Giter VIP home page Giter VIP logo

pytorch-segmentation-detection's Introduction

Image Segmentation and Object Detection in Pytorch

Pytorch-Segmentation-Detection is a library for image segmentation and object detection with reported results achieved on common image segmentation/object detection datasets, pretrained models and scripts to reproduce them.

Segmentation

PASCAL VOC 2012

Implemented models were tested on Restricted PASCAL VOC 2012 Validation dataset (RV-VOC12) or Full PASCAL VOC 2012 Validation dataset (VOC-2012) and trained on the PASCAL VOC 2012 Training data and additional Berkeley segmentation data for PASCAL VOC 12.

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 Inference time (512x512 px. image) Model Download Link Related paper
Resnet-18-8s RV-VOC12 59.0 in prog. in prog. 28 ms. Dropbox DeepLab
Resnet-34-8s RV-VOC12 68.0 in prog. in prog. 50 ms. Dropbox DeepLab
Resnet-50-16s VOC12 66.5 in prog. in prog. in prog. in prog. DeepLab
Resnet-50-8s VOC12 67.0 in prog. in prog. in prog. in prog. DeepLab
Resnet-50-8s-deep-sup VOC12 67.1 in prog. in prog. in prog. in prog. DeepLab
Resnet-101-16s VOC12 68.6 in prog. in prog. in prog. in prog. DeepLab
PSP-Resnet-18-8s VOC12 68.3 n/a n/a n/a in prog. PSPnet
PSP-Resnet-50-8s VOC12 73.6 n/a n/a n/a in prog. PSPnet

Some qualitative results:

Alt text

Endovis 2017

Implemented models were trained on Endovis 2017 segmentation dataset and the sequence number 3 was used for validation and was not included in training dataset.

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

Additional Qualitative results can be found on this youtube playlist.

Binary Segmentation

Model Test data Mean IOU Mean pix. accuracy Pixel accuracy Inference time (512x512 px. image) Model Download Link
Resnet-9-8s Seq # 3 * 96.1 in prog. in prog. 13.3 ms. Dropbox
Resnet-18-8s Seq # 3 96.0 in prog. in prog. 28 ms. Dropbox
Resnet-34-8s Seq # 3 in prog. in prog. in prog. 50 ms. in prog.

Resnet-9-8s network was tested on the 0.5 reduced resoulution (512 x 640).

Qualitative results (on validation sequence):

Alt text

Multi-class Segmentation

Model Test data Mean IOU Mean pix. accuracy Pixel accuracy Inference time (512x512 px. image) Model Download Link
Resnet-18-8s Seq # 3 81.0 in prog. in prog. 28 ms. Dropbox
Resnet-34-8s Seq # 3 in prog. in prog. in prog. 50 ms. in prog

Qualitative results (on validation sequence):

Alt text

Cityscapes

The dataset contains video sequences recorded in street scenes from 50 different cities, with high quality pixel-level annotations of 5โ€ฏ000 frames. The annotations contain 19 classes which represent cars, road, traffic signs and so on.

Model Test data Mean IOU Mean pix. accuracy Pixel accuracy Inference time (512x512 px. image) Model Download Link
Resnet-18-32s Validation set 61.0 in prog. in prog. in prog. in prog.
Resnet-18-8s Validation set 60.0 in prog. in prog. 28 ms. Dropbox
Resnet-34-8s Validation set 69.1 in prog. in prog. 50 ms. Dropbox
Resnet-50-16s-PSP Validation set 71.2 in prog. in prog. in prog. in prog.

Qualitative results (on validation sequence):

Whole sequence can be viewed here.

Alt text

Installation

This code requires:

  1. Pytorch.

  2. Some libraries which can be acquired by installing Anaconda package.

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

  3. Clone the library:

git clone --recursive https://github.com/warmspringwinds/pytorch-segmentation-detection

And use this code snippet before you start to use the library:

import sys
# update with your path
# All the jupyter notebooks in the repository already have this
sys.path.append("/your/path/pytorch-segmentation-detection/")
sys.path.insert(0, '/your/path/pytorch-segmentation-detection/vision/')

Here we use our pytorch/vision fork, which might be merged and futher merged in a future. We have added it as a submodule to our repository.

  1. Download segmentation or detection models that you want to use manually (links can be found below).

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:

pytorch-segmentation-detection's People

Contributors

erasaur avatar iamwilliamli avatar peteflorence avatar randl avatar warmspringwinds avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.