerf.fc4 262656 - [8, 512] float32
mapping_nerf.fc5 262656 - [8, 512] float32
mapping_nerf.fc6 262656 - [8, 512] float32
mapping_nerf.fc7 262656 - [8, 512] float32
mapping_nerf - 512 [8, 10, 512] float32
mapping.fc0 262656 - [8, 512] float32
mapping.fc1 262656 - [8, 512] float32
mapping.fc2 262656 - [8, 512] float32
mapping.fc3 262656 - [8, 512] float32
mapping.fc4 262656 - [8, 512] float32
mapping.fc5 262656 - [8, 512] float32
mapping.fc6 262656 - [8, 512] float32
mapping.fc7 262656 - [8, 512] float32
mapping - 512 [8, 7, 512] float32
synthesis.fg_nerf.fc_in 38588 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.0 82176 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.1 82176 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.2 82176 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.3 82176 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.4 82176 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.5 82176 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.6 82176 16 [112, 128, 32, 40] float32
synthesis.fg_nerf.sigma_out 65793 - [112, 1, 32, 40] float32
synthesis.fg_nerf.feat_out 73920 - [112, 64, 32, 40] float32
synthesis.fg_nerf.to_rgb 195 16 [112, 3, 32, 40] float32
synthesis.fg_nerf:0 - - [8, 17920, 67] float32
synthesis.fg_nerf:1 - - [8, 17920, 1] float32
synthesis.fg_nerf.fc_in - - [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.0 - - [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.1 - - [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.2 - - [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.3 - - [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.4 - - [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.5 - - [112, 128, 32, 40] float32
synthesis.fg_nerf.blocks.6 - - [112, 128, 32, 40] float32
synthesis.fg_nerf.sigma_out - - [112, 1, 32, 40] float32
synthesis.fg_nerf.feat_out - - [112, 64, 32, 40] float32
synthesis.fg_nerf.to_rgb - - [112, 3, 32, 40] float32
synthesis.fg_nerf:0 - - [8, 17920, 67] float32
synthesis.fg_nerf:1 - - [8, 17920, 1] float32
synthesis.bg_nerf.fc_in 7232 16 [32, 64, 32, 40] float32
synthesis.bg_nerf.blocks.0 4160 16 [32, 64, 32, 40] float32
synthesis.bg_nerf.blocks.1 4160 16 [32, 64, 32, 40] float32
synthesis.bg_nerf.blocks.2 4160 16 [32, 64, 32, 40] float32
synthesis.bg_nerf.sigma_out 65 - [32, 1, 32, 40] float32
synthesis.bg_nerf.feat_out 4160 - [32, 64, 32, 40] float32
synthesis.bg_nerf.to_rgb 195 16 [32, 3, 32, 40] float32
synthesis.bg_nerf:0 - - [8, 5120, 67] float32
synthesis.bg_nerf:1 - - [8, 5120, 1] float32
synthesis.b64.conv0 395968 48 [8, 512, 64, 64] float32
synthesis.b64.conv1 525312 16 [8, 512, 64, 64] float32
synthesis.b64.torgb 264195 - [8, 3, 64, 64] float32
synthesis.b64:0 - 16 [8, 512, 64, 64] float32
synthesis.b64:1 - - [8, 3, 64, 64] float32
synthesis.b128.conv0 476992 48 [8, 256, 128, 128] float16
synthesis.b128.conv1 197120 16 [8, 256, 128, 128] float16
synthesis.b128.torgb 132099 - [8, 3, 128, 128] float16
synthesis.b128:0 - 16 [8, 256, 128, 128] float16
synthesis.b128:1 - - [8, 3, 128, 128] float32
synthesis.b256.conv0 185248 48 [8, 128, 256, 256] float16
synthesis.b256.conv1 82176 16 [8, 128, 256, 256] float16
synthesis.b256.torgb 66051 - [8, 3, 256, 256] float16
synthesis.b256:0 - 16 [8, 128, 256, 256] float16
synthesis.b256:1 - - [8, 3, 256, 256] float32
synthesis.b64.conv0 - - [8, 512, 64, 128] float32
synthesis.b64.conv1 - - [8, 512, 64, 128] float32
synthesis.b64.torgb - - [8, 3, 64, 128] float32
synthesis.b128.conv0 - - [8, 256, 64, 128] float16
synthesis.b128.conv1 - - [8, 256, 64, 128] float16
synthesis.b128.torgb - - [8, 3, 64, 128] float16
synthesis.b128:0 - - [8, 256, 64, 128] float16
synthesis.b128:1 - - [8, 3, 64, 128] float32
synthesis.b256.conv0 - - [8, 128, 64, 128] float16
synthesis.b256.conv1 - - [8, 128, 64, 128] float16
synthesis.b256.torgb - - [8, 3, 64, 128] float16
synthesis.b256:0 - - [8, 128, 64, 128] float16
synthesis.b256:1 - - [8, 3, 64, 128] float32
synthesis - 1 - -

---

Total 7305517 1489 - -

Error executing job with overrides: []
wandb: Waiting for W&B process to finish... (failed 1). Press Ctrl-C to abort syncing.
Traceback (most recent call last):
File "D:\work\3di2i-translation\3di2i-translation-master\run_train.py", line 378, in main
subprocess_fn(rank=0, args=args)
File "D:\work\3di2i-translation\3di2i-translation-master\run_train.py", line 301, in subprocess_fn
training_loop.training_loop(**args)
File "D:\work\3di2i-translation\3di2i-translation-master\training\training_loop.py", line 159, in training_loop
misc.print_module_summary(D, [img, c], rank=rank) # todo: keras to torch ？
File "D:\work\3di2i-translation\3di2i-translation-master\torch_utils\misc.py", line 241, in print_module_summary
outputs = module(*inputs)
File "D:\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1538, in _call_impl
result = forward_call(*args, **kwargs)
File "D:\work\3di2i-translation\3di2i-translation-master\training\stylenerf.py", line 2278, in forward
logits = self.b4(x, img, cmap, c=c.detach())
File "D:\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 1538, in _call_impl
result = forward_call(*args, **kwargs)
TypeError: forward() got an unexpected keyword argument 'c'

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.

[sen-mao]

Whether labels are added when preparing the dataset ?

[561019]

你好，我在复现过程中也出现这个问题，该怎么解决