py-faster-rcnn中demo.py代码与C++版本的代码对比: part01 铺垫, demo.py引入的模块

这里”C++版本的代码”是指: https://github.com/galian123/cpp_faster_rcnn_detect .

py-faster-rcnn中demo.py代码, 是指 https://github.com/rbgirshick/py-faster-rcnn/blob/master/tools/demo.py 以及
https://github.com/rbgirshick/py-faster-rcnn/tree/master/lib 目录下的一些代码.

涉及到的.py文件都是 https://github.com/rbgirshick/py-faster-rcnn/ 中的.

★ python代码

tools/demo.py 中import的内容, 是整个代码流程的铺垫, 理解了import的内容, 对理解后续的python代码和C++ 代码都有帮助.

demo.py的import内容:

import _init_paths
from fast_rcnn.config import cfg 
from fast_rcnn.test import im_detect
from fast_rcnn.nms_wrapper import nms 
import numpy as np
import caffe, os, sys, cv2

♦ `_init_paths`

import _init_paths的_init_paths是指tools/_init_paths.py
其内容如下:

import os.path as osp
import sys

def add_path(path):
    if path not in sys.path:
        sys.path.insert(0, path)

# 当前目录是 py-faster-rcnn/tools
this_dir = osp.dirname(__file__)

# Add caffe to PYTHONPATH
caffe_path = osp.join(this_dir, '..', 'caffe-fast-rcnn', 'python')
add_path(caffe_path)

# Add lib to PYTHONPATH
lib_path = osp.join(this_dir, '..', 'lib')
add_path(lib_path)

可以看到, 将py-faster-rcnn/caffe-fast-rcnn/python目录和py-faster-rcnn/lib目录添加到了python库的搜索路径列表PYTHONPATH. 这样在后续的import时就可以找到了具体的包和模块了.

♦ `from fast_rcnn.config import cfg`

./lib/fast_rcnn/config.py
demo.py运行过程中的配置基本上都在这里了. 后续的代码流程中会用到这些配置值.
需要注意的是, TEST.HAS_RPN在demo.py中设置成了True.

config.py中的内容(部分):

__C.TEST = edict()

# Scales to use during testing (can list multiple scales)
# Each scale is the pixel size of an image's shortest side
__C.TEST.SCALES = (600,)

# Max pixel size of the longest side of a scaled input image
__C.TEST.MAX_SIZE = 1000

# Overlap threshold used for non-maximum suppression (suppress boxes with
# IoU >= this threshold)
__C.TEST.NMS = 0.3

# Experimental: treat the (K+1) units in the cls_score layer as linear
# predictors (trained, eg, with one-vs-rest SVMs).
__C.TEST.SVM = False

# Test using bounding-box regressors
__C.TEST.BBOX_REG = True

# Propose boxes
__C.TEST.HAS_RPN = False

# Use GPU implementation of non-maximum suppression
__C.USE_GPU_NMS = True

# Default GPU device id
__C.GPU_ID = 0

♦ `from fast_rcnn.test import im_detect`

./lib/fast_rcnn/test.py
主要的处理基本上都在这里了.

♦ `from fast_rcnn.nms_wrapper import nms`

./lib/fast_rcnn/nms_wrapper.py

from fast_rcnn.config import cfg
# 这里的nms.gpu_nms是 lib/nms/gpu_nms.so
from nms.gpu_nms import gpu_nms
from nms.cpu_nms import cpu_nms

def nms(dets, thresh, force_cpu=False):
    """Dispatch to either CPU or GPU NMS implementations."""

    if dets.shape[0] == 0:
        return []
    if cfg.USE_GPU_NMS and not force_cpu:
        # run here, 调用的是gpu_nms.so中的函数
        return gpu_nms(dets, thresh, device_id=cfg.GPU_ID)
    else:
        return cpu_nms(dets, thresh)

♦ `import numpy as np`

numpy用来处理图片数据(多维数组), 尤其是numpy的broadcasting特性, 使得不同维度的数组可以一起操作(加,减,乘, 除, 等).

♦ `import caffe, os, sys, cv2`

如果你的py-faster-rcnn是可以用的, 即执行demo.py是没有问题的, 那么,可以通过执行python, 并import caffe得知caffe是指py-faster-rcnn/caffe-fast-rcnn/python/caffe.

$ python
Python 2.7.12 (default, Nov 20 2017, 18:23:56) 
[GCC 5.4.0 20160609] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import caffe
>>> help(caffe)

可以看到caffe的帮助信息:

Help on package caffe:  # caffe是一个包

NAME
    caffe

FILE                    # caffe所在的路径: py-faster-rcnn/caffe-fast-rcnn/python/caffe
    /home/<your_name>/path/to/py-faster-rcnn/caffe-fast-rcnn/python/caffe/__init__.py

PACKAGE CONTENTS        # caffe包里的模块, 其中_caffe是c++实现的, pycaffe也是重点关注的
    _caffe
    classifier
    coord_map
    detector
    draw
    io
    net_spec
    proto (package)
    pycaffe

FUNCTIONS               #caffe包里导出来的函数, 可以供其他python模块调用
    get_solver(...)
        get_solver( (str)arg1) -> Solver :
略

如果import caffe出现问题, 可以添加/path/to/py-faster-rcnn/caffe-fast-rcnn/python到PYTHONPATH中:
将下面这句添加到~/.bashrc中, 然后执行. ~/.bashrc:
export PYTHONPATH=~/path/to/py-faster-rcnn/caffe-fast-rcnn/python:$PYTHONPATH

♦ `caffe`包中的`init.py`

py-faster-rcnn/caffe-fast-rcnn/python/caffe/init.py

from .pycaffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, RMSPropSolver, AdaDeltaSolver, AdamSolver, NCCL, Timer
from ._caffe import init_log, log, set_mode_cpu, set_mode_gpu, set_device, Layer, get_solver, layer_type_list, set_random_seed, solver_count, set_solver_count, solver_rank, set_solver_rank, set_multiprocess, has_nccl
from ._caffe import __version__
from .proto.caffe_pb2 import TRAIN, TEST
from .classifier import Classifier
from .detector import Detector
from . import io
from .net_spec import layers, params, NetSpec, to_proto

从上面可以知道, caffe包依赖了很多模块, 从其他模块中引入了很多函数和类. 这些函数和类可以通过caffe.xxx的形式来使用.

其中from ._caffe import init_log, log, set_mode_cpu, set_mode_gpu, set_device
就是从_caffe.so文件中, 引入set_mode_cpu, set_mode_gpu, set_device 等函数, 最终这些函数将调用C++版本的同名函数.

_caffe.so 是执行make pycaffe时生成的.
执行时所在目录: py-faster-rcnn/caffe-fast-rcnn/

make pycaffe
CXX/LD -o python/caffe/_caffe.so python/caffe/_caffe.cpp
touch python/caffe/proto/__init__.py
PROTOC (python) src/caffe/proto/caffe.proto

python调用C++的方式, 可以参考_caffe.cpp中的boost::python相关的代码处理.

接下来分析demo.py的初始化.

————– 分割线 ————–
本系列文章如下: