python pr曲线_Py-Faster R-CNN可视化——网络模型,图像特征,Loss图,PR曲线

可视化网络模型

使用Netscope在线可视化

Netscope

Netscope能可视化神经网络体系结构(或技术上说，Netscope能可视化任何有向无环图)。目前Netscope能可视化Caffe的prototxt 文件。网址为：ethereon.github.io/netscope/#/…Netscope的使用非常简单，只需要将prototxt的文件复制到Netscope的编辑框，再按快捷键Shift+Enter即可得到网络模型的可视化结构。Netscope的优点是显示的网络模型简洁，而且将鼠标放在右侧可视化的网络模型的任意模块上，会显示该模块的具体参数。图1以Faster R-CNN中ZF模型的train.prototxt文件为例

可视化图像特征

关于图像的可视化，我也使用过两种两种方式：

修改demo.py代码输出中间层结果

使用可视化工具deep-visualization-toolbox

修改demo.py

该部分是参考薛开宇的《caffe学习笔记》中的逐层特征可视化部分，还是以ZFNet网络训练Pascal VOC为例，修改demo.py文件后，代码如下：

#!/usr/bin/env python

#-*-coding:utf-8-*-

import matplotlib

matplotlib.use('Agg')

import _init_paths

from fast_rcnn.config import cfg

from fast_rcnn.test import im_detect

from fast_rcnn.nms_wrapper import nms

from utils.timer import Timer

import matplotlib.pyplot as plt

import numpy as np

import scipy.io as sio

import caffe, os, sys, cv2

import argparse

CLASSES = ('__background__',

'aeroplane', 'bicycle', 'bird', 'boat',

'bottle', 'bus', 'car', 'cat', 'chair',

'cow', 'diningtable', 'dog', 'horse',

'motorbike', 'person', 'pottedplant',

'sheep', 'sofa', 'train', 'tvmonitor')

NETS = {'vgg16': ('VGG16',

'VGG16_faster_rcnn_final.caffemodel'),

'zf': ('ZF',

'zf_faster_rcnn_iter_2000.caffemodel')}

def vis_detections(im, class_name, dets, thresh=0.5):

"""Draw detected bounding boxes."""

inds = np.where(dets[:, -1] >= thresh)[0]

if len(inds) == 0:

return

im = im[:, :, (2, 1, 0)]

fig, ax = plt.subplots(figsize=(12, 12))

ax.imshow(im, aspect='equal')

for i in inds:

bbox = dets[i, :4]

score = dets[i, -1]

ax.add_patch(

plt.Rectangle((bbox[0], bbox[1]),

bbox[2] - bbox[0],

bbox[3] - bbox[1], fill=False,

edgecolor='red', linewidth=3.5)

)

ax.text(bbox[0], bbox[1] - 2,

'{:s} {:.3f}'.format(class_name, score),

bbox=dict(facecolor='blue', alpha=0.5),

fontsize=14, color='white')

ax.set_title(('{} detections with '

'p({} | box) >= {:.1f}').format(class_name, class_name,

thresh),

fontsize=14)

plt.axis('off')

plt.tight_layout()

plt.draw()

def demo(net, image_name):

"""Detect object classes in an image using pre-computed object proposals."""

# Load the demo image

im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)

im = cv2.imread(im_file)

# Detect all object classes and regress object bounds

timer = Timer()

timer.tic()

scores, boxes = im_detect(net, im)

timer.toc()

print ('Detection took {:.3f}s for '

'{:d} object proposals').format(timer.total_time, boxes.shape[0])

# Visualize detections for each class

CONF_THRESH = 0.8

NMS_THRESH = 0.3

for cls_ind, cls in enumerate(CLASSES[1:]):

cls_ind += 1 # because we skipped background

cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]

cls_scores = scores[:, cls_ind]

dets = np.hstack((cls_boxes,

cls_scores[:, np.newaxis])).astype(np.float32)

keep = nms(dets, NMS_THRESH)

dets = dets[keep, :]

vis_detections(im, cls, dets, thresh=CONF_THRESH)

def parse_args():

