TF Image Segmentation: Image Segmentation framework

The aim of the TF Image Segmentation framework is to provide/provide a simplified way for:

Converting some popular general/medical/other Image Segmentation Datasets into easy-to-use for training .tfrecords format with unified interface: different datasets but same way to store images and annotations.
Training routine with on-the-fly data augmentation (scaling, color distortion).
Training routine that is proved to work for particular model/dataset pair.
Evaluating Accuracy of trained models with common accuracy measures: Mean IOU, Mean pix. accuracy, Pixel accuracy.
Model files that were trained on a particular dataset with reported accuracy (models that were trained using TF with reported training routine and not models that were converted from Caffe or other framework)
Model definitions (like FCN-32s and others) that use weights initializations from Image Classification models like VGG that are officially provided by TF-Slim library.

So far, the framework contains an implementation of the FCN models (training and evaluation) in Tensorflow and TF-Slim library with training routine, reported accuracy, trained models for PASCAL VOC 2012 dataset. To train these models on your data, convert your dataset to tfrecords and follow the instructions below.

The end goal is to provide utilities to convert other datasets, report accuracies on them and provide models.

Installation

This code requires:

Tensorflow r0.12 or later version.
Custom tensorflow/models repository, which might be merged in a future.

Simply run:

git clone -b fully_conv_vgg https://github.com/warmspringwinds/models

And add models/slim subdirectory to your path:

import sys
# update with your path
sys.path.append('/home/dpakhom1/workspace/models/slim/')

Some libraries which can be acquired by installing Anaconda package.

Or you can install scikit-image, matplotlib, numpy using pip.

VGG 16 checkpoint file, which you can get from here.
Clone this library:

git clone https://github.com/warmspringwinds/tf-image-segmentation

And add it to the path:

import sys
# update with your path
sys.path.append("/home/dpakhom1/tf_projects/segmentation/tf-image-segmentation/")

PASCAL VOC 2012

Implemented models were tested on Restricted PASCAL VOC 2012 Validation dataset (RV-VOC12) and trained on the PASCAL VOC 2012 Training data and additional Berkeley segmentation data for PASCAL VOC 12. It was important to test models on restricted Validation dataset to make sure no images in the validation dataset were seen by model during training.

The code to acquire the training and validating the model is also provided in the framework.

Fully Convolutional Networks for Semantic Segmentation (FCNs)

Here you can find models that were described in the paper "Fully Convolutional Networks for Semantic Segmentation" by Long et al. We trained and tested FCN-32s, FCN-16s and FCN-8s against PASCAL VOC 2012 dataset.

You can find all the scripts that were used for training and evaluation here.

This code has been used to train networks with this performance:

Model	Test data	Mean IOU	Mean pix. accuracy	Pixel accuracy	Model Download Link
FCN-32s (ours)	RV-VOC12	62.70	in prog.	in prog.	Dropbox
FCN-16s (ours)	RV-VOC12	63.52	in prog.	in prog.	Dropbox
FCN-8s (ours)	RV-VOC12	63.65	in prog.	in prog.	Dropbox
FCN-32s (orig.)	RV-VOC11	59.40	73.30	89.10
FCN-16s (orig.)	RV-VOC11	62.40	75.70	90.00
FCN-8s (orig.)	RV-VOC11	62.70	75.90	90.30

About

If you used the code for your research, please, cite the paper:

@article{pakhomov2017deep,
  title={Deep Residual Learning for Instrument Segmentation in Robotic Surgery},
  author={Pakhomov, Daniil and Premachandran, Vittal and Allan, Max and Azizian, Mahdi and Navab, Nassir},
  journal={arXiv preprint arXiv:1703.08580},
  year={2017}
}

During implementation, some preliminary experiments and notes were reported:

License

warmspringwinds/tf-image-segmentation

ErrorLooks like something went wrong!

About

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases

Packages 0

Uh oh!

Languages

Error
Looks like something went wrong!

Packages