PingoLH / Fchardnet
Licence: mit
Fully Convolutional HarDNet for Segmentation in Pytorch
Stars: ✭ 150
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Fchardnet
Panoptic Deeplab
This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)
Stars: ✭ 355 (+136.67%)
Mutual labels: semantic-segmentation, cityscapes
Efficient Segmentation Networks
Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)
Stars: ✭ 579 (+286%)
Mutual labels: semantic-segmentation, cityscapes
Icnet Tensorflow
TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".
Stars: ✭ 396 (+164%)
Mutual labels: semantic-segmentation, cityscapes
Pspnet Tensorflow
TensorFlow-based implementation of "Pyramid Scene Parsing Network".
Stars: ✭ 313 (+108.67%)
Mutual labels: semantic-segmentation, cityscapes
Chainer Pspnet
PSPNet in Chainer
Stars: ✭ 76 (-49.33%)
Mutual labels: semantic-segmentation, cityscapes
Edgenets
This repository contains the source code of our work on designing efficient CNNs for computer vision
Stars: ✭ 331 (+120.67%)
Mutual labels: semantic-segmentation, cityscapes
Tusimple Duc
Understanding Convolution for Semantic Segmentation
Stars: ✭ 567 (+278%)
Mutual labels: semantic-segmentation, cityscapes
LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 710 (+373.33%)
Mutual labels: semantic-segmentation, cityscapes
Pytorch Auto Drive
Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, SAD, PRNet, RESA, LSTR...) based on PyTorch 1.6 with mixed precision training
Stars: ✭ 32 (-78.67%)
Mutual labels: semantic-segmentation, cityscapes
Deeplabv3 Plus
Tensorflow 2.3.0 implementation of DeepLabV3-Plus
Stars: ✭ 32 (-78.67%)
Mutual labels: semantic-segmentation, cityscapes
Contrastiveseg
Exploring Cross-Image Pixel Contrast for Semantic Segmentation
Stars: ✭ 135 (-10%)
Mutual labels: semantic-segmentation, cityscapes
Nas Segm Pytorch
Code for Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells, CVPR '19
Stars: ✭ 126 (-16%)
Mutual labels: semantic-segmentation, cityscapes
Erfnet pytorch
Pytorch code for semantic segmentation using ERFNet
Stars: ✭ 304 (+102.67%)
Mutual labels: semantic-segmentation, cityscapes
Ademxapp
Code for https://arxiv.org/abs/1611.10080
Stars: ✭ 333 (+122%)
Mutual labels: semantic-segmentation, cityscapes
DST-CBC
Implementation of our paper "DMT: Dynamic Mutual Training for Semi-Supervised Learning"
Stars: ✭ 98 (-34.67%)
Mutual labels: semantic-segmentation, cityscapes
Fasterseg
[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang
Stars: ✭ 438 (+192%)
Mutual labels: semantic-segmentation, cityscapes
plusseg
ShanghaiTech PLUS Lab Segmentation Toolbox and Benchmark
Stars: ✭ 21 (-86%)
Mutual labels: semantic-segmentation, cityscapes
Dilation-Pytorch-Semantic-Segmentation
A PyTorch implementation of semantic segmentation according to Multi-Scale Context Aggregation by Dilated Convolutions by Yu and Koltun.
Stars: ✭ 32 (-78.67%)
Mutual labels: semantic-segmentation, cityscapes
Lightnet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 698 (+365.33%)
Mutual labels: semantic-segmentation, cityscapes
Dabnet
Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019)
Stars: ✭ 109 (-27.33%)
Mutual labels: semantic-segmentation, cityscapes
FCHarDNet
Fully Convolutional HarDNet for Segmentation in Pytorch
- Implementaion based on Harmonic DenseNet: A low memory traffic network (ICCV 2019)
- Refer to Pytorch-HarDNet for more information about the backbone model
- This repo was forked from meetshah1995/pytorch-semseg
Architecture
- Simple U-shaped encoder-decoder structure
- Conv3x3/Conv1x1 only (including the first layer)
- No self-attention layer or Pyramid Pooling
Results
| Method | #Param (M) |
GMACs / GFLOPs |
Cityscapes mIoU |
fps on Titan-V @1024x2048 |
fps on 1080ti @1024x2048 |
|---|---|---|---|---|---|
| ICNet | 7.7 | 30.7 | 69.5 | 63 | 48 |
| SwiftNetRN-18 | 11.8 | 104 | 75.5 | - | 39.9 |
| BiSeNet (1024x2048) | 13.4 | 119 | 77.7 | 36 | 27 |
| BiSeNet (768x1536) | 13.4 | 66.8 | 74.7 | 72** | 54** |
| FC-HarDNet-70 | 4.1 | 35.4 | 76.0 | 70 | 53 |
- ** Speed tested in 1536x768 instead of full resolution.
DataLoaders implemented
Requirements
- pytorch >=0.4.0
- torchvision ==0.2.0
- scipy
- tqdm
- tensorboardX
Usage
Setup config file
Please see the usage section in meetshah1995/pytorch-semseg
To train the model :
python train.py [-h] [--config [CONFIG]]
--config Configuration file to use (default: hardnet.yml)
To validate the model :
usage: validate.py [-h] [--config [CONFIG]] [--model_path [MODEL_PATH]] [--save_image]
[--eval_flip] [--measure_time]
--config Config file to be used
--model_path Path to the saved model
--eval_flip Enable evaluation with flipped image | False by default
--measure_time Enable evaluation with time (fps) measurement | True by default
--save_image Enable writing result images to out_rgb (pred label blended images) and out_predID
Pretrained Weights
- Cityscapes pretrained weights: Download
(Val mIoU: 77.7, Test mIoU: 75.9) - Cityscapes pretrained with color jitter augmentation: Download
(Val mIoU: 77.4, Test mIoU: 76.0) - HarDNet-Petite weights pretrained by ImageNet:
included in weights/hardnet_petite_base.pth
Prediction Samples
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].