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

.github/FUNDING.yml

@@ -1 +1 @@
-github: [lucidrains]
+github: [nousr, Veldrovive, lucidrains]

dalle2_pytorch/dalle2_pytorch.py

@@ -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:]))
@@ -1926,7 +1927,7 @@ class Unet(nn.Module):
                 hiddens.append(x)
 
             x = attn(x)
-            hiddens.append(x)
+            hiddens.append(x.contiguous())
 
             if exists(post_downsample):
                 x = post_downsample(x)
@@ -2172,6 +2173,7 @@ class Decoder(nn.Module):
         # random crop sizes (for super-resoluting unets at the end of cascade?)
 
         self.random_crop_sizes = cast_tuple(random_crop_sizes, len(image_sizes))
+        assert not exists(self.random_crop_sizes[0]), 'you would not need to randomly crop the image for the base unet'
 
         # predict x0 config
 

dalle2_pytorch/train_configs.py

@@ -225,6 +225,7 @@ class UnetConfig(BaseModel):
     self_attn: ListOrTuple(int)
     attn_dim_head: int = 32
     attn_heads: int = 16
+    init_cross_embed: bool = True
 
     class Config:
         extra = "allow"

dalle2_pytorch/version.py

@@ -1 +1 @@
-__version__ = '0.24.0'
+__version__ = '0.24.3'