Giux22's picture
Create README.md
b1155de verified

igual que semana2-figuras_libres-1 pero con

block_out_channels=(128, 128, 256, 256, 256, 512, 512), # the number of output channels for each UNet block down_block_types=( "DownBlock2D", # a regular ResNet downsampling block "DownBlock2D", "DownBlock2D", "DownBlock2D", "DownBlock2D", "AttnDownBlock2D", # a ResNet downsampling block with spatial self-attention "DownBlock2D", ),