Faster-rcnn 计算mAP程序精简版

由于Faster-rcnn里的计算mAP程序里面有很多嵌套，移植到自己的卷积网络框架下很麻烦，所以把这些嵌套都整合起来方便使用，整合之后的程序只包括test_net.py和voc_eval.py
下面是test_net.py

import _init_paths
from config import cfg
import caffe
import time, os, sys
from caffeWrapper.timer import Timer
import cv2
import numpy as np
from datasets.bbox_transform import clip_boxes, bbox_transform_inv ##这两个函数需要自己import进来
from nms.nms_wrapper import nms
import cPickle
import uuid
#import get_voc_results_file_template, im_detect
from voc_eval import voc_eval
import datetime


def get_voc_results_file_template(cls):##这个函数也改了一下
    #comp_id = ('comp4' + '_' + str(uuid.uuid4()))
    date = datetime.datetime.now().strftime('%Y-%m-%d-%H-%M-%S')##这里把原来的编码名称改为日期（年-月-日-时-分-秒），方便查看
    filename = date + '_det_' + 'test' + cls + '.txt'
    path = os.path.join(save_prob_path, filename)
    return path

def im_detect(net, im):
    """Detect object classes in an image given object proposals.

    Arguments:
        net (caffe.Net): Fast R-CNN network to use
        im (ndarray): color image to test (in BGR order)

    Returns:
        scores (ndarray): R x K array of object class scores (K includes
            background as object category 0)
        boxes (ndarray): R x (4*K) array of predicted bounding boxes
    """
    blobs = {'data' : None, 'rois' : None}

    im_orig = im.astype(np.float32, copy=True)
    im_orig -= cfg.PIXEL_MEANS

    im_shape = im_orig.shape
    im_size_min = np.min(im_shape[0:2])
    im_size_max = np.max(im_shape[0:2])

    processed_ims = []
    im_scale_factors = []
##这里图片都是一样大小
#    for target_size in cfg.TEST.SCALES:
#        im_scale = float(target_size) / float(im_size_min)
#        # Prevent the biggest axis from being more than MAX_SIZE
#        if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:
#            im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)
#        im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,
#                        interpolation=cv2.INTER_LINEAR)
#        im_scale_factors.append(im_scale)
#        processed_ims.append(im)


    im_scale = 1.0
    im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,
                    interpolation=cv2.INTER_LINEAR)
    im_scale_factors.append(im_scale)
    processed_ims.append(im)        

    max_shape = np.array([imn.shape for imn in processed_ims]).max(axis=0)
    num_images = len(processed_ims)
    blob = np.zeros((num_images, max_shape[0], max_shape[1], 3),
                    dtype=np.float32)
    for i in xrange(num_images):
        imn = processed_ims[i]
        blob[i, 0:imn.shape[0], 0:imn.shape[1], :] = imn
    # Move channels (axis 3) to axis 1
    # Axis order will become: (batch elem, channel, height, width)
    channel_swap = (0, 3, 1, 2)
    blob = blob.transpose(channel_swap)

    blobs['data'] = blob
    im_scales =  np.array(im_scale_factors)

    im_blob = blobs['data']
    blobs['im_info'] = np.array([[im_blob.shape[2], im_blob.shape[3], im_scales[0]]],dtype=np.float32)

    # reshape network inputs
    net.blobs['data'].reshape(*(blobs['data'].shape))
    net.blobs['im_info'].reshape(*(blobs['im_info'].shape))

