目标检测中几个指标的衡量

import os
import sys
sys.path.insert(0, "/home/xx/faceDetect/caffe/python")
import cv2
from xml.etree import ElementTree as ET
import numpy as np

import caffe
caffe.set_device(0)
caffe.set_mode_gpu()


model = "ssh_6.5M_400/model"
config = "ssh_6.5M_400/modelconfig"
net = caffe.Net(config, model, caffe.TEST)

transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2, 0, 1))
transformer.set_mean('data', np.array([104,117,123])) # mean pixel
transformer.set_raw_scale('data', 255)  # the reference model operates on images in [0,255] range instead of [0,1]
transformer.set_channel_swap('data', (2,1,0))  # the reference model has channels in BGR order instead of RGB


# set net to batch size of 1
image_resize = 400
net.blobs['data'].reshape(1,3,image_resize,image_resize)

gtRoot = "shoulder_test/gt"
imgRoot = "shoulder_test/image"
testFile = "shoulder_test/test.txt"

def IoUs(rect, boxs, type=0):
    x1 = rect[0]
    y1 = rect[1]
    x2 = rect[2]
    y2 = rect[3]
    xs1 = boxs[:,0]
    ys1 = boxs[:,1]
    xs2 = boxs[:,2]
    ys2 = boxs[:,3]
    rect_area = (x2 - x1 + 1) * (y2 - y1 + 1)
    areas = (xs2 - xs1 + 1) * (ys2 - ys1 + 1)
    ws = np.maximum(0, np.minimum(x2, xs2) - np.maximum(x1, xs1) + 1)
    hs = np.maximum(0, np.minimum(y2, ys2) - np.maximum(y1, ys1) + 1)
    inters = ws * hs
    if type==0:
        unions = areas + rect_area - inters
    else:
        unions = np.minimum(areas, rect_area)
    return inters/unions

tp = 0
fn = 0
tfp = 0
tp_fn = 0
count = 0


with open(testFile) as f:
	for line in f:
		name = line.strip()
		imgFile = imgRoot + "/" + name + ".jpg"
		gtFile = gtRoot + "/" + name + ".xml"

		img = cv2.imread(imgFile)
		tree = ET.parse(gtFile)
		root = tree.getroot()
		gtRects = []
		for bndbox in root.iter(tag="bndbox"):
			xmin = int(bndbox[0].text)
			ymin = int(bndbox[1].text)
			xmax = int(bndbox[2].text)
			ymax = int(bndbox[3].text)
			rect = [xmin, ymin, xmax, ymax]
			gtRects.append(rect)
			cv2.rectangle(img, (xmin,ymin),(xmax,ymax),(0,0,255),2)
			tp_fn += 1

		gtRects = np.array(gtRects)

		image = caffe.io.load_image(imgFile)
		transformed_image = transformer.preprocess('data', image)
		net.blobs['data'].data[...] = transformed_image

		detections = net.forward()['detection_out']

		det_label = detections[0,0,:,1]
		det_conf = detections[0,0,:,2]
		det_xmin = detections[0,0,:,3]
		det_ymin = detections[0,0,:,4]
		det_xmax = detections[0,0,:,5]
		det_ymax = detections[0,0,:,6]

		top_indices = [i for i, conf in enumerate(det_conf) if conf >= 0.6]

		top_conf = det_conf[top_indices]

		top_xmin = det_xmin[top_indices]
		top_ymin = det_ymin[top_indices]
		top_xmax = det_xmax[top_indices]
		top_ymax = det_ymax[top_indices]

		tfp += top_conf.shape[0]

		tp_idx = []

		for i in xrange(top_conf.shape[0]):
			xmin = round(top_xmin[i] * img.shape[1])
			ymin = round(top_ymin[i] * img.shape[0])
			xmax = round(top_xmax[i] * img.shape[1])
			ymax = round(top_ymax[i] * img.shape[0])
			rect = [xmin, ymin, xmax, ymax]
			iou = IoUs(rect, gtRects)

			# cv2.rectangle(img, (int(xmin),int(ymin)),(int(xmax),int(ymax)),(255,0,0),2)
			# cv2.imshow("ha", img)
			# cv2.waitKey()

			if np.max(iou) > 0.5:
				tp += 1

			# idx = np.where(iou>0.5)
			# tp_idx = np.append(tp_idx, idx)

		count += 1
		print count
fn = tp_fn - tp
print "tp: ",tp
print "tfp: ", tfp
print "tp_fn: ", tp_fn
print "precision: ", float(tp)/(float(tfp)) 
print "miss rate: ", float(fn)/tp_fn
		# cv2.imshow("", img)
		# cv2.waitKey()