Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Deep neural network for object detection and semantic segmentation in real-time. Official code for the paper "BlitzNet: A Real-Time Deep Network for Scene Understanding"
| Date | Stars |
|---|---|
| 2026-07-31 | 318 |
| 2026-08-01 | 318 |
| 2026-08-02 | 318 |
| 2026-08-06 | 318 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# BlitzNet: A Real-Time Deep Network for Scene Understanding
Deep neural network for object detection and semantic segmentation in real-time.
## Introduction
This repository contains original implementation of the paper 'BlitzNet: A Real-Time Deep Network for Scene Understanding' by Nikita Dvornik, Konstantin Shmelkov, Julien Mairal and Cordelia Schmid.
The paper is available at https://arxiv.org/abs/1708.02813
The page of the paper is http://thoth.inrialpes.fr/research/blitznet/
## Citing
Please cite BlitzNet in your publications if it helps your research:
@inproceedings{dvornik2017blitznet,
title = {{BlitzNet}: A Real-Time Deep Network for Scene Understanding},
author = {Dvornik, Nikita and Shmelkov, Konstantin and Mairal, Julien and Schmid, Cordelia},
booktitle = {{IEEE International Conference on Computer Vision (ICCV)}},
year = {2017}
}
## Requirements
* Python 3.5
* Tensorflow >=1.2
* Numpy 1.13
* Matplotlib 2.0.0
* OpenCV 3.2
* PIL 4.0
* glob
* tabulate
* progressbar
## Datasets
In this work we used the Pascal VOC07, VOC12 and the Microsoft COCO datasets. For the experiments with Pascal VOC datasets we also leveraged extra segmentation annotation provided by B. Hariharan et al. available [here](http://home.bharathh.info/pubs/codes/SBD/download.html).
## Instalation
Clone this git repository
```sh
git clone https://github.com/dvornikita/blitznet.git
```
and install all the requirements listed above.
## Preparation
1. Enter the directory of the project and set the paths to your directories in the file `paths.py`.
2. Download VOC2007 and VOC2012 dataset. By default, we assume the data is stored in `$HOME/Datasets/`.
```sh
# Download the data.
cd $HOME/Datasets
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
# Extract the data.
tar -xvf VOCtrainval_11-May-2012.tar
tar -xvf VOCtrainval_06-Nov-2007.tar
tar -xvf VOCtest_06-Nov-2007.tar
```
3. If you would like to use extra annotations for segmentation provided by B. Hariharan et al., run `set_extra_annotations.py`. If you want a model with better performance this step is recommended.
4. If you would like to train on COCO, visit http://mscoco.org/ for more information. You will need to install [pycocotools](https://github.com/pdollar/coco) and place a dataset in the `$HOME/Datasets/`.
5. We encode training data into a protobuf file to efficiently load the data during training. For this, you need to open the file `datasets.py` and uncomment needed dataset in the body of 'main' function. Then run the `datasets.py`. The dataset will be saved in `$HOME/Datasets/`.
## Running a demo with pretrained net
1. After you downloaded the models run (given you want to suppress all the detections with confidence less then 0.5)
```sh
python demo.py --run_name=BlitzNet300_COCO+VOC07+12 --x4 --detect --segment --eval_min_conf=0.5 --ckpt=1
```
2. Check the output in `$HOME/Demo/output`.
## Running BlitzNet with user interface (NEW)
1. Go to the folder `$HOME/interface` and run demo.sh script. It will
initialize the network and run the user interface where you can upload your
images and apply the algorithm to them.
2. The button `Browse` opens file dialog and allows to select an image on the
hard drive to operate on. To change the initial directory for browsing
modify the variable init_path in `$HOME/interface/main.py`
The button `From Clipboard` allows to grab the link to an image (in WEB) from
your clipboard (of course, you need to copy the link before) and to download it
automatically. To change a folder where the images are saved modify the
variable DOWNLOAD_ROOT in `$HOME/interface/demo_utils.py`.
Excerpt of 9,853 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6b08e0f4ee33aeb4, llm:Description: 'Deep neural network for object detection and semantic segmentation in real-time. Official code for the paper "BlitzNet: A Real-Time Deep Network for Scene Understanding"'
matched fp:6b08e0f4ee33aeb4, llm:Description: 'Deep neural network for object detection and semantic segmentation in real-time. Official code for the paper "BlitzNet: A Real-Time Deep Network for Scene Understanding"'