    # do forward
    forward_kwargs = {'data': blobs['data'].astype(np.float32, copy=False)}
    forward_kwargs['im_info'] = blobs['im_info'].astype(np.float32, copy=False)

    blobs_out = net.forward(**forward_kwargs)

    assert len(im_scales) == 1, "Only single-image batch implemented"
    rois = net.blobs['rois'].data.copy()
    # unscale back to raw image space
    boxes = rois[:, 1:5] / im_scales[0]

    scores = blobs_out['cls_prob']

    box_deltas = blobs_out['bbox_pred']
    pred_boxes = bbox_transform_inv(boxes, box_deltas)
    pred_boxes = clip_boxes(pred_boxes, im.shape)

    return scores, pred_boxes



file_path = 'VOC2007'
test_file = '/dataset/test.txt'
file_path_img = 'VOC2007/JPEGImages'
save_prob_path = 'VOC2007/output' ##生成的结果文件都保存在output里，包括detections.pkl，class_pr.pkl，和txt文件

test_prototxt = 'test.prototxt'
weight = 'vgg16.caffemodel'


thresh = 0.05
max_per_image = 100
num_classes = 2

Classes = ('__background__', 'ship')##这是二分类

with open(test_file) as f:
    image_index = [x.strip() for x in f.readlines()]

caffe.set_mode_gpu()
caffe.set_device(0)

net = caffe.Net(test_prototxt, weight, caffe.TEST)
net.name = os.path.splitext(os.path.basename(weight))[0]

num_images = len(image_index)
# all detections are collected into:
#    all_boxes[cls][image] = N x 5 array of detections in
#    (x1, y1, x2, y2, score)
all_boxes = [[[] for _ in xrange(num_images)]
             for _ in xrange(num_classes)]

# timers
_t = {'im_detect' : Timer(), 'misc' : Timer()}

for i in xrange(num_images):
    image_path = os.path.join(file_path_img, image_index[i] + '.jpg')
    im = cv2.imread(image_path)

    _t['im_detect'].tic()
    scores, boxes = im_detect(net, im)
    _t['im_detect'].toc()

    _t['misc'].tic()
    # skip j = 0, because it's the background class
    for j in xrange(1, num_classes):
        inds = np.where(scores[:, j] > thresh)[0]
        cls_scores = scores[inds, j]
        cls_boxes = boxes[inds, j*4:(j+1)*4]
        cls_dets = np.hstack((cls_boxes, cls_scores[:, np.newaxis])) \
            .astype(np.float32, copy=False)
        keep = nms(cls_dets, cfg.TEST.NMS)
        cls_dets = cls_dets[keep, :]
        all_boxes[j][i] = cls_dets

    # Limit to max_per_image detections *over all classes*
    if max_per_image > 0:
        image_scores = np.hstack([all_boxes[j][i][:, -1]
                                  for j in xrange(1, num_classes)])
        if len(image_scores) > max_per_image:
            image_thresh = np.sort(image_scores)[-max_per_image]
            for j in xrange(1, num_classes):
                keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
                all_boxes[j][i] = all_boxes[j][i][keep, :]
    _t['misc'].toc()

    print 'im_detect: {:d}/{:d} {:.3f}s {:.3f}s' \
          .format(i + 1, num_images, _t['im_detect'].average_time,
                  _t['misc'].average_time)
if not os.path.exists(save_prob_path):
    os.mkdir(save_prob_path)
det_file = os.path.join(save_prob_path, 'detections.pkl')
with open(det_file, 'wb') as f:
    cPickle.dump(all_boxes, f, cPickle.HIGHEST_PROTOCOL)

for cls_ind, cls in enumerate(Classes):
    if cls == '__background__':
        continue
    print 'Writing {} VOC results file'.format(cls)
    filename = get_voc_results_file_template(cls)
    if not os.path.exists(filename):
        os.mknod(filename) 

    with open(filename, 'wt') as f:
        for im_ind, index in enumerate(image_index):
            dets = all_boxes[cls_ind][im_ind]
            if dets == []:
                continue
            # the VOCdevkit expects 1-based indices
            for k in xrange(dets.shape[0]):
                f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'.
                        format(index, dets[k, -1],
                               dets[k, 0] + 1, dets[k, 1] + 1,
                               dets[k, 2] + 1, dets[k, 3] + 1))

annopath = os.path.join(file_path, 'Annotations', '{:s}.xml')
imagesetfile = os.path.join(file_path, 'ImageSets', 'Main', 'test.txt')
cachedir = os.path.join(save_prob_path)
aps = []

