Python-深度抠图KerasTensorFlowOpenCV

# Deep Image Matting This repository is to reproduce Deep Image Matting. ## Dependencies - [NumPy](http://docs.scipy.org/doc/numpy-1.10.1/user/install.html) - [Tensorflow](https://www.tensorflow.org/versions/r0.8/get_started/os_setup.html) - [Keras](https://keras.io/#installation) - [OpenCV](https://opencv-python-tutroals.readthedocs.io/en/latest/) ## Dataset ### Adobe Deep Image Matting Dataset Follow the [instruction](https://sites.google.com/view/deepimagematting) to contact author for the dataset. ### MSCOCO Go to [MSCOCO](http://cocodataset.org/#download) to download: * [2014 Train images](http://images.cocodataset.org/zips/train2014.zip) ### PASCAL VOC Go to [PASCAL VOC](http://host.robots.ox.ac.uk/pascal/VOC/) to download: * VOC challenge 2007 [training/validation data](http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar) ## ImageNet Pretrained Models Download [VGG16](https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5) into models folder. ## Usage ### Data Pre-processing Extract training images: ```bash $ python pre-process.py ``` ### Train ```bash $ python train.py ``` If you want to visualize during training, run in your terminal: ```bash $ tensorboard --logdir path_to_current_dir/logs ``` ### Demo ```bash $ python demo.py ``` Image/Trimap | Output/GT | New BG/Compose | |---|---|---| | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | | | |  |  | | |  | |