"""Parse input arguments."""

parser = argparse.ArgumentParser(description='Faster R-CNN demo')

parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',

default=0, type=int)

parser.add_argument('--cpu', dest='cpu_mode',

help='Use CPU mode (overrides --gpu)',

action='store_true')

parser.add_argument('--net', dest='demo_net', help='Network to use [zf]',

choices=NETS.keys(), default='zf')

args = parser.parse_args()

return args

if __name__ == '__main__':

cfg.TEST.HAS_RPN = True  # Use RPN for proposals

args = parse_args()

prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],

'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')

caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',

NETS[args.demo_net][1])

if not os.path.isfile(caffemodel):

raise IOError(('{:s} not found.\nDid you run ./data/script/'

'fetch_faster_rcnn_models.sh?').format(caffemodel))

if args.cpu_mode:

caffe.set_mode_cpu()

else:

caffe.set_mode_gpu()

caffe.set_device(args.gpu_id)

cfg.GPU_ID = args.gpu_id

net = caffe.Net(prototxt, caffemodel, caffe.TEST)

#指定caffe路径，以下是我的caffe路径

caffe_root='/home/ouyang/GitRepository/py-faster-rcnn/caffe-fast-rcnn/'

# import sys

sys.path.insert(0, caffe_root+'python')

# import caffe

# #显示的图表大小为 10,图形的插值是以最近为原则,图像颜色是灰色

plt.rcParams['figure.figsize'] = (10, 10)

plt.rcParams['image.interpolation'] = 'nearest'

plt.rcParams['image.cmap'] = 'gray'

image_file = caffe_root+'examples/images/vehicle_0000015.jpg'

# 载入模型

npload = caffe_root+ 'python/caffe/imagenet/ilsvrc_2012_mean.npy'

transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})

transformer.set_transpose('data', (2,0,1))

transformer.set_mean('data', np.load(npload).mean(1).mean(1))

# 参考模型的灰度为0~255，而不是0~1

transformer.set_raw_scale('data', 255)

# 由于参考模型色彩是BGR,需要将其转换为RGB

transformer.set_channel_swap('data', (2,1,0))

im=caffe.io.load_image(image_file)

net.blobs['data'].reshape(1,3,224,224)

net.blobs['data'].data[...] = transformer.preprocess('data',im)

# 显示出各层的参数和形状，第一个是批次，第二个是feature map数目，第三和第四是每个神经元中图片的长和宽

print [(k,v.data.shape) for k,v in net.blobs.items()]

#输出网络参数

print [(k,v[0].data.shape) for k,v in net.params.items()]

def show_image(im):

if im.ndim==3:

m=im[:,:,::-1]

plt.imshow(im)

#显示图片的方法

plt.axis('off') # 不显示坐标轴

plt.show()

# 每个可视化的都是在一个由一个个网格组成

def vis_square(data,padsize=1,padval=0):

data-=data.min()

data/=data.max()

# force the number of filters to be square

n=int(np.ceil(np.sqrt(data.shape[0])))

padding=((0,n**2-data.shape[0]),(0,padsize),(0,padsize))+((0,0),)*(data.ndim-3)

data=np.pad(data,padding,mode='constant',constant_values=(padval,padval))

# 对图像使用滤波器

data=data.reshape((n,n)+data.shape[1:]).transpose((0,2,1,3)+tuple(range( 4,data.ndim+1)))

data=data.reshape((n*data.shape[1],n*data.shape[3])+data.shape[4:])

#show_image(data)

plt.imshow(data)

plt.show()

# 设置图片的保存路径，此处是我的路径

plt.savefig("./tools/Vehicle_2000/fc6.jpg")

out = net.forward()

image=net.blobs['data'].data[4].copy()

image-=image.min()

image/=image.max()

# 显示原始图像

show_image(image.transpose(1,2,0))