# The PASCAL VOC metric changed in 2010
use_07_metric = True #True
print 'VOC07 metric? ' + ('Yes' if use_07_metric else 'No')

for i, cls in enumerate(Classes):
    if cls == '__background__':
        continue
    #filename = get_voc_results_file_template(cls)
    rec, prec, ap = voc_eval(
        filename, annopath, imagesetfile, cls, cachedir, ovthresh = 0.5,
        use_07_metric = use_07_metric)
    aps += [ap]
    print('AP for {} = {:.4f}'.format(cls, ap))
    with open(os.path.join(save_prob_path, cls + '_pr.pkl'), 'w') as f:
        cPickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)
print('Mean AP = {:.4f}'.format(np.mean(aps)))
print('~~~~~~~~')
print('Results:')
for ap 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('--------------------------------------------------------------')

接下来是voc_eval.py

# --------------------------------------------------------
# Fast/er R-CNN
# Licensed under The MIT License [see LICENSE for details]
# Written by Bharath Hariharan
# --------------------------------------------------------

import xml.etree.ElementTree as ET
import os
import cPickle
import numpy as np

def parse_rec(filename):
    """ Parse a PASCAL VOC xml file """
    tree = ET.parse(filename)
    objects = []
    for obj in tree.findall('object'):
        obj_struct = {}
        obj_struct['name'] = obj.find('name').text
        #obj_struct['pose'] = obj.find('pose').text
        #obj_struct['truncated'] = int(obj.find('truncated').text)
        obj_struct['difficult'] = int(obj.find('difficult').text)
        bbox = obj.find('bndbox')
        obj_struct['bbox'] = [int(bbox.find('xmin').text),
                              int(bbox.find('ymin').text),
                              int(bbox.find('xmax').text),
                              int(bbox.find('ymax').text)]
        objects.append(obj_struct)

    return objects

def voc_ap(rec, prec, use_07_metric=False):
    """ ap = voc_ap(rec, prec, [use_07_metric])
    Compute VOC AP given precision and recall.
    If use_07_metric is true, uses the
    VOC 07 11 point method (default:False).
    """
    if use_07_metric:
        # 11 point metric
        ap = 0.
        for t in np.arange(0., 1.1, 0.1):
            if np.sum(rec >= t) == 0:
                p = 0
            else:
                p = np.max(prec[rec >= t])
            ap = ap + p / 11.
    else:
        # correct AP calculation
        # first append sentinel values at the end
        mrec = np.concatenate(([0.], rec, [1.]))
        mpre = np.concatenate(([0.], prec, [0.]))

        # compute the precision envelope
        for i in range(mpre.size - 1, 0, -1):
            mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])

        # to calculate area under PR curve, look for points
        # where X axis (recall) changes value
        i = np.where(mrec[1:] != mrec[:-1])[0]

        # and sum (\Delta recall) * prec
        ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
    return ap

def voc_eval(detpath,
             annopath,
             imagesetfile,
             classname,
             cachedir,
             ovthresh=0.5,
             use_07_metric=False):
    """rec, prec, ap = voc_eval(detpath,
                                annopath,
                                imagesetfile,
                                classname,
                                [ovthresh],
                                [use_07_metric])

    Top level function that does the PASCAL VOC evaluation.

    detpath: Path to detections
        detpath.format(classname) should produce the detection results file.
    annopath: Path to annotations
        annopath.format(imagename) should be the xml annotations file.
    imagesetfile: Text file containing the list of images, one image per line.
    classname: Category name (duh)
    cachedir: Directory for caching the annotations
    [ovthresh]: Overlap threshold (default = 0.5)
    [use_07_metric]: Whether to use VOC07's 11 point AP computation
        (default False)
    """
    # assumes detections are in detpath.format(classname)
    # assumes annotations are in annopath.format(imagename)
    # assumes imagesetfile is a text file with each line an image name
    # cachedir caches the annotations in a pickle file

