Comments (5)
Hey @Johswald! Thanks for asking. Have you verified that you're running under 8 accelerators? That's the exact setting in the default flags, which reproduces the result (we've checked on cloud TPUs). This is often the culprit, and may suggest we should somehow raise an error if, e.g., the system's # accelerators doesn't match FLAGS.num_cores.
from uncertainty-baselines.
Hey @dustinvtran
No, I am just running it on a single GPU which is also quite fast. I can try to parallelise on my node with 8 GPUs if you think this would make a difference? Algorithmically I should not right? (No experience with TPUs :) )
I was asking about the config because it was not clear if this is a cifar10 or cifar100 config. So the one that is the default one in batchensemble.py is the cifar100 one that gets the 81.9% test set (on TPUs)? Are you using the same config for cifar10 and 100?
Thank you again!
from uncertainty-baselines.
All the CIFAR uses num_cores=8 currently, which means 8 GPUs. This affects the global batch size for each gradient step. The default flag values are for cifar10 and I think you need to just change FLAGS.dataset for cifar100.
from uncertainty-baselines.
Ah of course, thanks a lot! I will get back to you once the runs are done.
from uncertainty-baselines.
Closing due to inactivity, please reopen if needed!
from uncertainty-baselines.
Related Issues (20)
- Question: a good strategy to estimate covariance matrix for SNGP when there are no clear "epochs" HOT 1
- Implement eval_model.py script using a Pytorch ResNet-50 MC Dropout trained model - Diabetic Retinopathy Detection
- Question: SNGP initialization of random features HOT 2
- Question about SNGP BERT flags HOT 2
- input_utils to importing in Colab notebook
- plex_vit_demo : Failed to get url-imagenetv2public
- tensorflow_federated no attribute 'Popen' error
- ModuleNotFoundError: No module named 'official.nlp.bert' HOT 1
- Unsupported data type for TPU String HOT 3
- Where is keras_tokenizer.json supposed to come from for clinc_intent.py?
- Question about SNGP differences from the paper HOT 1
- Pretrained models or logits of these (Recalibration)
- mixup hyperparameters
- Remove need for registration mechanisms?
- bert_dropout_test is failing
- Clean up reliance on local utility files in the JFT directory
- Example code for computing Mahalanobis score in TF-2 HOT 4
- question on kl rescaling! HOT 1
- feature- baselines for vision tasks
- SNGP inference speed
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 uncertainty-baselines.