Comments (1)
Hi there, thank you for your interest in our project. Regarding training, this code snippet illustrates the logic of one training iteration. Regarding parallelization and batch size, since gradients computed on every GPU are then synchronized, the effective batch size would be the batch size on a singe GPU multiplied by the number of parallel GPUs. To be specific, to train the largest model, we set an effective batch size of 128, which amounts to a local batch size of 16 across 8 GPUs.
from vima.
Related Issues (20)
- [Evaluation] How to get the result reported in the paper
- [Test] The test result is not consistent with that reported in paper. HOT 11
- Question of the object encoding and training details HOT 1
- Some questions about the input observation HOT 1
- Request for Guidance on Implementing imitation_loss HOT 3
- Question: how to specific state or restore the state of the environment?
- RuntimeError: Failed to reset environment after 10 retries HOT 3
- Exception: Model "t5-base" on the Hub doesn't have a tokenizer HOT 4
- The inference process of the VIMA strongly relies on the images in the prompts and objects in the environment HOT 1
- Franka in Isaac-sim HOT 1
- The order of object token is always same
- ImportError: cannot import name 'checkpoint' from 'transformers.models.t5.modeling_t5' HOT 15
- Asking for better explanation HOT 2
- Action dim not match HOT 2
- How to eval the baseline? HOT 1
- Implementation details of the loss scaling algorithm HOT 1
- Invalid GLX version: major 1, minor 2 HOT 1
- Metrics related to evaluating the models.
- How is the current inference frequency? Did someone try it on real world experiment?
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 vima.