CNN
所属分类：matlab编程
开发工具：matlab
文件大小：270KB
下载次数：5
上传日期：2020-11-07 20:54:15
上 传 者：
wdxzyf999
说明： 卷积神经网络（CNN）主要是用于图像识别领域，它指的是一类网络，而不是某一种，其包含很多不同种结构的网络。不同的网络结构通常表现会不一样。从CNN的一些典型结构中，可以看到这些网络创造者非常有创造力，很多结构都非常巧妙，有机会再介绍现今主流的一些典型结构。 现在我们先来简单介绍一下卷积神经网络的原理。
(Convolutional neural network (CNN) is mainly used in the field of image recognition. It refers to a kind of network, not a certain kind of network, which contains many networks with different structures. Different network structures usually behave differently. From some typical structures of CNN, we can see that these network creators are very creative, and many of them are very clever. We have the opportunity to introduce some typical structures of the mainstream today. Now let's briefly introduce the principle of convolution neural network.)
文件列表:
data\demo\000004.jpg (102770, 2018-01-23)
data\demo\000004_boxes.mat (23296, 2018-01-23)
data\demo\001551.jpg (69440, 2018-01-23)
data\demo\001551_boxes.mat (16648, 2018-01-23)
data\pylintrc (56, 2018-01-23)
data\scripts\fetch_fast_rcnn_models.sh (832, 2018-01-23)
data\scripts\fetch_imagenet_models.sh (831, 2018-01-23)
data\scripts\fetch_selective_search_data.sh (853, 2018-01-23)
experiments\cfgs\fc_only.yml (50, 2018-01-23)
experiments\cfgs\multiscale.yml (200, 2018-01-23)
experiments\cfgs\no_bbox_reg.yml (102, 2018-01-23)
experiments\cfgs\piecewise.yml (54, 2018-01-23)
experiments\cfgs\svm.yml (223, 2018-01-23)
experiments\scripts\all_caffenet.sh (370, 2018-01-23)
experiments\scripts\all_vgg16.sh (364, 2018-01-23)
experiments\scripts\all_vgg_cnn_m_1024.sh (376, 2018-01-23)
experiments\scripts\default_caffenet.sh (539, 2018-01-23)
experiments\scripts\default_vgg16.sh (524, 2018-01-23)
experiments\scripts\default_vgg_cnn_m_1024.sh (569, 2018-01-23)
experiments\scripts\fc_only_vgg16.sh (618, 2018-01-23)
experiments\scripts\multiscale_caffenet.sh (640, 2018-01-23)
experiments\scripts\multiscale_vgg_cnn_m_1024.sh (670, 2018-01-23)
experiments\scripts\multitask_no_bbox_reg_caffenet.sh (428, 2018-01-23)
experiments\scripts\multitask_no_bbox_reg_vgg16.sh (419, 2018-01-23)
experiments\scripts\multitask_no_bbox_reg_vgg_cnn_m_1024.sh (446, 2018-01-23)
experiments\scripts\no_bbox_reg_caffenet.sh (669, 2018-01-23)
experiments\scripts\no_bbox_reg_vgg16.sh (654, 2018-01-23)
experiments\scripts\no_bbox_reg_vgg_cnn_m_1024.sh (699, 2018-01-23)
experiments\scripts\piecewise_caffenet.sh (691, 2018-01-23)
experiments\scripts\piecewise_vgg16.sh (676, 2018-01-23)
experiments\scripts\piecewise_vgg_cnn_m_1024.sh (721, 2018-01-23)
experiments\scripts\svd_caffenet.sh (608, 2018-01-23)
experiments\scripts\svd_vgg16.sh (590, 2018-01-23)
experiments\scripts\svd_vgg_cnn_m_1024.sh (645, 2018-01-23)
... ...
# fast-rcnn has been deprecated. Please see [Detectron](https://github.com/facebookresearch/Detectron), which includes an implementation of [Mask R-CNN](https://arxiv.org/abs/1703.06870).
