Comments (1)
Are you downloading the data and running laion_cloudwriter.py
at the same time? It does take a lot of time to run, but this will depend on the number of CPUs, network bandwidth, disk I/O, etc. We need to dig up the exact time it took us, but it will vary greatly based on the machine specs you are using.
Since the parquets can be processed in parallel, we divided the parquets into 4 subsets and processed each subset on a different machine. If you have access to more than one machine, I highly recommend this strategy. Our Streaming library can seamlessly use multiple streaming datasets, so no need to combine separately processed streaming datasets.
from diffusion.
Related Issues (20)
- FID score changes a lot during the model training HOT 2
- Bug Report of image_caption.py HOT 1
- train error during evaluation with 1 GPU and train with multi GPU HOT 2
- Any plan to support "Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack"? HOT 2
- Bug report: ValueError: invalid literal for int() with base 10: '/tmp/mds-cache/mds-coco-2014-val-fid-clip-17'
- FID from the mainline code is different from https://github.com/mosaicml/diffusion/tree/ejyuen-patch-1 HOT 1
- [dynamo] `UnspecializedNNModuleVariable` does not implement object identity HOT 1
- When is common canvas going to be released? HOT 23
- TypeError("'NoneType' object is not iterable") HOT 1
- Training with modest data HOT 1
- What is the benefit of multi phase training? HOT 2
- How to do continue training when a job failed HOT 1
- Convert Pt model to safetensor
- Example config for training VAE HOT 4
- Multi-node training
- Training a MosaicML
- Implementing Mosaic Diffusion into Patch-Diffusion
- Is this dataset still expected to be released? HOT 4
- ERROR:composer.cli.launcher:Rank 0 crashed with exit code -11. HOT 1
- Request for Sample Code and Tips on Using Huggingface Datasets for Training
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 diffusion.