深度学习之目标检测我爱编程

基于python+caffe的faster rcnn训练识别

2018-02-08  本文已影响1241人  db24cc

目录

  1. 环境setup
  2. 标注数据
  3. 训练和识别

1.环境setup

之前由于硬件平台的原因, 不支持tensorflow,用caffe作识别
我的GPU上有三个版本的caffe, 一个是原生的native-caffe, 一个是适配faster rcnn的内嵌在py-faster-rcnn中的caffe, 一个是适配ssd的caffe

caffe目前处于没有人维护的状态, 如果不是条件所限还是尽量使用tensorflow, 如果受限使用caffe应该考虑使用docker的手段隔离环境, 否则极易产生环境冲突
前提是装好opencv, cuda和cudnn

cat $FRCN_ROOT/caffe-fast-rcnn/Makefile.config
## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
# USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1

# uncomment to disable IO dependencies and corresponding data layers
USE_OPENCV := 1
# USE_LEVELDB := 0
USE_LMDB := 1

# uncomment to allow MDB_NOLOCK when reading LMDB files (only if necessary)
#   You should not set this flag if you will be reading LMDBs with any
#   possibility of simultaneous read and write
# ALLOW_LMDB_NOLOCK := 1

# Uncomment if you're using OpenCV 3
OPENCV_VERSION := 3

# To customize your choice of compiler, uncomment and set the following.
# N.B. the default for Linux is g++ and the default for OSX is clang++
# CUSTOM_CXX := g++

# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda
# On Ubuntu 14.04, if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

# CUDA architecture setting: going with all of them.
# For CUDA < 6.0, comment the *_50 lines for compatibility.
CUDA_ARCH := -gencode arch=compute_20,code=sm_20 \
        -gencode arch=compute_20,code=sm_21 \
        -gencode arch=compute_30,code=sm_30 \
        -gencode arch=compute_35,code=sm_35 \
        -gencode arch=compute_50,code=sm_50 \
        -gencode arch=compute_50,code=compute_50

# BLAS choice:
# atlas for ATLAS (default)
# mkl for MKL
# open for OpenBlas
BLAS := atlas
# Custom (MKL/ATLAS/OpenBLAS) include and lib directories.
# Leave commented to accept the defaults for your choice of BLAS
# (which should work)!
# BLAS_INCLUDE := /path/to/your/blas
# BLAS_LIB := /path/to/your/blas

# Homebrew puts openblas in a directory that is not on the standard search path
# BLAS_INCLUDE := $(shell brew --prefix openblas)/include
# BLAS_LIB := $(shell brew --prefix openblas)/lib

# This is required only if you will compile the matlab interface.
# MATLAB directory should contain the mex binary in /bin.
# MATLAB_DIR := /usr/local
# MATLAB_DIR := /Applications/MATLAB_R2012b.app

# NOTE: this is required only if you will compile the python interface.
# We need to be able to find Python.h and numpy/arrayobject.h.
PYTHON_INCLUDE := /usr/include/python2.7 \
        /usr/lib/python2.7/dist-packages/numpy/core/include
# Anaconda Python distribution is quite popular. Include path:
# Verify anaconda location, sometimes it's in root.
# ANACONDA_HOME := $(HOME)/anaconda
# PYTHON_INCLUDE := $(ANACONDA_HOME)/include \
        # $(ANACONDA_HOME)/include/python2.7 \
        # $(ANACONDA_HOME)/lib/python2.7/site-packages/numpy/core/include \

# Uncomment to use Python 3 (default is Python 2)
# PYTHON_LIBRARIES := boost_python3 python3.5m
# PYTHON_INCLUDE := /usr/include/python3.5m \
#                 /usr/lib/python3.5/dist-packages/numpy/core/include

# We need to be able to find libpythonX.X.so or .dylib.
PYTHON_LIB := /usr/lib
# PYTHON_LIB := $(ANACONDA_HOME)/lib

# Homebrew installs numpy in a non standard path (keg only)
# PYTHON_INCLUDE += $(dir $(shell python -c 'import numpy.core; print(numpy.core.__file__)'))/include
# PYTHON_LIB += $(shell brew --prefix numpy)/lib

