Skip to content

Fix hardcoded input dim in DiffusionModelEncoder #8514

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: dev
Choose a base branch
from
Open

Fix hardcoded input dim in DiffusionModelEncoder #8514

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
595ca84
fix: dynamic input dim in DiffusionModelEncoder
IamTingTing Jul 18, 2025
e6b440f
Merge branch 'dev' into fix-encoder-dim
KumoLiu Aug 1, 2025
f8fcb61
Merge branch 'dev' into fix-encoder-dim
ericspod Aug 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion monai/networks/nets/diffusion_model_unet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@

import math
from collections.abc import Sequence
from typing import Optional

import torch
from torch import nn
Expand Down Expand Up @@ -2005,7 +2006,7 @@ def __init__(

self.down_blocks.append(down_block)

self.out = nn.Sequential(nn.Linear(4096, 512), nn.ReLU(), nn.Dropout(0.1), nn.Linear(512, self.out_channels))
self.out: Optional[nn.Module] = None

def forward(
self,
Expand Down Expand Up @@ -2048,6 +2049,12 @@ def forward(
h, _ = downsample_block(hidden_states=h, temb=emb, context=context)

h = h.reshape(h.shape[0], -1)

# 5. out
if self.out is None:
self.out = nn.Sequential(
nn.Linear(h.shape[1], 512), nn.ReLU(), nn.Dropout(0.1), nn.Linear(512, self.out_channels)
)
output: torch.Tensor = self.out(h)

return output
Loading