diff options
Diffstat (limited to 'modules/codeformer')
| -rw-r--r-- | modules/codeformer/codeformer_arch.py | 10 | ||||
| -rw-r--r-- | modules/codeformer/vqgan_arch.py | 6 |
2 files changed, 6 insertions, 10 deletions
diff --git a/modules/codeformer/codeformer_arch.py b/modules/codeformer/codeformer_arch.py index 11dcc3ee..45c70f84 100644 --- a/modules/codeformer/codeformer_arch.py +++ b/modules/codeformer/codeformer_arch.py @@ -1,14 +1,12 @@ # this file is copied from CodeFormer repository. Please see comment in modules/codeformer_model.py import math -import numpy as np import torch from torch import nn, Tensor import torch.nn.functional as F -from typing import Optional, List +from typing import Optional -from modules.codeformer.vqgan_arch import * -from basicsr.utils import get_root_logger +from modules.codeformer.vqgan_arch import VQAutoEncoder, ResBlock from basicsr.utils.registry import ARCH_REGISTRY def calc_mean_std(feat, eps=1e-5): @@ -163,8 +161,8 @@ class Fuse_sft_block(nn.Module): class CodeFormer(VQAutoEncoder): def __init__(self, dim_embd=512, n_head=8, n_layers=9, codebook_size=1024, latent_size=256, - connect_list=['32', '64', '128', '256'], - fix_modules=['quantize','generator']): + connect_list=('32', '64', '128', '256'), + fix_modules=('quantize', 'generator')): super(CodeFormer, self).__init__(512, 64, [1, 2, 2, 4, 4, 8], 'nearest',2, [16], codebook_size) if fix_modules is not None: diff --git a/modules/codeformer/vqgan_arch.py b/modules/codeformer/vqgan_arch.py index e7293683..b24a0394 100644 --- a/modules/codeformer/vqgan_arch.py +++ b/modules/codeformer/vqgan_arch.py @@ -5,11 +5,9 @@ VQGAN code, adapted from the original created by the Unleashing Transformers aut https://github.com/samb-t/unleashing-transformers/blob/master/models/vqgan.py ''' -import numpy as np import torch import torch.nn as nn import torch.nn.functional as F -import copy from basicsr.utils import get_root_logger from basicsr.utils.registry import ARCH_REGISTRY @@ -328,7 +326,7 @@ class Generator(nn.Module): @ARCH_REGISTRY.register() class VQAutoEncoder(nn.Module): - def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=[16], codebook_size=1024, emb_dim=256, + def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=None, codebook_size=1024, emb_dim=256, beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None): super().__init__() logger = get_root_logger() @@ -339,7 +337,7 @@ class VQAutoEncoder(nn.Module): self.embed_dim = emb_dim self.ch_mult = ch_mult self.resolution = img_size - self.attn_resolutions = attn_resolutions + self.attn_resolutions = attn_resolutions or [16] self.quantizer_type = quantizer self.encoder = Encoder( self.in_channels, |