Getting Started

we visualize our training details via wandb (https://wandb.ai/site).

visualization

you'll need to login
```
$ wandb login
```
you'll need to copy & paste you API key in terminal
```
$ https://wandb.ai/authorize
```
or paste it to the Code/VnetLA/Configs/config.py
```
os.environ['WANDB_API_KEY'] = "you key"
```

training

run the scripts with your prefered labelled number

# for exmaple, #8 label protocol of LA dataset
./scripts/train_la.sh 8

inference

fullfill your environment name below

python3 Code/VnetLA/validate.py --env_name ""

Setting

We offer different training iterations upon the labelled num.

1). LA dataset

# labels	max_iterations	unsup weight
8	9000	0.3
16	9000	1.0
32	12000	1.0

2). Pancreas dataset

# labels	max_iterations	unsup weight
6	7000	0.3
12	7000	1.0
24	9000	1.0

3). BRaTS19 dataset

# labels	max_iterations	unsup weight
25	15000	0.3
50	30000	1.0
125	40000	1.0