MoCo

A PyTorch implementation of MoCo based on CVPR 2020 paper Momentum Contrast for Unsupervised Visual Representation Learning.

Requirements

conda install pytorch=1.6.0 torchvision cudatoolkit=10.2 -c pytorch

Dataset

CIFAR10 dataset is used in this repo, the dataset will be downloaded into data directory by PyTorch automatically.

Usage

Train MoCo

python train.py --batch_size 1024 --epochs 50
optional arguments:
--feature_dim                 Feature dim for each image [default value is 128]
--m                           Negative sample number [default value is 4096]
--temperature                 Temperature used in softmax [default value is 0.5]
--momentum                    Momentum used for the update of memory bank [default value is 0.999]
--k                           Top k most similar images used to predict the label [default value is 200]
--batch_size                  Number of images in each mini-batch [default value is 256]
--epochs                      Number of sweeps over the dataset to train [default value is 500]

Linear Evaluation

python linear.py --batch_size 1024 --epochs 200 
optional arguments:
--model_path                  The pretrained model path [default value is 'results/128_4096_0.5_0.999_200_256_500_model.pth']
--batch_size                  Number of images in each mini-batch [default value is 256]
--epochs                      Number of sweeps over the dataset to train [default value is 100]

Results

There are some difference between this implementation and official implementation, the model (ResNet50) is trained on one NVIDIA GeForce GTX TITAN GPU:

No Gaussian blur used;
Adam optimizer with learning rate 1e-3 is used to replace SGD optimizer;
No Linear learning rate scaling used.

Evaluation Protocol	Feature Dim	Momentum	Batch Size	Epoch Num	τ	K	Top1 Acc %	Top5 Acc %	Download
KNN	128	0.999	256	500	0.5	200	80.9	99.1	model \| tex8
Linear	-	-	256	100	-	-	86.3	99.6	model \| 6me4