aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-19 09:44:19 +01:00
Code Issues Packages Projects Releases Wiki Activity

offer way to turn off initial cross embed convolutional module, for debugging upsampler artifacts

Browse Source
This commit is contained in:
Phil Wang
2022-07-15 17:29:10 -07:00
parent a58a370d75
commit a2ee3fa3cc
3 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
dalle2_pytorch/dalle2_pytorch.py
View File

@@ -1550,6 +1550,7 @@ class Unet(nn.Module):
init_conv_kernel_size = 7,
resnet_groups = 8,
num_resnet_blocks = 2,
init_cross_embed = True,
init_cross_embed_kernel_sizes = (3, 7, 15),
cross_embed_downsample = False,
cross_embed_downsample_kernel_sizes = (2, 4),
@@ -1578,7 +1579,7 @@ class Unet(nn.Module):
init_channels = channels if not lowres_cond else channels * 2 # in cascading diffusion, one concats the low resolution image, blurred, for conditioning the higher resolution synthesis
init_dim = default(init_dim, dim)
self.init_conv = CrossEmbedLayer(init_channels, dim_out = init_dim, kernel_sizes = init_cross_embed_kernel_sizes, stride = 1)
self.init_conv = CrossEmbedLayer(init_channels, dim_out = init_dim, kernel_sizes = init_cross_embed_kernel_sizes, stride = 1) if init_cross_embed else nn.Conv2d(init_channels, init_dim, init_conv_kernel_size, padding = init_conv_kernel_size // 2)
dims = [init_dim, *map(lambda m: dim * m, dim_mults)]
in_out = list(zip(dims[:-1], dims[1:]))