- Predict mask / gender / age
- Input : 384 x 512 Image
- Output : 0~17 classes
- Mask : Wear, Incorrect, Not Wear
- Gender : Male, Female
- Age : <30, >=30 and <60, >=60
image-classification-level1-02/
βββ input/
β βββ train/
| βββ images/
| βββ train.csv
β βββ eval/
| βββ images/
| βββ info.csv
βββ Dataset.py
βββ Model.py
βββ Test.py
βββ functions.py
βββ main.py
input/data/train
: train dataset imagesinput/data/test
: used in evaluationinput/
: download from https://stages.ai/
- Ubuntu 18.04.5
- Python 3.8.5
- pytorch 1.7.1
- torchvision 0.8.2
Install packages : pip install -r requirements.txt
- CPU: 8 x Intel(R) Xeon(R) Gold 5220 CPU
- GPU: V100
- RAM: 88GB
sh run.sh
python main.py \
--PATH '../input/data' \
--BATCH_SIZE 128 \
--SAVE true \
--SAVE_PATH 'saved/' \
--EPOCH 20
--PATH
:train/
,eval/
parent directory--BATCH_SIZE
: Batch size (default=128)--SAVE
: If want to save weights while training else remove this line--SAVE_PATH
: Saving weights directory--EPOCH
: Train epoch (default=20)
- Pretrained ResNet18 model
- No data augmentation
- Hyperparameter
- Learning rate : 1e-5
- Optimizer : Adam
- Batch size : 128
Name @github | Project link |
---|---|
μλͺ μ² @abbymark | image classification |
κΉλ―Όμ§ @kkmjkim | image classification |
λ°μν @hyun06000 | image classification |
μ¬μΈλ Ή @seryoungshim17 | image classification |
μ΄μ μ§ @YoojLee | image classification |
μ λν΄ @Doohae | image classification |
νμ§μ° @hongjourney | image classification |