Closed KyriaAnnwyn closed 2 years ago
Found it in stylenerf_ffhq.yaml: G_kwargs: class_name: "training.networks.Generator" z_dim: 512 w_dim: 512
mapping_kwargs:
num_layers: ${spec.map}
synthesis_kwargs:
# global settings
num_fp16_res: ${num_fp16_res}
channel_base: 1
channel_max: 1024
conv_clamp: 256
kernel_size: 1
architecture: skip
upsample_mode: "nn_cat"
z_dim_bg: 32
z_dim: 0
resolution_vol: 32
resolution_start: 32
rgb_out_dim: 256 <------------------------- this should be changed to 64
use_noise: False
module_name: "training.stylenerf.NeRFSynthesisNetwork"
no_bbox: True
margin: 0
magnitude_ema_beta: 0.999
Next problem:
Error loading: synthesis.b64.conv0.adapter.0.weight torch.Size([128, 512, 1, 1]) torch.Size([128, 1024, 1, 1])
Found which param makes these changes: upsample_mode: "nn_cat" should be changed to "pixelshuffle"
I get this error when loading pretrained network. The size of the layer was changed: Error loading: synthesis.fg_nerf.feat_out.weight torch.Size([64, 128, 1, 1]) torch.Size([256, 128, 1, 1])
Where can I modify the structure of generator to be the same as in pretrained checkpoint?