aboutsummaryrefslogtreecommitdiff
path: root/extensions-builtin
diff options
context:
space:
mode:
Diffstat (limited to 'extensions-builtin')
-rw-r--r--extensions-builtin/LDSR/ldsr_model_arch.py4
-rw-r--r--extensions-builtin/LDSR/sd_hijack_ddpm_v1.py6
-rw-r--r--extensions-builtin/ScuNET/scunet_model_arch.py2
-rw-r--r--extensions-builtin/SwinIR/scripts/swinir_model.py2
-rw-r--r--extensions-builtin/SwinIR/swinir_model_arch.py2
-rw-r--r--extensions-builtin/SwinIR/swinir_model_arch_v2.py52
6 files changed, 34 insertions, 34 deletions
diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py
index 2173de79..7f450086 100644
--- a/extensions-builtin/LDSR/ldsr_model_arch.py
+++ b/extensions-builtin/LDSR/ldsr_model_arch.py
@@ -130,11 +130,11 @@ class LDSR:
im_og = im_og.resize((width_downsampled_pre, height_downsampled_pre), Image.LANCZOS)
else:
print(f"Down sample rate is 1 from {target_scale} / 4 (Not downsampling)")
-
+
# pad width and height to multiples of 64, pads with the edge values of image to avoid artifacts
pad_w, pad_h = np.max(((2, 2), np.ceil(np.array(im_og.size) / 64).astype(int)), axis=0) * 64 - im_og.size
im_padded = Image.fromarray(np.pad(np.array(im_og), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge'))
-
+
logs = self.run(model["model"], im_padded, diffusion_steps, eta)
sample = logs["sample"]
diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
index 57c02d12..631a08ef 100644
--- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
+++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py
@@ -460,7 +460,7 @@ class LatentDiffusionV1(DDPMV1):
self.instantiate_cond_stage(cond_stage_config)
self.cond_stage_forward = cond_stage_forward
self.clip_denoised = False
- self.bbox_tokenizer = None
+ self.bbox_tokenizer = None
self.restarted_from_ckpt = False
if ckpt_path is not None:
@@ -792,7 +792,7 @@ class LatentDiffusionV1(DDPMV1):
z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L )
# 2. apply model loop over last dim
- if isinstance(self.first_stage_model, VQModelInterface):
+ if isinstance(self.first_stage_model, VQModelInterface):
output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
force_not_quantize=predict_cids or force_not_quantize)
for i in range(z.shape[-1])]
@@ -890,7 +890,7 @@ class LatentDiffusionV1(DDPMV1):
if hasattr(self, "split_input_params"):
assert len(cond) == 1 # todo can only deal with one conditioning atm
- assert not return_ids
+ assert not return_ids
ks = self.split_input_params["ks"] # eg. (128, 128)
stride = self.split_input_params["stride"] # eg. (64, 64)
diff --git a/extensions-builtin/ScuNET/scunet_model_arch.py b/extensions-builtin/ScuNET/scunet_model_arch.py
index 8028918a..b51a8806 100644
--- a/extensions-builtin/ScuNET/scunet_model_arch.py
+++ b/extensions-builtin/ScuNET/scunet_model_arch.py
@@ -265,4 +265,4 @@ class SCUNet(nn.Module):
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
nn.init.constant_(m.bias, 0)
- nn.init.constant_(m.weight, 1.0) \ No newline at end of file
+ nn.init.constant_(m.weight, 1.0)
diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py
