NLDF

中文说明

An unofficial implementation of Non-Local Deep Features for Salient Object Detection.

The official Tensorflow version: NLDF

Some thing difference:

1. ~~dataset~~
2. score with one channel, rather than two channels
3. Dice IOU: boundary version and area version

Prerequisites

• Python 3
• Pytorch 1.0
• torchvision
• visdom (optional for visualization)

Results

The information of Loss:

Performance:

Note:

1. only training 200 epoch, larger epoch may nearly the original paper
2. This reproduction use area IOU, and original paper use boundary IOU
3. ~~it's unfairness to this compare. (Different training data, I can not find the dataset use in original paper )~~

Usage

1. Clone the repository

git clone [email protected]:AceCoooool/NLDF-pytorch.git
cd NLDF-pytorch/

2. Download the dataset

Note: the original paper use other datasets.

Download the ECSSD dataset.

bash download.sh

3. Get pre-trained vgg

cd tools/
python extract_vgg.py
cd ..

4. Demo

python demo.py --demo_img='your_picture' --trained_model='pre_trained pth' --cuda=True

Note:

1. default choose: download and copy the pretrained model to weights directory.
2. a demo picture is in png/demo.jpg

5. Train

python main.py --mode='train' --train_path='you_data' --label_path='you_label' --batch_size=8 --visdom=True --area=True

Note:

1. --area=True, --boundary=True area and boundary Dice IOU (default: --area=True --boundary=False)
2. --val=True add the validation (but your need to add the --val_path and --val_label)
3. you_data, you_label means your training data root. (connect to the step 2)

6. Test

python main.py --mode='test', --test_path='you_data' --test_label='your_label' --batch_size=1 --model='your_trained_model'

Note:

1. use the same evaluation (this is a reproduction from original achievement)

Bug

1. The boundary Dice IOU may cause inf，it is better to use area Dice IOU.

Maybe, it is better to add Batch Normalization.