All Projects → TimoSaemann → Caffe Segnet Cudnn5

TimoSaemann / Caffe Segnet Cudnn5

Licence: other
This repository was a fork of BVLC/caffe and includes the upsample, bn, dense_image_data and softmax_with_loss (with class weighting) layers of caffe-segnet (https://github.com/alexgkendall/caffe-segnet) to run SegNet with cuDNN version 5.

Labels

Projects that are alternatives of or similar to Caffe Segnet Cudnn5

Noiseface
Noise-Tolerant Paradigm for Training Face Recognition CNNs
Stars: ✭ 132 (-20.96%)
Mutual labels:  caffe
Low Rank Bilinear Pooling
Fine-grained classification via second order statistics in a compact end-to-end trainable model
Stars: ✭ 145 (-13.17%)
Mutual labels:  caffe
Py Rfcn Priv
code for py-R-FCN-multiGPU maintained by bupt-priv
Stars: ✭ 153 (-8.38%)
Mutual labels:  caffe
Facerecognition
This is an implematation project of face detection and recognition. The face detection using MTCNN algorithm, and recognition using LightenenCNN algorithm.
Stars: ✭ 137 (-17.96%)
Mutual labels:  caffe
Anomaly Detection In Surveillance Videos
Real-World Anomaly Detection in Surveillance Videos
Stars: ✭ 139 (-16.77%)
Mutual labels:  caffe
Caffe Mobilenet
A caffe implementation of mobilenet's depthwise convolution layer.
Stars: ✭ 146 (-12.57%)
Mutual labels:  caffe
Darknet2caffe
Convert darknet weights to caffemodel
Stars: ✭ 127 (-23.95%)
Mutual labels:  caffe
Nnef Tools
The NNEF Tools repository contains tools to generate and consume NNEF documents
Stars: ✭ 165 (-1.2%)
Mutual labels:  caffe
Mobilenet Ssd
Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.
Stars: ✭ 1,805 (+980.84%)
Mutual labels:  caffe
Sphereface Plus
SphereFace+ Implementation for <Learning towards Minimum Hyperspherical Energy> in NIPS'18.
Stars: ✭ 151 (-9.58%)
Mutual labels:  caffe
Flownet2 Docker
Dockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)
Stars: ✭ 137 (-17.96%)
Mutual labels:  caffe
Mobilenetv2
Stars: ✭ 138 (-17.37%)
Mutual labels:  caffe
Turkce Yapay Zeka Kaynaklari
Türkiye'de yapılan derin öğrenme (deep learning) ve makine öğrenmesi (machine learning) çalışmalarının derlendiği sayfa.
Stars: ✭ 1,900 (+1037.72%)
Mutual labels:  caffe
Xlearning
AI on Hadoop
Stars: ✭ 1,709 (+923.35%)
Mutual labels:  caffe
Resnet Cifar10 Caffe
ResNet-20/32/44/56/110 on CIFAR-10 with Caffe
Stars: ✭ 161 (-3.59%)
Mutual labels:  caffe
Videoauidt
📹 一个短视频APP视频内容安全审核的思路调研及实现汇总
Stars: ✭ 129 (-22.75%)
Mutual labels:  caffe
Ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Stars: ✭ 13,376 (+7909.58%)
Mutual labels:  caffe
Deformable Convnets Caffe
Deformable Convolutional Networks on caffe
Stars: ✭ 166 (-0.6%)
Mutual labels:  caffe
Caffe Yolo9000
Caffe for YOLOv2 & YOLO9000
Stars: ✭ 164 (-1.8%)
Mutual labels:  caffe
Brocolli
pytorch 2 caffe
Stars: ✭ 150 (-10.18%)
Mutual labels:  caffe

Caffe SegNet cuDNN5

This is a modified version of Caffe which supports the SegNet architecture

As described in SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla [http://arxiv.org/abs/1511.00561]

Please refer to Alex Kendalls caffe-segnet for tutorial and a guide how to use it (https://github.com/alexgkendall/caffe-segnet).

Since the original caffe-segnet supports just cuDNN v2, which is not supported for new pascal based GPUs, it was possible to decrease the inference time by 25 % to 35 % with caffe-segnet-cudnn5 using Titan X Pascal.

I recommend to use my trained weights (CityScapes Model) for semantic segmenation of traffic scenes, which you can find in segnet model zoo: https://github.com/alexgkendall/SegNet-Tutorial/blob/master/Example_Models/segnet_model_zoo.md

If you like to speed up SegNet even further, you can run the BN-absorber.py script. It merges the batch normalization layer into convolutional layer by modyfing its weights and biases. In doing so, it is possible to accelerate it by around 30 %. Please find BN-absorber.py in the script folder.

If you like to use SegNet with C++, the test_segmentation.cpp might be helpful. https://github.com/alexgkendall/SegNet-Tutorial/blob/master/Scripts/test_segmentation.cpp

News

  • If SegNet is too slow for you, try out the ENet in Caffe. It's much faster! (May the 30th, 2017)

  • Speed up SegNet by merging batch normalization and convolutional layer with BN-absorber.py in the script folder. (May the 12th, 2017)

  • cuDNN v.6 has been released. I have tested it using Titan X Pascal. It doesn't bring any noticeable improvements for SegNet. For that reason I will not update the repository to cuDNN6.

Publications

If you use this software in your research, please cite their publications:

http://arxiv.org/abs/1511.02680 Alex Kendall, Vijay Badrinarayanan and Roberto Cipolla "Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding." arXiv preprint arXiv:1511.02680, 2015.

http://arxiv.org/abs/1511.00561 Vijay Badrinarayanan, Alex Kendall and Roberto Cipolla "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation." arXiv preprint arXiv:1511.00561, 2015.

License

This extension to the Caffe library is released under a creative commons license which allows for personal and research use only. For a commercial license please contact the authors. You can view a license summary here: http://creativecommons.org/licenses/by-nc/4.0/

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].