Comments (3)
Thought it might be easier to just re-use OpenAI's interface here https://github.com/openai/CLIP
If you have an open_clip checkpoint saved at the path open_clip_checkpoint_pth
you can run the following code to store an OpenAI CLIP compatible checkpoint at clip_checkpoint_pth
import torch
open_clip_cp = torch.load(open_clip_checkpoint_pth)
open_clip_sd = {k[7:]:v for k, v in open_clip_cp['state_dict'].items()}
torch.save(open_clip_sd, clip_checkpoint_pth)
now you can use OpenAI's API
import clip
model = clip.load(clip_checkpoint_pth)
from open_clip.
Could be nice to add that info in the readme
from open_clip.
good point will do
from open_clip.
Related Issues (20)
- How to load BiomedCLIP from local path HOT 4
- Question: Are the CLIP tokenizers case sensitive? HOT 2
- Training open_clip using pretrained timm HOT 1
- Confirmation: Pretraining is Non-Deterministic? HOT 4
- recommended number of fine-tuning samples & batch size?
- Feature request: computation of multi-label accuracy
- How to reproduce the experiment of Figure 13 in "Learning Transferable Visual Models From Natural Language Supervision" HOT 1
- How to perform batch inference to accelerate the process - coca HOT 1
- Redundancy check: Unnecessary centercrop in default validation preprocessing HOT 1
- `force_image_size` does not work for eva models HOT 1
- Issue with Single GPU Utilization in Distributed Training using torchrun HOT 1
- custom dataset
- lr setting HOT 1
- key error HOT 1
- Model config for laion2b_s34b_b88k not found HOT 1
- Horovod Error HOT 4
- Attention Maps Visualization
- Questions about using COCa to generate captions HOT 17
- Incorrect license appears on PyPI
- Option to load just text or image models HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from open_clip.