#网络提取conv1的卷积核

filters = net.params['conv1'][0].data

vis_square(filters.transpose(0, 2, 3, 1))

#过滤后的输出,96 张 featuremap

feat =net.blobs['conv1'].data[0,:96]

vis_square(feat,padval=1)

#第二个卷积层,显示全部的96个滤波器,每一个滤波器为一行。

filters = net.params['conv2'][0].data

vis_square(filters[:96].reshape(96**2, 5, 5))

# #第二层输出 256 张 featuremap

feat = net.blobs['conv2'].data[0]

vis_square(feat, padval=1)

filters = net.params['conv3'][0].data

vis_square(filters[:256].reshape(256**2, 3, 3))

# 第三个卷积层:全部 384 个 feature map

feat = net.blobs['conv3'].data[0]

vis_square(feat, padval=0.5)

#第四个卷积层,我们只显示前面 48 个滤波器,每一个滤波器为一行。

filters = net.params['conv4'][0].data

vis_square(filters[:384].reshape(384**2, 3, 3))

# 第四个卷积层:全部 384 个 feature map

feat = net.blobs['conv4'].data[0]

vis_square(feat, padval=0.5)

# 第五个卷积层:全部 256 个 feature map

filters = net.params['conv5'][0].data

vis_square(filters[:384].reshape(384**2, 3, 3))

feat = net.blobs['conv5'].data[0]

vis_square(feat, padval=0.5)

#第五个 pooling 层

feat = net.blobs['fc6'].data[0]

vis_square(feat, padval=1)

第六层输出后的直方分布

feat=net.blobs['fc6'].data[0]

plt.subplot(2,1,1)

plt.plot(feat.flat)

plt.subplot(2,1,2)

_=plt.hist(feat.flat[feat.flat>0],bins=100)

# #显示图片的方法

#plt.axis('off') # 不显示坐标轴

plt.show()

plt.savefig("fc6_zhifangtu.jpg")

# 第七层输出后的直方分布

feat=net.blobs['fc7'].data[0]

plt.subplot(2,1,1)

plt.plot(feat.flat)

plt.subplot(2,1,2)

_=plt.hist(feat.flat[feat.flat>0],bins=100)

plt.show()

plt.savefig("fc7_zhifangtu.jpg")

#看标签

#执行测试

image_labels_filename=caffe_root+'data/ilsvrc12/synset_words.txt'

#try:

labels=np.loadtxt(image_labels_filename,str,delimiter='\t')

top_k=net.blobs['prob'].data[0].flatten().argsort()[-1:-6:-1]

#print labels[top_k]

for i in np.arange(top_k.size):

print top_k[i], labels[top_k[i]]

下面贴几张检测结果

图3 原始检测图片

图4 conv1参数可视化

图5 conv1特征可视化

deep-visualization-toolbox

deep-visualization-toolbox是Jason Yosinsk出版在Computer Science上的一篇论文的源代码，改论文主要讲述的是卷积神经网络的可视化，感兴趣的朋友可以看看这篇论文(论文地址)。B站上有个讲怎么使用该工具的视频，这里附上链接www.bilibili.com/video/av740…。 该工具的源码在github：github.com/yosinski/de…。该github下有完整的安装配置步骤，还是以图2中的马为例，贴几张检测结果图。

图6 ToolBox conv1特征可视化

图7 ToolBox conv2特征可视化

从检测效果上看，还是挺简洁的。图片左侧的一列图片左上角是输入图片，中间部分是图片经过网络前向传播得到的特征图可视化，左下角是其特征可视化。

Loss可视化

网络训练过程中Loss值的可视化可以帮助分析该网络模型的参数是否合适。在使用Faster R-CNN网络训练模型时，训练完成后的日志文件中保存了网络训练各个阶段的loss值，如图8所示。只用写简单的python程序，读取日志文件中的迭代次数，以及需要的损失值，再画图即可完成Loss的可视化。

