code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

Last update: Nov 23, 2022

Overview

Not All Unlabeled Data are Equal:
Learning to Weight Data in Semi-supervised Learning

Overview

This code is for paper: Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning. Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing. NeurIPS'20. (*equal contribtion)

Setup

Important: ML_DATA is a shell environment variable that should point to the location where the datasets are installed. See the Install datasets section for more details.
Environement*: this code is tested using python-3.7, anaconda3-5.0.1, cuda-10.0, cudnn-v7.6, tensorflow-1.15

Install dependencies

conda create -n semi-sup python=3.7
conda activate semi-sup
pip install -r requirements.txt

make sure tf.test.is_gpu_available() == True after installation so that GPUs will be used.

Install datasets

export ML_DATA="path to where you want the datasets saved"
export PYTHONPATH=$PYTHONPATH:"path to this repo"

# Download datasets
CUDA_VISIBLE_DEVICES= ./scripts/create_datasets.py
cp $ML_DATA/svhn-test.tfrecord $ML_DATA/svhn_noextra-test.tfrecord

# Create unlabeled datasets
CUDA_VISIBLE_DEVICES= scripts/create_unlabeled.py $ML_DATA/SSL2/cifar10 $ML_DATA/cifar10-train.tfrecord
CUDA_VISIBLE_DEVICES= scripts/create_unlabeled.py $ML_DATA/SSL2/svhn $ML_DATA/svhn-train.tfrecord $ML_DATA/svhn-extra.tfrecord
CUDA_VISIBLE_DEVICES= scripts/create_unlabeled.py $ML_DATA/SSL2/svhn_noextra $ML_DATA/svhn-train.tfrecord

# Create semi-supervised subsets
for seed in 0 1 2 3 4 5; do
    for size in 250 1000 4000; do
        CUDA_VISIBLE_DEVICES= scripts/create_split.py --seed=$seed --size=$size $ML_DATA/SSL2/cifar10 $ML_DATA/cifar10-train.tfrecord
        CUDA_VISIBLE_DEVICES= scripts/create_split.py --seed=$seed --size=$size $ML_DATA/SSL2/svhn $ML_DATA/svhn-train.tfrecord $ML_DATA/svhn-extra.tfrecord
        CUDA_VISIBLE_DEVICES= scripts/create_split.py --seed=$seed --size=$size $ML_DATA/SSL2/svhn_noextra $ML_DATA/svhn-train.tfrecord
    done
done

Running

Setup

All commands must be ran from the project root. The following environment variables must be defined:

export ML_DATA="path to where you want the datasets saved"
export PYTHONPATH=$PYTHONPATH:"path to this repo"

Example

For example, train a model with 32 filters on cifar10 shuffled with seed=1, 250 labeled samples and 1000 validation sample:

# single-gpu
CUDA_VISIBLE_DEVICES=0 python main.py --filters=32 [email protected] --train_dir ./experiments

# multi-gpu: just pass more GPUs and the model automatically scales to them, here we assign GPUs 0-1 to the program:
CUDA_VISIBLE_DEVICES=0,1 python main.py --filters=32 [email protected] --train_dir ./experiments

Naming rule: ${dataset}.${seed}@${size}-${valid}
Available labelled sizes are 250, 1000, 4000.
For validation, available sizes are 1000, 5000.
Possible shuffling seeds are 1, 2, 3, 4, 5 and 0 for no shuffling (0 is not used in practiced since data requires to be shuffled for gradient descent to work properly).

