yolo.py

# -*- coding: utf-8 -*-
"""
Class definition of YOLO_v3 style detection model on image and video
"""

import colorsys
import os
from timeit import default_timer as timer

import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
from PIL import Image, ImageFont, ImageDraw

from yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
from yolo3.utils import letterbox_image
import os
from keras.utils import multi_gpu_model

# 修改的参数
# classes_path = 'model_data/my_classes.txt'
# model_path = 'logs/000/trained_weights_final.h5'
# model_image_size = (640, 640)
# gpu_num = 2
max_boxes = 300
# score_threshold = 0.1
# iou_threshold = 0.45


class YOLO(object):
    classes_path = 'model_data/my_classes.txt'
    model_path = 'logs/000/trained_weights_final.h5'
    model_image_size = (640, 640)
    gpu_num = 6
    # max_boxes = 300
    score_threshold = 0.1
    iou_threshold = 0.35

    _defaults = {
        "model_path": model_path,
        "anchors_path": 'model_data/yolo_anchors.txt',
        "classes_path": classes_path,
        "score": score_threshold,
        "iou": iou_threshold,
        "model_image_size": model_image_size,
        "gpu_num": gpu_num,
    }

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

    def __init__(self, **kwargs):
        self.__dict__.update(self._defaults)  # set up default values
        self.__dict__.update(kwargs)  # and update with user overrides
        self.class_names = self._get_class()
        self.anchors = self._get_anchors()
        self.sess = K.get_session()
        self.boxes, self.scores, self.classes = self.generate()

    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

    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)

    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.'

        # Load model, or construct model and load weights.
        num_anchors = len(self.anchors)
        num_classes = len(self.class_names)
        is_tiny_version = num_anchors == 6  # default setting
        try:
            self.yolo_model = load_model(model_path, compile=False)
        except:
            self.yolo_model = tiny_yolo_body(Input(shape=(None, None, 3)), num_anchors//2, num_classes) \
                if is_tiny_version else yolo_body(Input(shape=(None, None, 3)), num_anchors//3, num_classes)
            # make sure model, anchors and classes match
            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))

        # Generate colors for drawing bounding boxes.
        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))
        np.random.seed(10101)  # Fixed seed for consistent colors across runs.
        # Shuffle colors to decorrelate adjacent classes.
        np.random.shuffle(self.colors)
        np.random.seed(None)  # Reset seed to default.

        # Generate output tensor targets for filtered bounding boxes.
        self.input_image_shape = K.placeholder(shape=(2, ))
        if self.gpu_num >= 2:
            self.yolo_model = multi_gpu_model(
                self.yolo_model, gpus=self.gpu_num)
        boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
                                           len(self.class_names), self.input_image_shape,
                                           score_threshold=self.score, iou_threshold=self.iou, max_boxes=max_boxes)
        return boxes, scores, classes

    def nms(self, boxes, scores, thresh):
        '''
        # dets: 检测的 boxes 及对应的 scores；
        # thresh: 设定的阈值
        '''
        # boxes 位置
        x1 = boxes[:, 0]
        y1 = boxes[:, 1]
        x2 = boxes[:, 2]
        y2 = boxes[:, 3]
        # boxes scores
        scores = scores

        areas = (x2 - x1 + 1) * (y2 - y1 + 1)  # 各 box 的面积
        order = scores.argsort()[::-1]  # boxes 的按照 score 排序

        keep = []  # 记录保留下的 boxes
        while order.size > 0:
            i = order[0]  # score 最大的 box 对应的 index
            keep.append(i)  # 将本轮 score 最大的 box 的 index 保留

            # 计算剩余 boxes 与当前 box 的重叠程度 IoU
            xx1 = np.maximum(x1[i], x1[order[1:]])
            yy1 = np.maximum(y1[i], y1[order[1:]])
            xx2 = np.minimum(x2[i], x2[order[1:]])
            yy2 = np.minimum(y2[i], y2[order[1:]])

            w = np.maximum(0.0, xx2 - xx1 + 1)  # IoU
            h = np.maximum(0.0, yy2 - yy1 + 1)
            inter = w * h
            ovr = inter / (areas[i] + areas[order[1:]] - inter)

            # 保留 IoU 小于设定阈值的 boxes
            inds = np.where(ovr <= thresh)[0]
            order = order[inds + 1]

        return keep

    def detect_image(self, image):
        if self.model_image_size != (None, None):
            assert self.model_image_size[0] % 32 == 0, 'Multiples of 32 required'
            assert self.model_image_size[1] % 32 == 0, 'Multiples of 32 required'
            boxed_image = letterbox_image(
                image, tuple(reversed(self.model_image_size)))
        else:
            new_image_size = (image.width - (image.width % 32),
                              image.height - (image.height % 32))
            boxed_image = letterbox_image(image, new_image_size)
        image_data = np.array(boxed_image, dtype='float32')

        # print(image_data.shape)
        image_data /= 255.
        image_data = np.expand_dims(image_data, 0)  # Add batch dimension.

        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
            })
        #############################################################################
        """
        NMS   0.2
        """
        keep_boxes_index = self.nms(out_boxes, out_scores, thresh=0.2)
        len1 = len(out_scores)
        len2 = len(keep_boxes_index)
        out_boxes, out_scores, out_classes = out_boxes[keep_boxes_index], out_scores[
            keep_boxes_index], out_classes[keep_boxes_index]

        print('经过NMS后删除了{}个Box!'.format(len1-len2))
        #############################################################################

        # print('Found {} boxes for {}'.format(len(out_boxes), 'img'))

        font = ImageFont.truetype(font='font/FiraMono-Medium.otf',
                                  size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
        thickness = (image.size[0] + image.size[1]) // 2000

        label_record = []
        score_record = []
        top_record = []
        left_record = []
        bottom_record = []
        right_record = []
        jpg_record = []

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

            label = '{} {:.2f}'.format(predicted_class, score)
            draw = ImageDraw.Draw(image)
            label_size = draw.textsize(label, font)

            top, left, bottom, right = box
            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'))
            # print(label, (left, top), (right, bottom))

            label_record.append(predicted_class)
            score_record.append(score)
            top_record.append(top)
            left_record.append(left)
            bottom_record.append(bottom)
            right_record.append(right)

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

            # My kingdom for a good redistributable image drawing library.
            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, label, fill=(0, 0, 0), font=font)
            del draw
        return image, label_record, score_record, top_record, left_record, bottom_record, right_record

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