caffe--detection--python--select-search

#encoding: utf-8
"""
对于il2012来说，
分类问题一共有1000各类别
检测问题有200个类别
"""




""" 0 产生数据框架包  ； """


"""
这里执行了python脚本：
利用   权重文件，部署文件，标签文件,待检测的目标图像  ， 作为输入，产生了一个以检测为目的的数据框架包。
"""


"""
1、 Rcnn简介 
原文连接：http://people.eecs.berkeley.edu/~rbg/papers/r-cnn-cvpr.pdf 
首先使用selective search算法，从图片中提取出2000个可能包含有目标的区域，
再将这2000个候选区（ROI：region of interest）压缩到统一大小（227*227）送入卷积神经网络中进行特征提取，
在最后一层将特征向量输入svm分类器，得到该候选区域的种类。整体上看R-cnn比较简单，与此同时也有两个 重大缺陷： 
（1）selective search进行候选区域提取的过程在cpu内计算完成，占用了大量计算时间。 
（2）对2000个候选框进行卷积计算，提取特征的时候，存在大量的重复计算，进一步增加了计算复杂度。
针对以上两个缺点，R Girshick分别在fast-Rcnn和faster-rcnn中进行了改进。
"""


# !mkdir -p _temp
# !echo `pwd`/images/fish-bike.jpg > _temp/det_input.txt
# !../python/detect.py --crop_mode=selective_search\
#  --pretrained_model=../models/bvlc_reference_rcnn_ilsvrc13/bvlc_reference_rcnn_ilsvrc13.caffemodel\
#  --model_def=../models/bvlc_reference_rcnn_ilsvrc13/deploy.prototxt\
#  --gpu --raw_scale=255 _temp/det_input_person.txt _temp/det_output_person.h5


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# %matplotlib inline


nameImg = "/home/sea/caffeM/caffe/examples/images/fish-bike.jpg" 
# nameImg ="/home/sea/Downloads/1.jpeg"
# nameImg ="/home/sea/Downloads/2.jpeg"
# nameImg ="/home/sea/Downloads/3.jpeg"
nameImg ="/home/sea/Downloads/4.jpeg"
nameImg ="/home/sea/Downloads/person.jpeg"


"""1  准备模型"""
print  """1  准备模型"""
df = pd.read_hdf('/home/sea/caffeM/caffe/examples/_temp/det_output_person.h5', 'df')
print "(df.shape) = ",  (df.shape)   # (df.shape) =  (1565, 5)
print "type(df.iloc[0]) = ",  type(df.iloc[0])    # type(df.iloc[0]) =  <class 'pandas.core.series.Series'>
print "df.iloc[0].shape  = ",  df.iloc[0].shape  #df.iloc[0].shape  =  (5,)
print "(df.iloc[0]) = ",  (df.iloc[0])    # 


print 'aaaaa'
with open( '/home/sea/caffeM/caffe/data/ilsvrc12/det_synset_words.txt' ) as f:
    labels_df = pd.DataFrame([
        {
            'synset_id': l.strip().split(' ')[0],
            'name': ' '.join(l.strip().split(' ')[1:]).split(',')[0]
        }
        for l in f.readlines()
    ])
print 'aaaaa'
print  "type(labels_df) = ", type(labels_df)    # type(labels_df) =  <class 'pandas.core.frame.DataFrame'>
print  "labels_df.shape = ", labels_df.shape    # labels_df.shape =  (200, 2)
# print  "labels_df = ", labels_df
# print  "labels_df sort_index= ", labels_df.sort_index(  )
# labels_df.sort_values(by, axis, ascending, inplace, kind, na_position)
# labels_df.sort('synset_id')
predictions_df = pd.DataFrame(np.vstack(df.prediction.values), columns=labels_df['name'])
""" 这个是所有的大类"""
# print  "(predictions_df.iloc[0]) = ",  (predictions_df.iloc[0])




aa = predictions_df.iloc[0]
print  "type( aa  ) = ",  type( aa  )     # 
if 0:
    dt = aa.to_dict()
    dt = sorted(  dt.items(), lambda x, y: cmp( abs(x[1] ), abs( y[1] ) ), reverse=False )
    print 'dt = ', dt #




plt.gray()
plt.matshow(predictions_df.values)
plt.xlabel('Classes')
plt.ylabel('Windows')
# plt.show(3)


print "type( predictions_df ) = ",  type( predictions_df )    # 
print  "这个是总表来着 : "  
pprr = predictions_df.sort_index(    )
print "pprr.shape = ",  pprr.shape    ##   1565*  200  这个是其规格  
# print " predictions_df.sort_index(    ) = ",  pprr


max_s = predictions_df.max(0)
print "type( max_s ) = ", type( max_s )
# print  "max_s = ",  max_s
# max_s.sort(ascending=False)
# print(max_s[:10])




