Comments (5)
to be addressed after #72
from open_flamingo.
happy to take point on this, I am becoming passionate about cleaning up the eval codebase anyway, we need to clean it up a lot before things get too messy when adding more eval datasets
from open_flamingo.
cc @simonster , I will follow up on this once imagenet is set up and we can formulate a reasonable plan of attack
from open_flamingo.
I think this strategy should be compatible with any sane API, but my general plan for Flamingo eval is as follows:
- Run the eval script once and save out all the data to TFRecords
- Run bulk inference on the TFRecords using Flamingo and save the outputs
- Run the eval script again and feed the Flamingo outputs in
This seems like the best option because it avoids trying to run the eval code in Google's monorepo, which would restrict what packages could be used, and I should already have bulk inference capabilities for these models. This strategy won't support a conversation between the model and evaluation script, but it should work for the datasets we are currently considering.
from open_flamingo.
SGTM. In this case, it sounds like we don't really need to "abstract away" the PyTorch so much as support dumping of the eval sets to tfrecords, which will actually be simpler anyway.
Whenever you have a chance @simonster (not urgent), feel free to share any info on the schema needed for the tfrecords to work with the bulk inference pipeline.
from open_flamingo.
Related Issues (20)
- 'media_token_id' AttributeError
- Import Error HOT 5
- How to set hyperparameters?
- Worse performance compared to vanilla cross attention HOT 2
- [BUG] an error in get_dataset_size about args.shards
- Understanding MP policy for parameters
- Open Flamingo Perplexity Calculation HOT 3
- TypeError: Flamingo.__init__() got an unexpected keyword argument 'cache_dir' HOT 1
- [BUG] ViT-L-14 downloaded in Demo compared to Huggingface Demo Card don't seem to be the same
- How to try my own fine-tuning experiments HOT 1
- [FEATURE REQUEST] Is it possible to train a 3B openflamingo on 4 V100 on one node with deepspeed by simplifying pre-training data used?
- Failure to use https://huggingface.co/anas-awadalla/mpt-7b model downloading issue?
- Allow `PerceiverResampler` to take in attention masks
- how to get synthetic data mentioned in the paper
- Implementation
- Unable to reproduce the evaluation results on textvqa
- what's the meaning of media in input to PerceiverResampler ? Why give time embedding to different media ? Shouldn't given time embedding to different frames?
- The bug in getting attention weight
- [BUG] Cannot Initialize Any Models in transformers==4.41.2 HOT 1
- The format of dataset of mmc4 and laion? So I can train on other dataset.
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_flamingo.