BayesWatch/minimal-ml-template BayesWatch/minimal-ml-template

  • Stars
    star
    15
  • Rank 1,371,379 (Top 28 %)
  • Language
    Python
  • License
    MIT License
  • Created about 2 years ago
  • Updated almost 2 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
BayesWatch/minimal-ml-template
github

BayesWatch

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A very minimal ml project template that uses HF transformers and wandb to train a simple NN and evaluate it, in a stateless manner compatible with Spot instances kubernetes workflows

More Repositories

1

nas-without-training

Code for Neural Architecture Search without Training (ICML 2021)
Python
440
star
2

sequential-imagenet-dataloader

A plug-in replacement for DataLoader to load Imagenet disk-sequentially in PyTorch.
Python
227
star
3

cinic-10

A drop-in replacement for CIFAR-10.
Jupyter Notebook
223
star
4

deep-kernel-transfer

Official pytorch implementation of the paper "Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels" (NeurIPS 2020)
Python
191
star
5

pytorch-prunes

Code for https://arxiv.org/abs/1810.04622
Python
138
star
6

pytorch-GENet

A Pytorch implementation of https://arxiv.org/abs/1810.12348.
Python
35
star
7

pytorch-moonshine

Cheap distillation for convolutional neural networks.
Python
32
star
8

pytorch-blockswap

Code for BlockSwap (ICLR 2020).
Python
31
star
9

tf-variational-dropout

Sparsifying Variational Dropout in Tensorflow
Python
22
star
10

deficient-efficient

Successfully training approximations to full-rank matrices for efficiency in deep learning.
Python
15
star
11

mpl_sizes

Match your fig size and font to conference formats.
Python
11
star
12

mini-nasbench-201

Python
1
star