encorechow / deep-interactive

DeepLab-ResNet-TensorFlow

This is an (re-)implementation of DeepLab-ResNet in TensorFlow for semantic image segmentation on the PASCAL VOC dataset.

Updates

29 Jan, 2017:

• Fixed the implementation of the batch normalisation layer: it now supports both the training and inference steps. If the flag --is-training is provided, the running means and variances will be updated; otherwise, they will be kept intact. The .ckpt files have been updated accordingly - to download please refer to the new link provided below.
• Image summaries during the training process can now be seen using TensorBoard.
• Fixed the evaluation procedure: the 'void' label (255) is now correctly ignored. As a result, the performance score on the validation set has increased to 80.1%.

11 Feb, 2017:

• The training script train.py has been re-written following the original optimisation setup: SGD with momentum, weight decay, learning rate with polynomial decay, different learning rates for different layers, ignoring the 'void' label (255).
• The training script with multi-scale inputs train_msc.py has been added: the input is resized to 0.5 and 0.75 of the original resolution, and 4 losses are aggregated: loss on the original resolution, on the 0.75 resolution, on the 0.5 resolution, and loss on the all fused outputs.
• Evaluation of a single-scale converted pre-trained model on the PASCAL VOC validation dataset (using 'SegmentationClassAug') leads to 86.9% mIoU. This is confirmed by the official PASCAL VOC server. The score on the test dataset is 75.8%.

Model Description

The DeepLab-ResNet is built on a fully convolutional variant of ResNet-101 with atrous (dilated) convolutions, atrous spatial pyramid pooling, and multi-scale inputs (not implemented here).

The model is trained on a mini-batch of images and corresponding ground truth masks with the softmax classifier at the top. During training, the masks are downsampled to match the size of the output from the network; during inference, to acquire the output of the same size as the input, bilinear upsampling is applied. The final segmentation mask is computed using argmax over the logits. Optionally, a fully-connected probabilistic graphical model, namely, CRF, can be applied to refine the final predictions. On the test set of PASCAL VOC, the model achieves 79.7% of mean intersection-over-union.

For more details on the underlying model please refer to the following paper:

@article{CP2016Deeplab,
  title={DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs},
  author={Liang-Chieh Chen and George Papandreou and Iasonas Kokkinos and Kevin Murphy and Alan L Yuille},
  journal={arXiv:1606.00915},
  year={2016}
}

Requirements

TensorFlow needs to be installed before running the scripts. TensorFlow 0.12 is supported; for TensorFlow 0.11 please refer to this branch.

To install the required python packages (except TensorFlow), run

pip install -r requirements.txt

or for a local installation

pip install -user -r requirements.txt

Caffe to TensorFlow conversion

To imitate the structure of the model, we have used .caffemodel files provided by the authors. The conversion has been performed using Caffe to TensorFlow with an additional configuration for atrous convolution and batch normalisation (since the batch normalisation provided by Caffe-tensorflow only supports inference). There is no need to perform the conversion yourself as you can download the already converted models - deeplab_resnet.ckpt (pre-trained) and deeplab_resnet_init.ckpt (the last layers are randomly initialised) - here.

Nevertheless, it is easy to perform the conversion manually, given that the appropriate .caffemodel file has been downloaded, and Caffe to TensorFlow dependencies have been installed. The Caffe model definition is provided in misc/deploy.prototxt. To extract weights from .caffemodel, run the following:

python convert.py /path/to/deploy/prototxt --caffemodel /path/to/caffemodel --data-output-path /where/to/save/numpy/weights

As a result of running the command above, the model weights will be stored in /where/to/save/numpy/weights. To convert them to the native TensorFlow format (.ckpt), simply execute:

python npy2ckpt.py /where/to/save/numpy/weights --save-dir=/where/to/save/ckpt/weights

Dataset and Training

To train the network, one can use the augmented PASCAL VOC 2012 dataset with 10582 images for training and 1449 images for validation.

The training script allows to monitor the progress in the optimisation process using TensorBoard's image summary. Besides that, one can also exploit random scaling of the inputs during training as a means for data augmentation. For example, to train the model from scratch with random scale turned on, simply run:

python train.py --random-scale

To see the documentation on each of the training settings run the following:

python train.py --help

An additional script, fine_tune.py, demonstrates how to train only the last layers of the network. The script train_msc.py with multi-scale inputs fully resembles the training setup of the original model.

Evaluation

The single-scale model shows 86.9% mIoU on the Pascal VOC 2012 validation dataset ('SegmentationClassAug'). No post-processing step with CRF is applied.

The following command provides the description of each of the evaluation settings:

python evaluate.py --help

Inference

To perform inference over your own images, use the following command:

python inference.py /path/to/your/image /path/to/ckpt/file

This will run the forward pass and save the resulted mask with this colour map:

Missing features

The post-processing step with CRF is currently being implemented in this branch.

Other implementations

• DeepLab-LargeFOV in TensorFlow