Skip to content

Latest commit

 

History

History
47 lines (42 loc) · 2.89 KB

README.md

File metadata and controls

47 lines (42 loc) · 2.89 KB

fn_playground

Background


Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. It shares the same image size and structure of training and testing splits.

In this repo, I try to do some experiments with Fashion-MNIST dataset. (I do some experiments with Cifar-10 dataset either.)

Training Schedule


  1. Standard preprocessing (mean/std subtraction/division) and data augment(Rand augment, random crops,horizontal flips, random erasing);
  2. Backbone: wide-resnet 40-4;
  3. Learning rate schedule: CosineAnnealingLR;
  4. Other tricks: Label smoothing, Exponential Moving Average, and so on.

Usage


1.run pip install -r requirements.txt;

2.choose a python script to run.

               
script namedatasetbest test accuracyweight files
fn_fmix_40_4_gn_ws_learning.py Fashion-MNIST 96.44%(epoch 562) Google Cloud
fn_fmix_40_4_bn_mish_ws_gem.py Fashion-MNIST 96.69%(epoch 881) Google Cloud
kaggle_cifar10_fmix_40_4_bn_mish_ws_gem.py Cifar-10 98.03%(epoch 864) Google Cloud
fn_96_74.py Fashion-MNIST 96.74%(epoch 785) Google Cloud