### This code base is no longer maintained and exists as a historical artifact to supplement my ICCV 2015 paper. For more recent work that's faster and more accurrate, please see [Faster R-CNN](https://github.com/rbgirshick/py-faster-rcnn) (which also includes functionality for training Fast R-CNN).
# *Fast* R-CNN: Fast Region-based Convolutional Networks for object detection
Created by Ross Girshick at Microsoft Research, Redmond.
### Introduction
**Fast R-CNN** is a fast framework for object detection with deep ConvNets. Fast R-CNN
- trains state-of-the-art models, like VGG16, 9x faster than traditional R-CNN and 3x faster than SPPnet,
- runs 200x faster than R-CNN and 10x faster than SPPnet at test-time,
- has a significantly higher mAP on PASCAL VOC than both R-CNN and SPPnet,
- and is written in Python and C++/Caffe.
Fast R-CNN was initially described in an [arXiv tech report](http://arxiv.org/abs/1504.08083) and later published at ICCV 2015.
### License
Fast R-CNN is released under the MIT License (refer to the LICENSE file for details).
### Citing Fast R-CNN
If you find Fast R-CNN useful in your research, please consider citing:
@inproceedings{girshickICCV15fastrcnn,
Author = {Ross Girshick},
Title = {Fast R-CNN},
Booktitle = {International Conference on Computer Vision ({ICCV})},
Year = {2015}
}
### Contents
1. [Requirements: software](#requirements-software)
2. [Requirements: hardware](#requirements-hardware)
3. [Basic installation](#installation-sufficient-for-the-demo)
4. [Demo](#demo)
5. [Beyond the demo: training and testing](#beyond-the-demo-installation-for-training-and-testing-models)
6. [Usage](#usage)
7. [Extra downloads](#extra-downloads)
### Requirements: software
1. Requirements for `Caffe` and `pycaffe` (see: [Caffe installation instructions](http://caffe.berkeleyvision.org/installation.html))
**Note:** Caffe *must* be built with support for Python layers!
```make
# In your Makefile.config, make sure to have this line uncommented
WITH_PYTHON_LAYER := 1
```
You can download my [Makefile.config](https://dl.dropboxusercontent.com/s/6joa55k***xo2h68/Makefile.config?dl=0) for reference.
2. Python packages you might not have: `cython`, `python-opencv`, `easydict`
3. [optional] MATLAB (required for PASCAL VOC evaluation only)
### Requirements: hardware
1. For training smaller networks (CaffeNet, VGG_CNN_M_1024) a good GPU (e.g., Titan, K20, K40, ...) with at least 3G of memory suffices
2. For training with VGG16, you'll need a K40 (~11G of memory)
### Installation (sufficient for the demo)
1. Clone the Fast R-CNN repository
```Shell
# Make sure to clone with --recursive
git clone --recursive https://github.com/rbgirshick/fast-rcnn.git
```
2. We'll call the directory that you cloned Fast R-CNN into `FRCN_ROOT`
*Ignore notes 1 and 2 if you followed step 1 above.*
**Note 1:** If you didn't clone Fast R-CNN with the `--recursive` flag, then you'll need to manually clone the `caffe-fast-rcnn` submodule:
```Shell
git submodule update --init --recursive
```
**Note 2:** The `caffe-fast-rcnn` submodule needs to be on the `fast-rcnn` branch (or equivalent detached state). This will happen automatically *if you follow these instructions*.
3. Build the Cython modules
```Shell
cd $FRCN_ROOT/lib
make
```
4. Build Caffe and pycaffe
```Shell
cd $FRCN_ROOT/caffe-fast-rcnn
# Now follow the Caffe installation instructions here:
# http://caffe.berkeleyvision.org/installation.html
# If you're experienced with Caffe and have all of the requirements installed
# and your Makefile.config in place, then simply do:
make -j8 && make pycaffe
```
5. Download pre-computed Fast R-CNN detectors
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_fast_rcnn_models.sh
```
This will populate the `$FRCN_ROOT/data` folder with `fast_rcnn_models`. See `data/README.md` for details.