# Uncomment to support layers written in Python (will link against Python libs)
 WITH_PYTHON_LAYER := 1

# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial/ /usr/include/opencv/ /usr/include/opencv2/
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/x86_64-linux-gnu/hdf5/serial/  /usr/local/lib/lib/ /usr/lib/x86_64-linux-gnu/

# If Homebrew is installed at a non standard location (for example your home directory) and you use it for general dependencies
# INCLUDE_DIRS += $(shell brew --prefix)/include
# LIBRARY_DIRS += $(shell brew --prefix)/lib

# Uncomment to use `pkg-config` to specify OpenCV library paths.
# (Usually not necessary -- OpenCV libraries are normally installed in one of the above $LIBRARY_DIRS.)
# USE_PKG_CONFIG := 1

BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
# DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @

配置好了之后make all -j12 && make pycaffe

./experiments/scripts/faster_rcnn_alt_opt.sh [GPU_ID] [NET] [--set ...]
# GPU_ID is the GPU you want to train on
# NET in {ZF, VGG_CNN_M_1024, VGG16} is the network arch to use
# --set ... allows you to specify fast_rcnn.config options, e.g.
#   --set EXP_DIR seed_rng1701 RNG_SEED 1701
比如:nohup ./experiments/scripts/faster_rcnn_end2end.sh 0 VGG16 pascal_voc 2>&1 &

但是启动可能会遇到如下一些问题, 此处都是其他同事告诉我的(https://www.douban.com/note/630834963/?type=rec#sep):

这里是因为numpy版本不兼容导致的问题，最好的解决办法是卸载你的numpy，安装numpy1.11.0, 但是重新装numpy1.11.0又和tensorflow冲突
就修改代码兼容, 所以这里最好用docker做环境, 相互隔离:

  1. $FRCN_ROOT/lib/roi_data_layer/minibatch.py

将第26行：fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)
改为：fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image).astype(np.int)

  1. $FRCN_ROOT/lib/datasets/ds_utils.py

将第12行：hashes = np.round(boxes * scale).dot(v)
改为：hashes = np.round(boxes * scale).dot(v).astype(np.int)

  1. $FRCN_ROOT/lib/fast_rcnn/test.py

将第129行： hashes = np.round(blobs['rois'] * cfg.DEDUP_BOXES).dot(v)
改为： hashes = np.round(blobs['rois'] * cfg.DEDUP_BOXES).dot(v).astype(np.int)

  1. $FRCN_ROOT/lib/rpn/proposal_target_layer.py

将第60行：fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)
改为：fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image).astype(np.int)

TypeError: slice indices must be integers or None or have an index method
修改 /home/lzx/py-faster-rcnn/lib/rpn/proposal_target_layer.py，转到123行：

for ind in inds:
cls = clss[ind]
start = 4 * cls
end = start + 4
bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]
bbox_inside_weights[ind, start:end] = cfg.TRAIN.BBOX_INSIDE_WEIGHTS
return bbox_targets, bbox_inside_weights

这里的ind，start，end都是 numpy.int 类型，这种类型的数据不能作为索引，所以必须对其进行强制类型转换，转化结果如下：

for ind in inds:
ind = int(ind)
cls = clss[ind]
start = int(4 * cos)
end = int(start + 4)
bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]
bbox_inside_weights[ind, start:end] = cfg.TRAIN.BBOX_INSIDE_WEIGHTS
return bbox_targets, bbox_inside_weights

不排除build 还有其他问题, 需要分析Google解决
看到原生的数据集可以开始训练环境setup基本就可以了

2.标注数据

git clone https://github.com/tzutalin/labelImg.git
我是在mac上标注,按照教程setup 没有遇到问题
Python 3 + Qt5 (Works on macOS High Sierra)

brew install qt  # will install qt-5.x.x
brew install libxml2
make qt5py3
python labelImg.py
python  labelImg.py [IMAGE_PATH] [PRE-DEFINED CLASS FILE]

在data/predefined_classes.txt下提前写入好的分类的label,设置输出目录

然后框图选择对应label,会在输入目录生成对应图的xml文件标识分类

3.训练和识别

上一篇 下一篇

猜你喜欢

热点阅读