index 55dd94ab..0ba50487 100644
--- a/extensions-builtin/SwinIR/scripts/swinir_model.py
+++ b/extensions-builtin/SwinIR/scripts/swinir_model.py
@@ -150,7 +150,7 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
for w_idx in w_idx_list:
if state.interrupted or state.skipped:
break
-
+
in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
out_patch = model(in_patch)
out_patch_mask = torch.ones_like(out_patch)
diff --git a/extensions-builtin/SwinIR/swinir_model_arch.py b/extensions-builtin/SwinIR/swinir_model_arch.py
index 73e37cfa..93b93274 100644
--- a/extensions-builtin/SwinIR/swinir_model_arch.py
+++ b/extensions-builtin/SwinIR/swinir_model_arch.py
@@ -805,7 +805,7 @@ class SwinIR(nn.Module):
def forward(self, x):
H, W = x.shape[2:]
x = self.check_image_size(x)
-
+
self.mean = self.mean.type_as(x)
x = (x - self.mean) * self.img_range
diff --git a/extensions-builtin/SwinIR/swinir_model_arch_v2.py b/extensions-builtin/SwinIR/swinir_model_arch_v2.py
index 3ca9be78..dad22cca 100644
--- a/extensions-builtin/SwinIR/swinir_model_arch_v2.py
+++ b/extensions-builtin/SwinIR/swinir_model_arch_v2.py
@@ -241,7 +241,7 @@ class SwinTransformerBlock(nn.Module):
attn_mask = None
self.register_buffer("attn_mask", attn_mask)
-
+
def calculate_mask(self, x_size):
# calculate attention mask for SW-MSA
H, W = x_size
@@ -263,7 +263,7 @@ class SwinTransformerBlock(nn.Module):
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
- return attn_mask
+ return attn_mask
def forward(self, x, x_size):
H, W = x_size
@@ -288,7 +288,7 @@ class SwinTransformerBlock(nn.Module):
attn_windows = self.attn(x_windows, mask=self.attn_mask) # nW*B, window_size*window_size, C
else:
attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device))
-
+
# merge windows
attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
shifted_x = window_reverse(attn_windows, self.window_size, H, W) # B H' W' C
@@ -369,7 +369,7 @@ class PatchMerging(nn.Module):
H, W = self.input_resolution
flops = (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim
flops += H * W * self.dim // 2
- return flops
+ return flops
class BasicLayer(nn.Module):
""" A basic Swin Transformer layer for one stage.
@@ -447,7 +447,7 @@ class BasicLayer(nn.Module):
nn.init.constant_(blk.norm1.weight, 0)
nn.init.constant_(blk.norm2.bias, 0)
nn.init.constant_(blk.norm2.weight, 0)
-
+
class PatchEmbed(nn.Module):
r""" Image to Patch Embedding
Args:
@@ -492,7 +492,7 @@ class PatchEmbed(nn.Module):
flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1])
if self.norm is not None:
flops += Ho * Wo * self.embed_dim
- return flops
+ return flops
class RSTB(nn.Module):
"""Residual Swin Transformer Block (RSTB).
@@ -531,7 +531,7 @@ class RSTB(nn.Module):
num_heads=num_heads,
window_size=window_size,
mlp_ratio=mlp_ratio,
- qkv_bias=qkv_bias,
+ qkv_bias=qkv_bias,
drop=drop, attn_drop=attn_drop,
drop_path=drop_path,
norm_layer=norm_layer,
@@ -622,7 +622,7 @@ class Upsample(nn.Sequential):
else:
raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
super(Upsample, self).__init__(*m)
-
+
class Upsample_hf(nn.Sequential):
"""Upsample module.
