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

blur sigma for upsampling training was 0.6 in the paper, make that the default value

Browse Source
This commit is contained in:
Phil Wang
2022-06-30 17:03:16 -07:00
parent 908ab83799
commit 8f2466f1cd
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
dalle2_pytorch/dalle2_pytorch.py
View File

@@ -1799,7 +1799,7 @@ class Decoder(nn.Module):
image_sizes = None, # for cascading ddpm, image size at each stage
random_crop_sizes = None, # whether to random crop the image at that stage in the cascade (super resoluting convolutions at the end may be able to generalize on smaller crops)
lowres_downsample_first = True, # cascading ddpm - resizes to lower resolution, then to next conditional resolution + blur
blur_sigma = (0.1, 0.2), # cascading ddpm - blur sigma
blur_sigma = 0.6, # cascading ddpm - blur sigma
blur_kernel_size = 3, # cascading ddpm - blur kernel size
clip_denoised = True,
clip_x_start = True,