Implementing Class_attack

1. Prediction

Single image:

python predict.py --input datasets/data/cityscapes/leftImg8bit/train/bremen/bremen_000000_000019_leftImg8bit.png  --dataset cityscapes --model deeplabv3plus_mobilenet --ckpt checkpoints/best_deeplabv3plus_mobilenet_cityscapes_os16.pth --save_val_results_to test_results

Image folder:

python predict.py --input datasets/data/cityscapes/leftImg8bit/train/bremen  --dataset cityscapes --model deeplabv3plus_mobilenet --ckpt checkpoints/best_deeplabv3plus_mobilenet_cityscapes_os16.pth --save_val_results_to test_results

2. New backbones

Please refer to this commit (Xception) for more details about how to add new backbones.

3. New datasets

You can train deeplab models on your own datasets. Your torch.utils.data.Dataset should provide a decoding method that transforms your predictions to colorized images, just like the VOC Dataset:

class MyDataset(data.Dataset):
    ...
    @classmethod
    def decode_target(cls, mask):
        """decode semantic mask to RGB image"""
        return cls.cmap[mask]

Results

1. Performance on Pascal VOC2012 Aug (21 classes, 513 x 513)

Training: 513x513 random crop
validation: 513x513 center crop

Model	Batch Size	FLOPs	train/val OS	mIoU	Dropbox	Tencent Weiyun
DeepLabV3-MobileNet	16	6.0G	16/16	0.701	Download	Download
DeepLabV3-ResNet50	16	51.4G	16/16	0.769	Download	Download
DeepLabV3-ResNet101	16	72.1G	16/16	0.773	Download	Download
DeepLabV3Plus-MobileNet	16	17.0G	16/16	0.711	Download	Download
DeepLabV3Plus-ResNet50	16	62.7G	16/16	0.772	Download	Download
DeepLabV3Plus-ResNet101	16	83.4G	16/16	0.783	Download	Download

2. Performance on Cityscapes (19 classes, 1024 x 2048)

Training: 768x768 random crop
validation: 1024x2048

Model	Batch Size	FLOPs	train/val OS	mIoU	Dropbox	Tencent Weiyun
DeepLabV3Plus-MobileNet	16	135G	16/16	0.721	Download	Download
DeepLabV3Plus-ResNet101	16	N/A	16/16	0.762	Download	N/A

Segmentation Results on Pascal VOC2012 (DeepLabv3Plus-MobileNet)

Segmentation Results on Cityscapes (DeepLabv3Plus-MobileNet)

Visualization of training

Pascal VOC

1. Requirements

pip install -r requirements.txt

2. Prepare Datasets

2.1 Standard Pascal VOC

You can run train.py with "--download" option to download and extract pascal voc dataset. The defaut path is './datasets/data':

/datasets
    /data
        /VOCdevkit 
            /VOC2012 
                /SegmentationClass
                /JPEGImages
                ...
            ...
        /VOCtrainval_11-May-2012.tar
        ...

2.2 Pascal VOC trainaug (Recommended!!)

See chapter 4 of [2]

    The original dataset contains 1464 (train), 1449 (val), and 1456 (test) pixel-level annotated images. We augment the dataset by the extra annotations provided by [76], resulting in 10582 (trainaug) training images. The performance is measured in terms of pixel intersection-over-union averaged across the 21 classes (mIOU).

./datasets/data/train_aug.txt includes the file names of 10582 trainaug images (val images are excluded). Please to download their labels from Dropbox or Tencent Weiyun. Those labels come from DrSleep's repo.

Extract trainaug labels (SegmentationClassAug) to the VOC2012 directory.

/datasets
    /data
        /VOCdevkit  
            /VOC2012
                /SegmentationClass
                /SegmentationClassAug  # <= the trainaug labels
                /JPEGImages
                ...
            ...
        /VOCtrainval_11-May-2012.tar
        ...

3. Training on Pascal VOC2012 Aug

3.1 Visualize training (Optional)

Start visdom sever for visualization. Please remove '--enable_vis' if visualization is not needed.

# Run visdom server on port 28333
visdom -port 28333

3.2 Training with OS=16

Run main.py with "--year 2012_aug" to train your model on Pascal VOC2012 Aug. You can also parallel your training on 4 GPUs with '--gpu_id 0,1,2,3'

Note: There is no SyncBN in this repo, so training with multple GPUs and small batch size may degrades the performance. See PyTorch-Encoding for more details about SyncBN

python main.py --model deeplabv3plus_mobilenet --enable_vis --vis_port 28333 --gpu_id 0 --year 2012_aug --crop_val --lr 0.01 --crop_size 513 --batch_size 16 --output_stride 16

3.3 Continue training

Run main.py with '--continue_training' to restore the state_dict of optimizer and scheduler from YOUR_CKPT.

python main.py ... --ckpt YOUR_CKPT --continue_training

3.4. Testing

Results will be saved at ./results.

python main.py --model deeplabv3plus_mobilenet --enable_vis --vis_port 28333 --gpu_id 0 --year 2012_aug --crop_val --lr 0.01 --crop_size 513 --batch_size 16 --output_stride 16 --ckpt checkpoints/best_deeplabv3plus_mobilenet_voc_os16.pth --test_only --save_val_results

Cityscapes

1. Download cityscapes and extract it to 'datasets/data/cityscapes'

/datasets
    /data
        /cityscapes
            /gtFine
            /leftImg8bit

2. Train your model on Cityscapes

python main.py --model deeplabv3plus_mobilenet --dataset cityscapes --enable_vis --vis_port 28333 --gpu_id 0  --lr 0.1  --crop_size 768 --batch_size 16 --output_stride 16 --data_root ./datasets/data/cityscapes

Reference

[1] Rethinking Atrous Convolution for Semantic Image Segmentation

[2] Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

u6630774/Class_Attack