# Find, print, and display the top detections: person and bicycle.
i = predictions_df['person'].idxmax()
j = predictions_df['bicycle'].idxmax()


# Show top predictions for top detection.
print "f : "
f = pd.Series(df['prediction'].iloc[i], index=labels_df['name'])
"""f是200个 类别"""
f.sort_values(  )
print  "f.shape = ",  f.shape
# print 'f.sort_values(  ) = ', f.sort_values(  )
print('Top detection:')
print  f.sort_values(ascending=False)[:5]




# Show top predictions for second-best detection.
f = pd.Series(df['prediction'].iloc[j], index=labels_df['name'])
print ('Second-best detection:')
print f.sort_values(ascending=False)[:5]


 
"""2  读图开始"""
print  """2  读图开始"""
# Show top detection in red, second-best top detection in blue.
im = plt.imread(   nameImg  )
plt.imshow(im)
# plt.show(3)
currentAxis = plt.gca()


det = df.iloc[i]
coords = (det['xmin'], det['ymin']), det['xmax'] - det['xmin'], det['ymax'] - det['ymin']
currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor='r', linewidth=5))


det = df.iloc[j]
coords = (det['xmin'], det['ymin']), det['xmax'] - det['xmin'], det['ymax'] - det['ymin']
currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor='b', linewidth=5))


# exit()


def nms_detections(dets, overlap=0.3):
    """
    Non-maximum suppression: Greedily select high-scoring detections and
    skip detections that are significantly covered by a previously
    selected detection.


    This version is translated from Matlab code by Tomasz Malisiewicz,
    who sped up Pedro Felzenszwalb's code.


    Parameters
    ----------
    dets: ndarray
        each row is ['xmin', 'ymin', 'xmax', 'ymax', 'score']
    overlap: float
        minimum overlap ratio (0.3 default)


    Output
    ------
    dets: ndarray
        remaining after suppression.
    """
    x1 = dets[:, 0]
    y1 = dets[:, 1]
    x2 = dets[:, 2]
    y2 = dets[:, 3]
    ind = np.argsort(dets[:, 4])


    w = x2 - x1
    h = y2 - y1
    area = (w * h).astype(float)


    pick = []
    while len(ind) > 0:
        i = ind[-1]
        pick.append(i)
        ind = ind[:-1]


        xx1 = np.maximum(x1[i], x1[ind])
        yy1 = np.maximum(y1[i], y1[ind])
        xx2 = np.minimum(x2[i], x2[ind])
        yy2 = np.minimum(y2[i], y2[ind])


        w = np.maximum(0., xx2 - xx1)
        h = np.maximum(0., yy2 - yy1)


        wh = w * h
        o = wh / (area[i] + area[ind] - wh)


        ind = ind[np.nonzero(o <= overlap)[0]]


    return dets[pick, :]






"""3  检测"""
print  """3  检测"""
scores = predictions_df['bicycle']     ##  这个有1565 各数据的长度
print "scores : "
# print "scores = predictions_df['bicycle'] :  ",  scores
windows = df[['xmin', 'ymin', 'xmax', 'ymax']].values
dets = np.hstack((windows, scores[:, np.newaxis]))
nms_dets = nms_detections(dets)


"""4  显示"""
print  """4  显示"""
plt.imshow(im)
plt.show(3)
currentAxis = plt.gca()
colors = ['r', 'b', 'y']
for c, det in zip(colors, nms_dets[:3]):
    currentAxis.add_patch(
        plt.Rectangle((det[0], det[1]), det[2]-det[0], det[3]-det[1],
        fill=False, edgecolor=c, linewidth=5)
    )
print 'scores:', nms_dets[:3, 4]


# !rm -rf _temp