Skip to content

Update distill.py to include device agnostic code for distill_mlp head and distillation_token #324

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
vivekh2000 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update distill.py to include device agnostic code for distill_mlp head and distillation_token #324

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions vit_pytorch/distill.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,7 @@ def __init__(
super().__init__()
assert (isinstance(student, (DistillableViT, DistillableT2TViT, DistillableEfficientViT))) , 'student must be a vision transformer'

device = 'cuda' if torch.cuda.is_available() else 'cpu'
self.teacher = teacher
self.student = student

Expand All @@ -125,12 +126,12 @@ def __init__(
self.alpha = alpha
self.hard = hard

self.distillation_token = nn.Parameter(torch.randn(1, 1, dim))
self.distillation_token = nn.Parameter(torch.randn(1, 1, dim,device=device))

self.distill_mlp = nn.Sequential(
nn.LayerNorm(dim) if mlp_layernorm else nn.Identity(),
nn.Linear(dim, num_classes)
)
).to(device)

def forward(self, img, labels, temperature = None, alpha = None, **kwargs):

Expand Down