matconvnet-fcn-master
所属分类：图形图像处理
开发工具：matlab
文件大小：22KB
下载次数：50
上传日期：2018-06-26 14:42:17
上 传 者：
果子李
说明： 全卷积神经网络FCN用于图像分割的工具箱
(FCN for image segmentation)
文件列表:
matconvnet-fcn-master (0, 2016-01-23)
matconvnet-fcn-master\bilinear_u.m (675, 2016-01-23)
matconvnet-fcn-master\COPYING (735, 2016-01-23)
matconvnet-fcn-master\fcnInitializeModel.m (4253, 2016-01-23)
matconvnet-fcn-master\fcnInitializeModel16s.m (2138, 2016-01-23)
matconvnet-fcn-master\fcnInitializeModel8s.m (2141, 2016-01-23)
matconvnet-fcn-master\fcnTest.m (6723, 2016-01-23)
matconvnet-fcn-master\fcnTestModelZoo.m (2081, 2016-01-23)
matconvnet-fcn-master\fcnTrain.m (3500, 2016-01-23)
matconvnet-fcn-master\getBatch.m (2531, 2016-01-23)
matconvnet-fcn-master\getDatasetStatistics.m (937, 2016-01-23)
matconvnet-fcn-master\matconvnet (0, 2016-01-23)
matconvnet-fcn-master\SegmentationAccuracy.m (1765, 2016-01-23)
matconvnet-fcn-master\SegmentationLoss.m (952, 2016-01-23)
matconvnet-fcn-master\utils (0, 2016-01-23)
matconvnet-fcn-master\utils\download-split.sh (333, 2016-01-23)
matconvnet-fcn-master\utils\showRF.m (1199, 2016-01-23)
matconvnet-fcn-master\utils\testcaffe.m (1137, 2016-01-23)
matconvnet-fcn-master\utils\testcaffe.py (1990, 2016-01-23)
matconvnet-fcn-master\vocSetup.m (10032, 2016-01-23)
matconvnet-fcn-master\vocSetupAdditionalSegmentations.m (4275, 2016-01-23)
# MatConvNet implementation of the FCN models for semantic segmentation
This package contains an implementation of the FCN models (training
and evaluation) using the MatConvNet library.
For training, look at the `fcnTrain.m` script, and for evaluation at
`fcnTest.m`. The script `fcnTestModelZoo.m` is designed to test third
party networks imported in MatConvNet (mainly from Caffe).
While we are still tuning parameters, on the PASCAL VOC 2011
validation data subset used in the FCN paper, this code has been used
to train networks with this performance:
| Model | Test data |Mean IOU | Mean pix. accuracy | Pixel accuracy |
|-----------------|-----------|---------|--------------------|----------------|
| FCN-32s (ours) | RV-VOC11 | 60.80 | 89.61 | 75.49 |
| FCN-16s (ours) | RV-VOC11 | 62.25 | 90.08 | 77.81 |
| FCN-8s (ours) | RV-VOC11 | in prog.| in prog. | in prog. |
| FNC-32s (orig.) | RV-VOC11 | 59.43 | 89.12 | 73.28 |
| FNC-16s (orig.) | RV-VOC11 | 62.35 | 90.02 | 75.74 |
| FNC-8s (orig.) | RV-VOC11 | 62.69 | 90.33 | 75.86 |
The original FCN models can be downloaded from the MatConvNet
[model repository](http://www.vlfeat.org/matconvnet/pretrained/).
## About
This code was developed by
* Sebastien Ehrhardt
* Andrea Vedaldi
## References
'Fully Convolutional Models for Semantic Segmentation', *Jonathan
Long, Evan Shelhamer and Trevor Darrell*, CVPR, 2015
([paper](http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Long_Fully_Convolutional_Networks_2015_CVPR_paper.pdf)).
## Changes
* v0.9.1 -- Bugfixes.
* v0.9 -- Initial release. FCN32s and FCN16s work well.
近期下载者：
相关文件：
收藏者：