图8 模型的训练日志

在下面贴出Loss可视化的代码：

#!/usr/bin/env python

import os

import sys

import numpy as np

import matplotlib.pyplot as plt

import math

import re

import pylab

from pylab import figure, show, legend

from mpl_toolkits.axes_grid1 import host_subplot

# 日志文件名

fp = open('faster_rcnn_end2end_ZF_.txt.2018-04-13_19-46-23', 'r',encoding='UTF-8')

train_iterations = []

train_loss = []

test_iterations = []

#test_accuracy = []

for ln in fp:

# get train_iterations and train_loss

if '] Iteration ' in ln and 'loss = ' in ln:

arr = re.findall(r'ion \b\d+\b,',ln)

train_iterations.append(int(arr[0].strip(',')[4:]))

train_loss.append(float(ln.strip().split(' = ')[-1]))

fp.close()

host = host_subplot(111)

plt.subplots_adjust(right=0.8) # ajust the right boundary of the plot window

#par1 = host.twinx()

# set labels

host.set_xlabel("iterations")

host.set_ylabel("RPN loss")

#par1.set_ylabel("validation accuracy")

# plot curves

p1, = host.plot(train_iterations, train_loss, label="train RPN loss")

.

host.legend(loc=1)

# set label color

host.axis["left"].label.set_color(p1.get_color())

host.set_xlim([-1000, 60000])

host.set_ylim([0., 3.5])

plt.draw()

plt.show()

可视化效果如下图所示

图9 Loss可视化

画PR图

在pascal_voc.py里添加几行代码即可：

1，文件头部：

importmatplotlib.pyplot as plt

importpylab as pl

from sklearn.metricsimportprecision_recall_curve

from itertoolsimportcycle

2，_do_python_eval函数：

def _do_python_eval(self, output_dir='output'):

annopath = os.path.join(

self._devkit_path,

'VOC'+self._year,

'Annotations',

'{:s}.xml')

imagesetfile = os.path.join(

self._devkit_path,

'VOC'+self._year,

'ImageSets',

'Main',

self._image_set +'.txt')

cachedir = os.path.join(self._devkit_path,'annotations_cache')

aps = []

# The PASCAL VOC metric changed in 2010

use_07_metric =Trueifint(self._year) <2010elseFalse

print('VOC07 metric? '+ ('Yes'ifuse_07_metricelse'No'))

ifnot os.path.isdir(output_dir):

os.mkdir(output_dir)

fori, cls in enumerate(self._classes):

ifcls =='__background__':

continue

filename =self._get_voc_results_file_template().format(cls)

rec, prec, ap = voc_eval(

filename, annopath, imagesetfile, cls, cachedir, ovthresh=0.5,

use_07_metric=use_07_metric)

aps += [ap]

pl.plot(rec, prec, lw=2,

label='Precision-recall curve of class {} (area = {:.4f})'

''.format(cls, ap))

print(('AP for {} = {:.4f}'.format(cls, ap)))

with open(os.path.join(output_dir, cls +'_pr.pkl'),'wb')asf:

pickle.dump({'rec': rec,'prec': prec,'ap': ap}, f)

pl.xlabel('Recall')

pl.ylabel('Precision')

plt.grid(True)

pl.ylim([0.0,1.05])

pl.xlim([0.0,1.0])

pl.title('Precision-Recall')

pl.legend(loc="upper right")

plt.show()

print(('Mean AP = {:.4f}'.format(np.mean(aps))))

print('~~~~~~~~')

print('Results:')

forap in aps:

print(('{:.3f}'.format(ap)))

print(('{:.3f}'.format(np.mean(aps))))

print('~~~~~~~~')

print('')

print('--------------------------------------------------------------')

print('Results computed with the **unofficial** Python eval code.')

print('Results should be very close to the official MATLAB eval code.')

print('Recompute with `./tools/reval.py --matlab ...` for your paper.')

print('-- Thanks, The Management')

print('--------------------------------------------------------------')

然后运行test_net.py，就可以得到如下图的PR曲线。如果想比较多条曲线，可以先把rec, prec数据存起来再画图。