@@ -642,7 +642,7 @@ class Upsample_hf(nn.Sequential):
m.append(nn.PixelShuffle(3))
else:
raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
- super(Upsample_hf, self).__init__(*m)
+ super(Upsample_hf, self).__init__(*m)
class UpsampleOneStep(nn.Sequential):
@@ -667,8 +667,8 @@ class UpsampleOneStep(nn.Sequential):
H, W = self.input_resolution
flops = H * W * self.num_feat * 3 * 9
return flops
-
-
+
+
class Swin2SR(nn.Module):
r""" Swin2SR
@@ -699,7 +699,7 @@ class Swin2SR(nn.Module):
def __init__(self, img_size=64, patch_size=1, in_chans=3,
embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6),
- window_size=7, mlp_ratio=4., qkv_bias=True,
+ window_size=7, mlp_ratio=4., qkv_bias=True,
drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv',
@@ -764,7 +764,7 @@ class Swin2SR(nn.Module):
num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=self.mlp_ratio,
- qkv_bias=qkv_bias,
+ qkv_bias=qkv_bias,
drop=drop_rate, attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results
norm_layer=norm_layer,
@@ -776,7 +776,7 @@ class Swin2SR(nn.Module):
)
self.layers.append(layer)
-
+
if self.upsampler == 'pixelshuffle_hf':
self.layers_hf = nn.ModuleList()
for i_layer in range(self.num_layers):
@@ -787,7 +787,7 @@ class Swin2SR(nn.Module):
num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=self.mlp_ratio,
- qkv_bias=qkv_bias,
+ qkv_bias=qkv_bias,
drop=drop_rate, attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results
norm_layer=norm_layer,
@@ -799,7 +799,7 @@ class Swin2SR(nn.Module):
)
self.layers_hf.append(layer)
-
+
self.norm = norm_layer(self.num_features)
# build the last conv layer in deep feature extraction
@@ -829,10 +829,10 @@ class Swin2SR(nn.Module):
self.conv_aux = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
self.conv_after_aux = nn.Sequential(
nn.Conv2d(3, num_feat, 3, 1, 1),
- nn.LeakyReLU(inplace=True))
+ nn.LeakyReLU(inplace=True))
self.upsample = Upsample(upscale, num_feat)
self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
-
+
elif self.upsampler == 'pixelshuffle_hf':
self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
nn.LeakyReLU(inplace=True))
@@ -846,7 +846,7 @@ class Swin2SR(nn.Module):
nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
nn.LeakyReLU(inplace=True))
self.conv_last_hf = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
-
+
elif self.upsampler == 'pixelshuffledirect':
# for lightweight SR (to save parameters)
self.upsample = UpsampleOneStep(upscale, embed_dim, num_out_ch,
@@ -905,7 +905,7 @@ class Swin2SR(nn.Module):
x = self.patch_unembed(x, x_size)
return x
-
+
def forward_features_hf(self, x):
x_size = (x.shape[2], x.shape[3])
x = self.patch_embed(x)
@@ -919,7 +919,7 @@ class Swin2SR(nn.Module):
x = self.norm(x) # B L C
x = self.patch_unembed(x, x_size)
- return x
+ return x
def forward(self, x):
H, W = x.shape[2:]
@@ -951,7 +951,7 @@ class Swin2SR(nn.Module):
x = self.conv_after_body(self.forward_features(x)) + x
x_before = self.conv_before_upsample(x)
x_out = self.conv_last(self.upsample(x_before))
-
+
x_hf = self.conv_first_hf(x_before)
x_hf = self.conv_after_body_hf(self.forward_features_hf(x_hf)) + x_hf
x_hf = self.conv_before_upsample_hf(x_hf)
@@ -977,15 +977,15 @@ class Swin2SR(nn.Module):
x_first = self.conv_first(x)
res = self.conv_after_body(self.forward_features(x_first)) + x_first
x = x + self.conv_last(res)
-
+
x = x / self.img_range + self.mean
if self.upsampler == "pixelshuffle_aux":
return x[:, :, :H*self.upscale, :W*self.upscale], aux
-
+
elif self.upsampler == "pixelshuffle_hf":
x_out = x_out / self.img_range + self.mean
return x_out[:, :, :H*self.upscale, :W*self.upscale], x[:, :, :H*self.upscale, :W*self.upscale], x_hf[:, :, :H*self.upscale, :W*self.upscale]
-
+
else:
return x[:, :, :H*self.upscale, :W*self.upscale]
@@ -1014,4 +1014,4 @@ if __name__ == '__main__':
x = torch.randn((1, 3, height, width))
x = model(x)
- print(x.shape) \ No newline at end of file
+ print(x.shape)
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 09:40:54 +0000