Keras版Faster-RCNN代码学习（measure_map，train/test）5

Keras版Faster-RCNN代码学习（IOU，RPN）1
Keras版Faster-RCNN代码学习（Batch Normalization）2
Keras版Faster-RCNN代码学习（loss，xml解析）3
Keras版Faster-RCNN代码学习（roipooling resnet/vgg）4
Keras版Faster-RCNN代码学习（measure_map，train/test）5

mAP

mAP是目标算法中衡量算法的精确度的指标，涉及两个概念：查准率Precision、查全率Recall。对于object detection任务，每一个object都可以计算出其Precision和Recall，多次计算/试验，每个类都 可以得到一条P-R曲线，曲线下的面积就是AP的值，这个mean的意思是对每个类的AP再求平均，得到的就是mAP的值，mAP的大小一定在[0,1]区间。
AP:Precision对Recall积分，可通过改变正负样本阈值求得矩形面积，进而求积分得到，也可以通过sklearn.metrics.average_precision_score函数直接得到。
mAP:每类AP求均值

measure_py

传入预测值和真实值和resize比例，得到可以传入sklearn.metrics.average_precision_score函数的值，即：真实值和预测概率

def get_map(pred, gt, f):
    T = {}
    P = {}
    fx, fy = f

    for bbox in gt:
        bbox['bbox_matched'] = False

    pred_probs = np.array([s['prob'] for s in pred])
    box_idx_sorted_by_prob = np.argsort(pred_probs)[::-1]

    for box_idx in box_idx_sorted_by_prob:
        pred_box = pred[box_idx]
        pred_class = pred_box['class']
        pred_x1 = pred_box['x1']
        pred_x2 = pred_box['x2']
        pred_y1 = pred_box['y1']
        pred_y2 = pred_box['y2']
        pred_prob = pred_box['prob']
        if pred_class not in P:
            P[pred_class] = []
            T[pred_class] = []
        P[pred_class].append(pred_prob)
        found_match = False

        for gt_box in gt:
            gt_class = gt_box['class']
            gt_x1 = gt_box['x1']/fx
            gt_x2 = gt_box['x2']/fx
            gt_y1 = gt_box['y1']/fy
            gt_y2 = gt_box['y2']/fy
            gt_seen = gt_box['bbox_matched']
            if gt_class != pred_class:
                continue
            if gt_seen:
                continue
            iou = data_generators.iou((pred_x1, pred_y1, pred_x2, pred_y2), (gt_x1, gt_y1, gt_x2, gt_y2))
            if iou >= 0.5:
                found_match = True
                gt_box['bbox_matched'] = True
                break
            else:
                continue

        T[pred_class].append(int(found_match))
        #漏检的计入
    for gt_box in gt:
        if not gt_box['bbox_matched'] and not gt_box['difficult']:
            if gt_box['class'] not in P:
                P[gt_box['class']] = []
                T[gt_box['class']] = []

            T[gt_box['class']].append(1)
            P[gt_box['class']].append(0)

    #import pdb
    #pdb.set_trace()
    return T, P

resize比例计算

def format_img(img, C):
    img_min_side = float(C.im_size)
    (height,width,_) = img.shape

    if width <= height:
        f = img_min_side/width
        new_height = int(f * height)
        new_width = int(img_min_side)
    else:
        f = img_min_side/height
        new_width = int(f * width)
        new_height = int(img_min_side)
    fx = width/float(new_width)
    fy = height/float(new_height)
    img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_CUBIC)
    img = img[:, :, (2, 1, 0)]
    img = img.astype(np.float32)
    img[:, :, 0] -= C.img_channel_mean[0]
    img[:, :, 1] -= C.img_channel_mean[1]
    img[:, :, 2] -= C.img_channel_mean[2]
    img /= C.img_scaling_factor
    img = np.transpose(img, (2, 0, 1))
    img = np.expand_dims(img, axis=0)
    return img, fx, fy

然后搭建网络，载入权重，传递参数，计算mAP～～

train_frcnn

from __future__ import division
import random
import pprint
import sys
import time
import numpy as np
from optparse import OptionParser
import pickle

from keras import backend as K
from keras.optimizers import Adam, SGD, RMSprop
from keras.layers import Input
from keras.models import Model
from keras_frcnn import config, data_generators
from keras_frcnn import losses as losses
import keras_frcnn.roi_helpers as roi_helpers
from keras.utils import generic_utils

sys.setrecursionlimit(40000)

parser = OptionParser()

parser.add_option("-p", "--path", dest="train_path", help="Path to training data.")
parser.add_option("-o", "--parser", dest="parser", help="Parser to use. One of simple or pascal_voc",
                default="pascal_voc")
parser.add_option("-n", "--num_rois", type="int", dest="num_ro