mirror of
https://github.com/openai/CLIP.git
synced 2026-11-05 01:37:26 +00:00
[GH-ISSUE #172] Get different image_features in different environment? #150
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
openai/CLIP#150
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @MagicCodess on GitHub (Nov 4, 2021).
Original GitHub issue: https://github.com/openai/CLIP/issues/172
`import torch
import clip
from PIL import Image
device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)
image = preprocess(Image.open("CLIP.png")).unsqueeze(0).to(device)
text = clip.tokenize(["a diagram", "a dog", "a cat"]).to(device)
with torch.no_grad():
image_features = model.encode_image(image)`
This feautures are different in different environment, is there a method to fix it?
@jongwook commented on GitHub (Nov 16, 2021):
Unfortunately there are slight numerical differences depending on which hardware the model was run on. See #114 and #13.