Folders and files

Name		Name	Last commit message	Last commit date
Latest commit History 89 Commits
archived		archived
data/demos/deeplab/resnet_101_voc2012		data/demos/deeplab/resnet_101_voc2012
nets		nets
.gitignore		.gitignore
LICENSE.md		LICENSE.md
README.md		README.md
download.py		download.py
feature_extractor.py		feature_extractor.py
install_dependencies.sh		install_dependencies.sh
model.py		model.py
modules.py		modules.py
requirements.txt		requirements.txt
test_demo.py		test_demo.py
test_demo_any.py		test_demo_any.py
train.py		train.py
utils.py		utils.py

Repository files navigation

DeepLab V3

Lei Mao, Shengjie Lin

University of Chicago

Toyota Technological Institute at Chicago

Introduction

DeepLab is a series of image semantic segmentation models, whose latest version, i.e. v3+, proves to be the state-of-art. Its major contribution is the use of atrous spatial pyramid pooling (ASPP) operation at the end of the encoder. While the model works extremely well, its open source code is hard to read (at least from my personal perspective). Here we re-implemented DeepLab V3, the earlier version of v3+ (which only additionally employs the decoder architecture), in a much simpler and more understandable way.

Dependencies

Python 3.5
TensorFlow 1.8
Tqdm 4.26.0
Numpy 1.14
OpenCV 3.4.3
Pillow 5.3.0

Files

.├── archieved├── download.py├── feature_extractor.py├── LICENSE.md├── model.py├── modules.py├── nets├── README.md├── test_demo.py├── test_any_image.py├── train.py└── utils.py

Thenets directory contains network definition files that are directly copied fromtensorflow/models/research/slim/nets

Usages

Install Dependencies

To install dependencies, please run the following command to install everything required automatically:

$ chmod +x install_dependencies.sh$ pip install -r requirements.txt$ ./install_dependencies.sh

If found permission problems, please run the following command instead:

$ chmod +x install_dependencies.sh$ pip install -r requirements.txt$ sudo ./install_dependencies.sh

Download Dataset

Download and extract VOC2012 dataset, SBD dataset, and pretrained models to designated directories.

$ python download.py --helpusage: download.py [-h] [--downloads_dir DOWNLOADS_DIR] [--data_dir DATA_DIR]                   [--pretrained_models_dir PRETRAINED_MODELS_DIR]                   [--pretrained_models PRETRAINED_MODELS [PRETRAINED_MODELS ...]]Download DeepLab semantic segmentation datasets and pretrained backbonemodels.optional arguments:-h, --help            show thishelp message andexit  --downloads_dir DOWNLOADS_DIR                        Downloads directory  --data_dir DATA_DIR   Data directory  --pretrained_models_dir PRETRAINED_MODELS_DIR                        Pretrained models directory  --pretrained_models PRETRAINED_MODELS [PRETRAINED_MODELS ...]                        Pretrained models to download: resnet_50, resnet_101,                        mobilenet_1.0_224

For example, to download and extract datasets and models into directories specified:

$ python download.py --downloads_dir ./downloads --data_dir ./data --pretrained_models_dir ./models/pretrained --pretrained_models resnet_50 resnet_101 mobilenet_1.0_224

For simplicity, please just run the following command in terminal:

$ python download.py

Train Model

$ python train.py --helpusage: train.py [-h] [--network_backbone NETWORK_BACKBONE]                [--pre_trained_model PRE_TRAINED_MODEL]                [--trainset_filename TRAINSET_FILENAME]                [--valset_filename VALSET_FILENAME] [--images_dir IMAGES_DIR]                [--labels_dir LABELS_DIR]                [--trainset_augmented_filename TRAINSET_AUGMENTED_FILENAME]                [--images_augmented_dir IMAGES_AUGMENTED_DIR]                [--labels_augmented_dir LABELS_AUGMENTED_DIR]                [--model_dir MODEL_DIR] [--log_dir LOG_DIR]                [--random_seed RANDOM_SEED]Train DeepLab V3for image semantic segmantation.optional arguments:  -h, --help            show thishelp message andexit  --network_backbone NETWORK_BACKBONE                        Network backbones: resnet_50, resnet_101,                        mobilenet_1.0_224. Default: resnet_101  --pre_trained_model PRE_TRAINED_MODEL                        Pretrained model directory  --trainset_filename TRAINSET_FILENAME                        Train dataset filename  --valset_filename VALSET_FILENAME                        Validation dataset filename  --images_dir IMAGES_DIR                        Images directory  --labels_dir LABELS_DIR                        Labels directory  --trainset_augmented_filename TRAINSET_AUGMENTED_FILENAME                        Train augmented dataset filename  --images_augmented_dir IMAGES_AUGMENTED_DIR                        Images augmented directory  --labels_augmented_dir LABELS_AUGMENTED_DIR                        Labels augmented directory  --model_dir MODEL_DIR                        Trained model saving directory  --log_dir LOG_DIR     TensorBoard log directory  --random_seed RANDOM_SEED                        Random seedfor model training.

For simplicity, please run the following command in terminal:

$ python train.py

With learning rate of1e-5, the mIOU could be greater 0.7 after 20 epochs, which is comparable to the test statistics of DeepLab V3 in the publication.