Skip to content
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

Cuda GPU option for build_sam.py #798

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+8 −3
Open

Cuda GPU option for build_sam.py #798

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0c2ef95
My cuda gpu code updates
bhanu-pm Dec 1, 2024
35a5490
Updated build_sam.py
bhanu-pm Dec 1, 2024
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
11 changes: 8 additions & 3 deletions segment_anything/build_sam.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,36 +11,39 @@
from .modeling import ImageEncoderViT, MaskDecoder, PromptEncoder, Sam, TwoWayTransformer


def build_sam_vit_h(checkpoint=None):
def build_sam_vit_h(checkpoint=None, device='cpu'):
return _build_sam(
encoder_embed_dim=1280,
encoder_depth=32,
encoder_num_heads=16,
encoder_global_attn_indexes=[7, 15, 23, 31],
checkpoint=checkpoint,
device=device
)


build_sam = build_sam_vit_h


def build_sam_vit_l(checkpoint=None):
def build_sam_vit_l(checkpoint=None, device='cpu'):
return _build_sam(
encoder_embed_dim=1024,
encoder_depth=24,
encoder_num_heads=16,
encoder_global_attn_indexes=[5, 11, 17, 23],
checkpoint=checkpoint,
device=device
)


def build_sam_vit_b(checkpoint=None):
def build_sam_vit_b(checkpoint=None, device='cpu'):
return _build_sam(
encoder_embed_dim=768,
encoder_depth=12,
encoder_num_heads=12,
encoder_global_attn_indexes=[2, 5, 8, 11],
checkpoint=checkpoint,
device=device
)


Expand All @@ -58,6 +61,7 @@ def _build_sam(
encoder_num_heads,
encoder_global_attn_indexes,
checkpoint=None,
device='cpu'
):
prompt_embed_dim = 256
image_size = 1024
Expand Down Expand Up @@ -99,6 +103,7 @@ def _build_sam(
pixel_mean=[123.675, 116.28, 103.53],
pixel_std=[58.395, 57.12, 57.375],
)
sam.to(device)
sam.eval()
if checkpoint is not None:
with open(checkpoint, "rb") as f:
Expand Down