### Demo
*After successfully completing [basic installation](#installation-sufficient-for-the-demo)*, you'll be ready to run the demo.
**Python**
To run the demo
```Shell
cd $FRCN_ROOT
./tools/demo.py
```
The demo performs detection using a VGG16 network trained for detection on PASCAL VOC 2007. The object proposals are pre-computed in order to reduce installation requirements.
**Note:** If the demo crashes Caffe because your GPU doesn't have enough memory, try running the demo with a small network, e.g., `./tools/demo.py --net caffenet` or with `--net vgg_cnn_m_1024`. Or run in CPU mode `./tools/demo.py --cpu`. Type `./tools/demo.py -h` for usage.
**MATLAB**
There's also a *basic* MATLAB demo, though it's missing some minor bells and whistles compared to the Python version.
```Shell
cd $FRCN_ROOT/matlab
matlab # wait for matlab to start...
# At the matlab prompt, run the script:
>> fast_rcnn_demo
```
Fast R-CNN training is implemented in Python only, but test-time detection functionality also exists in MATLAB.
See `matlab/fast_rcnn_demo.m` and `matlab/fast_rcnn_im_detect.m` for details.
**Computing object proposals**
The demo uses pre-computed selective search proposals computed with [this code](https://github.com/rbgirshick/rcnn/blob/master/selective_search/selective_search_boxes.m).
If you'd like to compute proposals on your own images, there are many options.
Here are some pointers; if you run into trouble using these resources please direct questions to the respective authors.
1. Selective Search: [original matlab code](http://disi.unitn.it/~uijlings/MyHomepage/index.php#page=projects1), [python wrapper](https://github.com/sergeyk/selective_search_ijcv_with_python)
2. EdgeBoxes: [matlab code](https://github.com/pdollar/edges)
3. GOP and LPO: [python code](http://www.philkr.net/)
4. MCG: [matlab code](http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/mcg/)
5. RIGOR: [matlab code](http://cpl.cc.gatech.edu/projects/RIGOR/)
Apologies if I've left your method off this list. Feel free to contact me and ask for it to be included.
### Beyond the demo: installation for training and testing models
1. Download the training, validation, test data and VOCdevkit
```Shell
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar
```
2. Extract all of these tars into one directory named `VOCdevkit`
```Shell
tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar
```
3. It should have this basic structure
```Shell
$VOCdevkit/ # development kit
$VOCdevkit/VOCcode/ # VOC utility code
$VOCdevkit/VOC2007 # image sets, annotations, etc.
# ... and several other directories ...
```
4. Create symlinks for the PASCAL VOC dataset
```Shell
cd $FRCN_ROOT/data
ln -s $VOCdevkit VOCdevkit2007
```
Using symlinks is a good idea because you will likely want to share the same PASCAL dataset installation between multiple projects.
5. [Optional] follow similar steps to get PASCAL VOC 2010 and 2012
6. Follow the next sections to download pre-computed object proposals and pre-trained ImageNet models
### Download pre-computed Selective Search object proposals
Pre-computed selective search boxes can also be downloaded for VOC2007 and VOC2012.
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_selective_search_data.sh
```
This will populate the `$FRCN_ROOT/data` folder with `selective_selective_data`.
### Download pre-trained ImageNet models
Pre-trained ImageNet models can be downloaded for the three networks described in the paper: CaffeNet (model **S**), VGG_CNN_M_1024 (model **M**), and VGG16 (model **L**).
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_imagenet_models.sh
```
These models are all available in the [Caffe Model Zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo), but are provided here for your convenience.
