Comments (2)
Hi @vbursztyn,
Could you please run the inference colab and check if you still face the error from the line tmp_att, tmp_fc = clip_model.encode_image(image)
? Since the line works on the colab, checking the details such as image input and other package versions might help you find what the issue is.
from clip-caption-reward.
Thank you very much, @j-min. It's fixed! For reference, here's the reason:
I had taken the liberty of installing CLIP from OpenAI's repo, and for some reason it was causing this error. Uninstalling CLIP fixed it.
from clip-caption-reward.
Related Issues (12)
- Confusion about the config HOT 3
- Factor in the weigthed reward sum is inconsistent with the paper HOT 2
- pre-training model HOT 4
- Select part of the data set
- onnx version ?
- difference between clip_prepo_feat.py and clipscore_prepo_feat.py HOT 2
- Where is the file 'data/ finecapeval. json'? HOT 1
- Phase 1 validation throws: shape '[4, -1, 512]' is invalid for input of size 64000 HOT 3
- About language_evaluation HOT 1
- Config file and performance reproduce HOT 11
- phase 2 of clips HOT 2
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 clip-caption-reward.