diff --git a/monai/networks/nets/diffusion_model_unet.py b/monai/networks/nets/diffusion_model_unet.py index cb0c69d033..fe627c7e24 100644 --- a/monai/networks/nets/diffusion_model_unet.py +++ b/monai/networks/nets/diffusion_model_unet.py @@ -1529,9 +1529,9 @@ class DiffusionModelUNet(nn.Module): upcast_attention: if True, upcast attention operations to full precision. dropout_cattn: if different from zero, this will be the dropout value for the cross-attention layers. include_fc: whether to include the final linear layer. Default to True. - use_combined_linear: whether to use a single linear layer for qkv projection, default to True. + use_combined_linear: whether to use a single linear layer for qkv projection, default to False. use_flash_attention: if True, use Pytorch's inbuilt flash attention for a memory efficient attention mechanism - (see https://pytorch.org/docs/2.2/generated/torch.nn.functional.scaled_dot_product_attention.html). + (see https://pytorch.org/docs/2.2/generated/torch.nn.functional.scaled_dot_product_attention.html), default to False. """ def __init__(