### Usage
**Train** a Fast R-CNN detector. For example, train a VGG16 network on VOC 2007 trainval:
```Shell
./tools/train_net.py --gpu 0 --solver models/VGG16/solver.prototxt \
--weights data/imagenet_models/VGG16.v2.caffemodel
```
If you see this error
```
EnvironmentError: MATLAB command 'matlab' not found. Please add 'matlab' to your PATH.
```
then you need to make sure the `matlab` binary is in your `$PATH`. MATLAB is currently required for PASCAL VOC evaluation.
**Test** a Fast R-CNN detector. For example, test the VGG 16 network on VOC 2007 test:
```Shell
./tools/test_net.py --gpu 1 --def models/VGG16/test.prototxt \
--net output/default/voc_2007_trainval/vgg16_fast_rcnn_iter_40000.caffemodel
```
Test output is written underneath `$FRCN_ROOT/output`.
**Compress** a Fast R-CNN model using truncated SVD on the fully-connected layers:
```Shell
./tools/compress_net.py --def models/VGG16/test.prototxt \
--def-svd models/VGG16/compressed/test.prototxt \
--net output/default/voc_2007_trainval/vgg16_fast_rcnn_iter_40000.caffemodel
# Test the model you just compressed
./tools/test_net.py --gpu 0 --def models/VGG16/compressed/test.prototxt \
--net output/default/voc_2007_trainval/vgg16_fast_rcnn_iter_40000_svd_fc6_1024_fc7_256.caffemodel
```
### Experiment scripts
Scripts to reproduce the experiments in the paper (*up to stochastic variation*) are provided in `$FRCN_ROOT/experiments/scripts`. Log files for experiments are located in `experiments/logs`.
**Note:** Until recently (commit a566e39), the RNG seed for Caffe was not fixed during training. Now it's fixed, unless `train_net.py` is called with the `--rand` flag.
Results generated before this commit will have some stochastic variation.
### Extra downloads
- [Experiment logs](https://dl.dropboxusercontent.com/s/q4i9v66xq9vhskl/fast_rcnn_experiments.tgz?dl=0)
- PASCAL VOC test set detections
- [voc_2007_test_results_fast_rcnn_caffenet_trained_on_2007_trainval.tgz](https://dl.dropboxusercontent.com/s/rkj8ngkoebpltlt/voc_2007_test_results_fast_rcnn_caffenet_trained_on_2007_trainval.tgz?dl=0)
- [voc_2007_test_results_fast_rcnn_vgg16_trained_on_2007_trainval.tgz](https://dl.dropboxusercontent.com/s/y8supay93f7dj0i/voc_2007_test_results_fast_rcnn_vgg16_trained_on_2007_trainval.tgz?dl=0)
- [voc_2007_test_results_fast_rcnn_vgg_cnn_m_1024_trained_on_2007_trainval.tgz](https://dl.dropboxusercontent.com/s/yiqm42vtvvw60dg/voc_2007_test_results_fast_rcnn_vgg_cnn_m_1024_trained_on_2007_trainval.tgz?dl=0)
- [voc_2012_test_results_fast_rcnn_vgg16_trained_on_2007_trainvaltest_2012_trainval.tgz](https://dl.dropboxusercontent.com/s/a3loiewc4f4tnaj/voc_2012_test_results_fast_rcnn_vgg16_trained_on_2007_trainvaltest_2012_trainval.tgz?dl=0)
- [voc_2012_test_results_fast_rcnn_vgg16_trained_on_2012_trainval.tgz](https://dl.dropboxusercontent.com/s/7pctvinam6j2nho/voc_2012_test_results_fast_rcnn_vgg16_trained_on_2012_trainval.tgz?dl=0)
- [Fast R-CNN VGG16 model](https://dl.dropboxusercontent.com/s/53im2gut2jin2qq/voc12_submission.tgz?dl=0) trained on VOC07 train,val,test union with VOC12 train,val
近期下载者：
相关文件：
收藏者：