LikeLy-Journey / Segmentron
Licence: apache-2.0
Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
Stars: ✭ 490
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Segmentron
Tf Faster Rcnn
Tensorflow Faster RCNN for Object Detection
Stars: ✭ 3,604 (+635.51%)
Mutual labels: mobilenet, coco
Lightnet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 698 (+42.45%)
Mutual labels: mobilenet, cityscapes
LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 710 (+44.9%)
Mutual labels: cityscapes, mobilenet
Edgenets
This repository contains the source code of our work on designing efficient CNNs for computer vision
Stars: ✭ 331 (-32.45%)
Mutual labels: cityscapes
Embedded Ai.bi Weekly
嵌入式AI公众号: NeuralTalk,Weekly report and awesome list of embedded-ai.
Stars: ✭ 331 (-32.45%)
Mutual labels: mobilenet
Segmentation.x
Papers and Benchmarks about semantic segmentation, instance segmentation, panoptic segmentation and video segmentation
Stars: ✭ 450 (-8.16%)
Mutual labels: cityscapes
Pspnet Tensorflow
TensorFlow-based implementation of "Pyramid Scene Parsing Network".
Stars: ✭ 313 (-36.12%)
Mutual labels: 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 (-10.61%)
Mutual labels: cityscapes
Pytorch Human Pose Estimation
Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
Stars: ✭ 346 (-29.39%)
Mutual labels: coco
Icnet Tensorflow
TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".
Stars: ✭ 396 (-19.18%)
Mutual labels: cityscapes
Pytorch Mobilenet
PyTorch MobileNet Implementation of "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"
Stars: ✭ 443 (-9.59%)
Mutual labels: mobilenet
Mobilenetv2 Ssdlite
Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.
Stars: ✭ 435 (-11.22%)
Mutual labels: mobilenet
Deeplabv3plus Pytorch
DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes
Stars: ✭ 337 (-31.22%)
Mutual labels: cityscapes
Adaptis
[ICCV19] AdaptIS: Adaptive Instance Selection Network, https://arxiv.org/abs/1909.07829
Stars: ✭ 314 (-35.92%)
Mutual labels: cityscapes
Mobilefacenet V2
🔥improve the accuracy of mobilefacenet(insight face) reached 99.733 in the cfp-ff、 the 99.68+ in lfw,96.71+ in agedb30.🔥
Stars: ✭ 339 (-30.82%)
Mutual labels: mobilenet
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 (-27.55%)
Mutual labels: cityscapes
Myvision
Computer vision based ML training data generation tool 🚀
Stars: ✭ 453 (-7.55%)
Mutual labels: coco
PyTorch for Semantic Segmentation
Introduce
This repository contains some models for semantic segmentation and the pipeline of training and testing models, implemented in PyTorch.
Model zoo
Model | Backbone | Datasets | eval size | Mean IoU(paper) | Mean IoU(this repo) |
---|---|---|---|---|---|
DeepLabv3_plus | xception65 | cityscape(val) | (1025,2049) | 78.8 | 78.93 |
DeepLabv3_plus | xception65 | coco(val) | 480/520 | - | 70.50 |
DeepLabv3_plus | xception65 | pascal_aug(val) | 480/520 | - | 89.56 |
DeepLabv3_plus | xception65 | pascal_voc(val) | 480/520 | - | 88.39 |
DeepLabv3_plus | resnet101 | cityscape(val) | (1025,2049) | - | 78.27 |
Danet | resnet101 | cityscape(val) | (1024,2048) | 79.9 | 79.34 |
Pspnet | resnet101 | cityscape(val) | (1025,2049) | 78.63 | 77.00 |
real-time models
Model | Backbone | Datasets | eval size | Mean IoU(paper) | Mean IoU(this repo) | FPS |
---|---|---|---|---|---|---|
ICnet | resnet50(0.5) | cityscape(val) | (1024,2048) | 67.8 | - | 41.39 |
DeepLabv3_plus | mobilenetV2 | cityscape(val) | (1024,2048) | 70.7 | 70.3 | 46.64 |
BiSeNet | resnet18 | cityscape(val) | (1024,2048) | - | - | 39.90 |
LEDNet | - | cityscape(val) | (1024,2048) | - | - | 31.78 |
CGNet | - | cityscape(val) | (1024,2048) | - | - | 46.11 |
HardNet | - | cityscape(val) | (1024,2048) | 75.9 | - | 69.06 |
DFANet | xceptionA | cityscape(val) | (1024,2048) | 70.3 | - | 21.46 |
HRNet | w18_small_v1 | cityscape(val) | (1024,2048) | 70.3 | 70.5 | 66.01 |
Fast_SCNN | - | cityscape(val) | (1024,2048) | 68.3 | 68.9 | 145.77 |
FPS was tested on V100.
Environments
- python 3
- torch >= 1.1.0
- torchvision
- pyyaml
- Pillow
- numpy
INSTALL
python setup.py develop
if you do not want to run CCNet, you do not need to install, just comment following line in segmentron/models/__init__.py
from .ccnet import CCNet
Dataset prepare
Support cityscape, coco, voc, ade20k now.
Please refer to DATA_PREPARE.md for dataset preparation.
Pretrained backbone models
pretrained backbone models will be download automatically in pytorch default directory(~/.cache/torch/checkpoints/
).
Code structure
├── configs # yaml config file
├── segmentron # core code
├── tools # train eval code
└── datasets # put datasets here
Train
Train with a single GPU
CUDA_VISIBLE_DEVICES=0 python -u tools/train.py --config-file configs/cityscapes_deeplabv3_plus.yaml
Train with multiple GPUs
CUDA_VISIBLE_DEVICES=0,1,2,3 ./tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM} [optional arguments]
Eval
Eval with a single GPU
You can download trained model from model zoo table above, or train by yourself.
CUDA_VISIBLE_DEVICES=0 python -u ./tools/eval.py --config-file configs/cityscapes_deeplabv3_plus.yaml \
TEST.TEST_MODEL_PATH your_test_model_path
Eval with a multiple GPUs
CUDA_VISIBLE_DEVICES=0,1,2,3 ./tools/dist_test.sh ${CONFIG_FILE} ${GPU_NUM} \
TEST.TEST_MODEL_PATH your_test_model_path
References
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].