yjh0410 0ad3b62fc7 all in yolo		1 vuosi sitten
..
data	0ad3b62fc7 all in yolo	1 vuosi sitten
models	0ad3b62fc7 all in yolo	1 vuosi sitten
utils	0ad3b62fc7 all in yolo	1 vuosi sitten
.gitignore	0ad3b62fc7 all in yolo	1 vuosi sitten
README.md	0ad3b62fc7 all in yolo	1 vuosi sitten
engine.py	0ad3b62fc7 all in yolo	1 vuosi sitten
main.py	0ad3b62fc7 all in yolo	1 vuosi sitten
requirements.txt	0ad3b62fc7 all in yolo	1 vuosi sitten

General Image Classification Laboratory

Train

For example, we are going to train ConvNet designed in this repo, so we can use the following command:

cd Vision-Pretraining-Tutorial/image_classification/
python main.py --cuda \
               --dataset cifar \
               --model convnet \
               --batch_size 256 \
               --optimizer adamw \
               --base_lr 1e-3 \
               --min_lr 1e-6

Evaluate

Evaluate the top1 & top5 accuracy:

cd Vision-Pretraining-Tutorial/image_classification/
python main.py --cuda \
           --dataset cifar \
           --model convnet \
           --batch_size 256 \
           --eval \
           --resume path/to/checkpoint

README.md

General Image Classification Laboratory

Train

Evaluate