All Projects → TillBeemelmanns → cityscapes-to-coco-conversion

TillBeemelmanns / cityscapes-to-coco-conversion

Licence: other
Cityscapes to CoCo Format Conversion Tool for Mask-RCNN and Detectron

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to cityscapes-to-coco-conversion

multiclass-semantic-segmentation
Experiments with UNET/FPN models and cityscapes/kitti datasets [Pytorch]
Stars: ✭ 96 (+140%)
Mutual labels:  cityscapes, cityscapes-dataset
DA-RetinaNet
Official Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'
Stars: ✭ 31 (-22.5%)
Mutual labels:  cityscapes, cityscapes-dataset
Chainer Pspnet
PSPNet in Chainer
Stars: ✭ 76 (+90%)
Mutual labels:  cityscapes
Decouplesegnets
Implementation of Our ECCV2020-work: Improving Semantic Segmentation via Decoupled Body and Edge Supervision
Stars: ✭ 232 (+480%)
Mutual labels:  cityscapes
Fchardnet
Fully Convolutional HarDNet for Segmentation in Pytorch
Stars: ✭ 150 (+275%)
Mutual labels:  cityscapes
Deeplab V3 Plus Cityscapes
mIOU=80.02 on cityscapes. My implementation of deeplabv3+ (also know as 'Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation' based on the dataset of cityscapes).
Stars: ✭ 121 (+202.5%)
Mutual labels:  cityscapes
Cgnet
CGNet: A Light-weight Context Guided Network for Semantic Segmentation [IEEE Transactions on Image Processing 2020]
Stars: ✭ 186 (+365%)
Mutual labels:  cityscapes
Switchnorm segmentation
Switchable Normalization for semantic image segmentation and scene parsing.
Stars: ✭ 47 (+17.5%)
Mutual labels:  cityscapes
Lightnetplusplus
LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation
Stars: ✭ 218 (+445%)
Mutual labels:  cityscapes
Bisenetv2 Tensorflow
Unofficial tensorflow implementation of real-time scene image segmentation model "BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation"
Stars: ✭ 139 (+247.5%)
Mutual labels:  cityscapes
Contrastiveseg
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Stars: ✭ 135 (+237.5%)
Mutual labels:  cityscapes
Ccnet Pure Pytorch
Criss-Cross Attention for Semantic Segmentation in pure Pytorch with a faster and more precise implementation.
Stars: ✭ 124 (+210%)
Mutual labels:  cityscapes
Fastseg
📸 PyTorch implementation of MobileNetV3 for real-time semantic segmentation, with pretrained weights & state-of-the-art performance
Stars: ✭ 202 (+405%)
Mutual labels:  cityscapes
Dabnet
Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019)
Stars: ✭ 109 (+172.5%)
Mutual labels:  cityscapes
instance-segmentation
No description or website provided.
Stars: ✭ 40 (+0%)
Mutual labels:  mask-rcnn
City Scapes Script
Download City Scapes Dataset using this script
Stars: ✭ 57 (+42.5%)
Mutual labels:  cityscapes
Robust Detection Benchmark
Code, data and benchmark from the paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" (NeurIPS 2019 ML4AD)
Stars: ✭ 128 (+220%)
Mutual labels:  cityscapes
Hrnet Semantic Segmentation
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
Stars: ✭ 2,369 (+5822.5%)
Mutual labels:  cityscapes
MetalCity
MetalCity - a procedural night city landscape generator
Stars: ✭ 29 (-27.5%)
Mutual labels:  cityscapes
image-segmentation
Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available
Stars: ✭ 62 (+55%)
Mutual labels:  mask-rcnn

Cityscapes to CoCo Conversion Tool

This script allows to convert the Cityscapes Dataset to Mircosoft's CoCo Format. The code heavily relies on Facebook's Detection Repo and Cityscapes Scripts.

The converted annotations can be easily used for Mask-RCNN or other deep learning projects.

Folder Structure

Download the Cityscapes Dataset and organize the files in the following structure. Create an empty annotations directory.

data/
└── cityscapes
    ├── annotations
    ├── gtFine
    │   ├── test
    │   ├── train
    │   └── val
    └── leftImg8bit
        ├── test
        ├── train
        └── val
main.py
inspect_coco.py
README.md
requirements.txt

Installation

pip install -r requirements.txt 

Run

To run the conversion execute the following

python main.py --dataset cityscapes --datadir data/cityscapes --outdir data/cityscapes/annotations

In order to run the visualization of the CoCo dataset you may run

python inspect_coco.py --coco_dir data/cityscapes

Output

vis1 vis2

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].