YOLOV4用训练好的模型实现在测试集上批量画框

很多现存的YOLOV4开源代码是使用单张图片进行测试，下面这个程序可以根据训练好的模型实现对测试集进行批量画框，简单方便。

import os
import numpy as np
import copy
import colorsys
import time
from timeit import default_timer as timer
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw
from nets.yolo4 import yolo_body,yolo_eval
from utils.utils import letterbox_image

import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"
#......
path = './VOCdevkit/VOC2007_test/JPEGImages/'  #待检测图片的位置

# 创建创建一个存储检测结果的dir
result_path = './output'
if not os.path.exists(result_path):
    os.makedirs(result_path)

# result如果之前存放的有文件，全部清除
for i in os.listdir(result_path):
    path_file = os.path.join(result_path,i)
    if os.path.isfile(path_file):
        os.remove(path_file)

#创建一个记录检测结果的文件
txt_path =result_path + '/result.txt'
file = open(txt_path,'w')
#..........

class YOLO(object):
    _defaults = {
        "model_path": '/log/ep100-loss15.036-val_loss15.055.h5',
        "anchors_path": 'model_data/yolo_anchors_512.txt',
        "classes_path": 'model_data/coco_classes.txt',
        "score": 0.5,
        "iou": 0.5,
        # 显存比较小可以使用416x416
        # 显存比较大可以使用608x608
        "model_image_size" : (512, 512)
    }

    @classmethod
    def get_defaults(cls, n):
        if n in cls._defaults:
            return cls._defaults[n]
        else:
            return "Unrecognized attribute name '" + n + "'"

    # ---------------------------------------------------#
    #   初始化yolo
    # ---------------------------------------------------#
    def __init__(self, **kwargs):
        self.__dict__.update(self._defaults)
        self.class_names = self._get_class()
        self.anchors = self._get_anchors()
        self.sess = K.get_session()
        self.boxes, self.scores, self.classes = self.generate()

    # ---------------------------------------------------#
    #   获得所有的分类
    # ---------------------------------------------------#
    def _get_class(self):
        classes_path = os.path.expanduser(self.classes_path)
        with open(classes_path) as f:
            class_names = f.readlines()
        class_names = [c.strip() for c in class_names]
        return class_names

    # ---------------------------------------------------#
    #   获得所有的先验框
    # ---------------------------------------------------#
    def _get_anchors(self):
        anchors_path = os.path.expanduser(self.anchors_path)
        with open(anchors_path) as f:
            anchors = f.readline()
        anchors = [float(x) for x in anchors.split(',')]
        return np.array(anchors).reshape(-1, 2)

    # ---------------------------------------------------#
    #   获得所有的分类
    # ---------------------------------------------------#
    def generate(self):
        model_path = os.path.expanduser(self.model_path)
        assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'

        # 计算anchor数量
        num_anchors = len(self.anchors)
        num_classes = len(self.class_names)

        # 载入模型，如果原来的模型里已经包括了模型结构则直接载入。
        # 否则先构建模型再载入
        try:
            self.yolo_model = load_model(model_path, compile=False)
        except:
            self.yolo_model = yolo_body(Input(shape=(None, None, 3)), num_anchors // 3, num_classes)
            self.yolo_model.load_weights(self.model_path)
        else:
            assert self.yolo_model.layers[-1].output_shape[-1] == \
                   num_anchors / len(self.yolo_model.output) * (num_classes + 5), \
                'Mismatch between model and given anchor and class sizes'

        print('{} model, anchors, and classes loaded.'.format(model_path))
        
        # 画框设置不同的颜色
        hsv_tuples = [(x / len(self.class_names), 1., 1.)
                      for x in range(len(self.class_names))]
        self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
        self.colors = list(
            map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
                self.colors))

        # 打乱颜色
        np.random.seed(10101)
        np.random.shuffle(self.colors)
        np.random.seed(None)

        self.input_image_shape = K.placeholder(shape=(2,))

        boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
                                           num_classes, self.input_image_shape,
                                           score_threshold=self.score, iou_threshold=self.iou)
        return boxes, scores, classes

    # ---------------------------------------------------#
    #   检测图片
    # ---------------------------------------------------#
    def detect_image(self, image):
        start = timer()

        # 调整图片使其符合输入要求
        new_image_size = self.model_image_size
        boxed_image = letterbox_image(image, new_image_size)
        image_data = np.array(boxed_image, dtype='float32')
        image_data /= 255.
        image_data = np.expand_dims(image_data, 0)  # Add batch dimension.

        # 预测结果
        out_boxes, out_scores, out_classes = self.sess.run(
            [self.boxes, self.scores, self.classes],
            feed_dict={
                self.yolo_model.input: image_data,
                self.input_image_shape: [image.size[1], image.size[0]],
                K.learning_phase(): 0
            })

        print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
     
        # 设置字体
        font = ImageFont.truetype(font='font/simhei.ttf',
                                  size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
        thickness = (image.size[0] + image.size[1]) // 300

        small_pic = []

        for i, c in list(enumerate(out_classes)):
            predicted_class = self.class_names[c]
            box = out_boxes[i]
            score = out_scores[i]

            top, left, bottom, right = box
            top = top - 5
            left = left - 5
            bottom = bottom + 5
            right = right + 5

            top = max(0, np.floor(top + 0.5).astype('int32'))
            left = max(0, np.floor(left + 0.5).astype('int32'))
            bottom = min(image.size[1], np.floor(bottom + 0.5).astype('int32'))
            right = min(image.size[0], np.floor(right + 0.5).astype('int32'))

            # 画框框
            label = '{} {:.2f}'.format(predicted_class, score)
            draw = ImageDraw.Draw(image)
            label_size = draw.textsize(label, font)
            label = label.encode('utf-8')
            print(label)

            if top - label_size[1] >= 0:
                text_origin = np.array([left, top - label_size[1]])
            else:
                text_origin = np.array([left, top + 1])

            for i in range(thickness):
                draw.rectangle(
                    [left + i, top + i, right - i, bottom - i],
                    outline=self.colors[c])
            draw.rectangle(
                [tuple(text_origin), tuple(text_origin + label_size)],
                fill=self.colors[c])
            draw.text(text_origin, str(label, 'UTF-8'), fill=(0, 0, 0), font=font)
            del draw

        end = timer()
        print(end - start)
        return image

    def close_session(self):
        self.sess.close()

#.......
# 图片检测

if __name__ == '__main__':

    t1 = time.time()
    yolo = YOLO()
    for filename in os.listdir(path):
        # print(filename)
        image_path = path+'/'+filename
        portion = os.path.split(image_path)
        file.write(portion[1]+' detect_result：\n')
        image = Image.open(image_path)
        r_image = yolo.detect_image(image)
        file.write('\n')
        #r_image.show() 显示检测结果
        image_save_path = './output/'+portion[1]
        print('detect result save to....:'+image_save_path)
        r_image.save(image_save_path)

    time_sum = time.time() - t1
    file.write('time sum: '+str(time_sum)+'s')
    print('time sum:',time_sum)
    file.close()
    yolo.close_session()
# .......