Image classification

The hyper-parameters used in the paper:

# 2GPU setting is recommended
for seed in 1 2 3 4 5; do
    for size in 250 1000 4000; do
    CUDA_VISIBLE_DEVICES=0,1 python main.py --filters=32 \
        --dataset=cifar10.${seed}@${size}-1000 \
        --train_dir ./experiments --alpha 0.01 --inner_steps 512
    done
done

Flags

python main.py --help
# The following option might be too slow to be really practical.
# python main.py --helpfull
# So instead I use this hack to find the flags:
fgrep -R flags.DEFINE libml main.py

Monitoring training progress

You can point tensorboard to the training folder (by default it is --train_dir=./experiments) to monitor the training process:

tensorboard.sh --port 6007 --logdir ./experiments

Checkpoint accuracy

We compute the median accuracy of the last 20 checkpoints in the paper, this is done through this code:

# Following the previous example in which we trained [email protected], extracting accuracy:
./scripts/extract_accuracy.py ./experiments/[email protected]/CTAugment_depth2_th0.80_decay0.990/FixMatch_alpha0.01_archresnet_batch64_confidence0.95_filters32_inf_warm0_inner_steps100_lr0.03_nclass10_repeat4_scales3_size_unlabeled49000_uratio7_wd0.0005_wu1.0
# The command above will create a stats/accuracy.json file in the model folder.
# The format is JSON so you can either see its content as a text file or process it to your liking.

Use you own data

You first need to creat *.tfrecord for the labeled and unlabled data; please check scripts/create_datasets.py and scripts/create_unlabeled.py for examples.
Then you need to creat the splits for semi-supervied learning; see scripts/create_split.py.
modify libml/data.py to support the new dataset. Specifically, check this function and this class.
tune hyper-parameters (e.g., learning rate, num_epochs, etc.) to achieve the best results.

Note: our algorithm involves approximation of inverse-Hessian and computation of per-example gradients. Therefore, running on a dataset with large number of classes will be computationally heavy in terms of both speed and memory.

License

Please check LICENSE

Citing this work

If you use this code for your research, please cite our paper.

@inproceedings{ren-ssl2020,
  title = {Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning},
  author = {Zhongzheng Ren$^\ast$ and Raymond A. Yeh$^\ast$ and Alexander G. Schwing},
  booktitle = {Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  note = {$^\ast$ equal contribution},
}

Acknowledgement

The code is built based on: FixMatch (commit: 08d9b83)

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence. Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel.

Contact

Github issues and PR are preferred. Feel free to contact Jason Ren (zr5 AT illinois.edu) for any questions!

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren*, Raymond A. Yeh*, Alexander G. Schwing.

Related tags

Overview

Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning

Overview

Setup

Install dependencies

Install datasets

Running

Setup

Example

Image classification

Flags

Monitoring training progress

Checkpoint accuracy

Use you own data

License

Citing this work

Acknowledgement

Contact

Owner

Jason Ren

[v1 (ISBI'21) + v2] MedMNIST: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification

Secure Distributed Training at Scale

Object detection, 3D detection, and pose estimation using center point detection:

Disentangled Face Attribute Editing via Instance-Aware Latent Space Search, accepted by IJCAI 2021.

Human pose estimation from video plays a critical role in various applications such as quantifying physical exercises, sign language recognition, and full-body gesture control.

Making a music video with Wav2CLIP and VQGAN-CLIP

Label-Free Model Evaluation with Semi-Structured Dataset Representations

A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).

Datasets, Transforms and Models specific to Computer Vision

PyTorch implementation of CVPR 2020 paper (Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence) and pre-trained model on ImageNet dataset

用opencv的dnn模块做yolov5目标检测，包含C++和Python两个版本的程序

Medical Image Segmentation using Squeeze-and-Expansion Transformers

🕹️ Official Implementation of Conditional Motion In-betweening (CMIB) 🏃

Code for the paper "Multi-task problems are not multi-objective"

A script written in Python that returns a consensus string and profile matrix of a given DNA string(s) in FASTA format.

RL Algorithms with examples in Python / Pytorch / Unity ML agents

Curved Projection Reformation

ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives

for a paper about leveraging discourse markers for training new models

Implementation of the "Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos" paper.

code for paper "Not All Unlabeled Data are Equal: Learning to Weight Data in Semi-supervised Learning" by Zhongzheng Ren, Raymond A. Yeh, Alexander G. Schwing.

Not All Unlabeled Data are Equal:
Learning to Weight Data in Semi-supervised Learning