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

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

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

# single-gpu
CUDA_VISIBLE_DEVICES=0 python main.py --filters=32 --dataset=cifar10.1@250-1000 --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 --dataset=cifar10.1@250-1000 --train_dir ./experiments

# 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

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

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

# Following the previous example in which we trained cifar10.1@250-1000, extracting accuracy:
./scripts/extract_accuracy.py ./experiments/cifar10.d.d.d.1@250-1000/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.

@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},
}