    # first load gt
    if not os.path.isdir(cachedir):
        os.mkdir(cachedir)
    cachefile = os.path.join(cachedir, 'annots.pkl')
    # read list of images
    with open(imagesetfile, 'r') as f:
        lines = f.readlines()
    imagenames = [x.strip() for x in lines]

    if not os.path.isfile(cachefile):
        # load annots
        recs = {}
        for i, imagename in enumerate(imagenames):
            recs[imagename] = parse_rec(annopath.format(imagename))
            if i % 100 == 0:
                print 'Reading annotation for {:d}/{:d}'.format(
                    i + 1, len(imagenames))
        # save
        print 'Saving cached annotations to {:s}'.format(cachefile)
        with open(cachefile, 'w') as f:
            cPickle.dump(recs, f)
    else:
        # load
        with open(cachefile, 'r') as f:
            recs = cPickle.load(f)

    # extract gt objects for this class
    class_recs = {}
    npos = 0
    for imagename in imagenames:
        R = [obj for obj in recs[imagename] if obj['name'] == classname]
        bbox = np.array([x['bbox'] for x in R])
        difficult = np.array([x['difficult'] for x in R]).astype(np.bool)
        det = [False] * len(R)
        npos = npos + sum(~difficult)
        class_recs[imagename] = {'bbox': bbox,
                                 'difficult': difficult,
                                 'det': det}

    # read dets
    detfile = detpath
    with open(detfile, 'r') as f:
        lines = f.readlines()

    splitlines = [x.strip().split(' ') for x in lines]
    image_ids = [x[0] for x in splitlines]
    confidence = np.array([float(x[1]) for x in splitlines])
    BB = np.array([[float(z) for z in x[2:]] for x in splitlines])

    # sort by confidence
    sorted_ind = np.argsort(-confidence)
    sorted_scores = np.sort(-confidence)
    BB = BB[sorted_ind, :]
    image_ids = [image_ids[x] for x in sorted_ind]

    # go down dets and mark TPs and FPs
    nd = len(image_ids)
    tp = np.zeros(nd)
    fp = np.zeros(nd)
    for d in range(nd):
        R = class_recs[image_ids[d]]
        bb = BB[d, :].astype(float)
        ovmax = -np.inf
        BBGT = R['bbox'].astype(float)

        if BBGT.size > 0:
            # compute overlaps
            # intersection
            ixmin = np.maximum(BBGT[:, 0], bb[0])
            iymin = np.maximum(BBGT[:, 1], bb[1])
            ixmax = np.minimum(BBGT[:, 2], bb[2])
            iymax = np.minimum(BBGT[:, 3], bb[3])
            iw = np.maximum(ixmax - ixmin + 1., 0.)
            ih = np.maximum(iymax - iymin + 1., 0.)
            inters = iw * ih

            # union
            uni = ((bb[2] - bb[0] + 1.) * (bb[3] - bb[1] + 1.) +
                   (BBGT[:, 2] - BBGT[:, 0] + 1.) *
                   (BBGT[:, 3] - BBGT[:, 1] + 1.) - inters)

            overlaps = inters / uni
            ovmax = np.max(overlaps)
            jmax = np.argmax(overlaps)

        if ovmax > ovthresh:
            if not R['difficult'][jmax]:
                if not R['det'][jmax]:
                    tp[d] = 1.
                    R['det'][jmax] = 1
                else:
                    fp[d] = 1.
        else:
            fp[d] = 1.

    # compute precision recall
    fp = np.cumsum(fp)
    tp = np.cumsum(tp)
    rec = tp / float(npos)
    # avoid divide by zero in case the first detection matches a difficult
    # ground truth
    prec = tp / np.maximum(tp + fp, np.finfo(np.float64).eps)
    ap = voc_ap(rec, prec, use_07_metric)

    return rec, prec, ap