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

Blip2 #2

Open
wants to merge 11 commits into
base: main
Choose a base branch
from
Open

Blip2 #2

Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
c7285e7
Update clip_baseline.py
lenguyen2592004 Aug 8, 2024
d14fa24
Update clip_baseline.py
lenguyen2592004 Aug 8, 2024
a8121de
Update comclip.py
lenguyen2592004 Aug 8, 2024
a1302e4
Create blip2.py
lenguyen2592004 Aug 8, 2024
2a23c5a
Update blip2.py
lenguyen2592004 Aug 8, 2024
7b1e3c2
Update blip2.py
lenguyen2592004 Aug 8, 2024
284fb46
Update blip2.py
lenguyen2592004 Aug 8, 2024
1cbb881
Update blip2.py
lenguyen2592004 Aug 8, 2024
1bd6b70
Update blip2.py
lenguyen2592004 Aug 8, 2024
7e919f9
Update comclip.sh
lenguyen2592004 Aug 8, 2024
4652e9e
Update demo.py
lenguyen2592004 Aug 18, 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
Prev Previous commit
Next Next commit
Update blip2.py
@lenguyen2592004
lenguyen2592004 authored Aug 8, 2024

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Verified
Learn about vigilant mode
commit 284fb46cd79af91e363c103c20a1b9c72e90904a
4 changes: 2 additions & 2 deletions image_retrieval/blip2.py
View file
Original file line number Diff line number Diff line change
@@ -35,7 +35,7 @@ def subimage_score_embedding(image, text):
image_inputs = processor(images=image, return_tensors="pt")
image_input = model.get_image_features(**image_inputs).cuda(device)
text_inputs = tokenizer(caption, padding=True, return_tensors="pt")
text_input= = model.get_text_features(**text_inputs).cuda(device)
text_input = model.get_text_features(**text_inputs).cuda(device)
with torch.no_grad():
original_image_embed = image_input.float()
original_text_embed = text_input.float()
@@ -51,7 +51,7 @@ def comclip_one_pair(row_id, caption, image_id):
image_inputs = processor(images=image, return_tensors="pt")
image_input = model.get_image_features(**image_inputs).cuda(device)
text_inputs = tokenizer(caption, padding=True, return_tensors="pt")
text_input= = model.get_text_features(**text_inputs).cuda(device)
text_input = model.get_text_features(**text_inputs).cuda(device)
with torch.no_grad():
original_image_embed = image_input.float()
original_text_embed = text_input.float()