Comments (2)
Should also work with two pipe
s, something like "pipe:aws s3 cp ${ROOT_PATH}/folder1/{00000..00019}.tar -::pipe:aws s3 cp ${ROOT_PATH}/folder2/{00000..00031}.tar -"
. You'll need this if you want to mix with different weighting for the different sources.
from open_clip.
I think I figured it out ... It seems that for S3 piping, one needs to use a comma separated list as illustrated in the example below:
Let me know if you want me to clarify in the documentation.
from open_clip.
Related Issues (20)
- A beginner's guide to fine-tuning the CLIP model for your downstream tasks using OpenClip HOT 2
- Is there any particular reason why bias term is kept as False in the projection layers HOT 2
- Q-LORA for BiomedCLIP
- Model weights missing ViT-SO400M-14-SigLIP-384 (webli pretrained) HOT 2
- Model Download fails on Mac, works on Linux HOT 2
- Finetuning CLIP VIT32 on COCO captions
- Model coca_ViT-B-32 not found; available models = ['RN50', 'RN50-quickgelu', 'RN101', 'RN101-quickgelu', 'RN50x4', 'RN50x16', 'RN50x64', 'ViT-B-32', 'ViT-B-32-quickgelu', 'ViT-B-16', 'ViT-L-14', 'ViT-L-14-336'] HOT 1
- How does the logit_scale vary while training , i noitced that in my case it starts from the 14.28(1/0.07) and then just goes down and towards the end of the training it reaches 1 HOT 2
- ValueError: Batch dimension of `input_ids` should be 0, but is 6. HOT 1
- How to reproduce the VQA results of CoCa?
- Loss isn't converging HOT 1
- oscillations in the loss HOT 2
- Example of launcher script with Horovod HOT 1
- Evaluation of Trained SigLIP Checkpoints
- How much GPU memory can SigLIP save compared with CLIP?
- Will fine-tuning affect the ability of the original search? HOT 1
- how to get hidden_state from every layers of ViT of openclip vision encoder? HOT 2
- Logging for cuda usage could be a little confused when specifying gpu-id HOT 1
- Is there someone who can share implemented script for --lock-text-unlocked-layers for "Native Clip Model"?
- On mismatch of model input, does not give correct list of valid ones 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.