TensorFlow + Keras + YOLO V3用官网权重文件训练出错的注意事项

后期要用yolov3做物体检测，所以想要先试试用官网权重文件，训练TensorFlow + Keras + YOLO V3。然后输入一张随便图像，试试效果。弄了大半天，问了好几次学长查了超多博客。。。

1、下载TensorFlow + Keras + YOLO V3代码（keras-yolo3文件夹）

https://github.com/qqwweee/keras-yolo3

2、下载yoloV3权重文件：

https://pjreddie.com/media/files/yolov3.weights

3、将darknet下的yolov3配置文件转换成keras适用的h5文件：

python3 convert.py yolov3.cfg yolov3.weights model_data/yolo.h5

这个地方注意了！！！我就是各种磕绊在最后两步！！！执行上述命令的步骤是，（1）将权重文件下载好后，放到第一步下载的keras-yolo3文件夹里 （2）在pycharm里把keras-yolo3文件夹打开，file----open----选择文件夹 （3）打开convert.py，然后右键点击“open in Terminal”   （4）在底下那个输入框里输入上述命令“python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5”

第3步的步骤图

 

 

 

4、运行YOLO 目标检测，按照提示输入要测试的图片即可

python yolo.py

注意！！！！第四步我坑了很久，差点就放弃emmmmm！！！和第三步一样，“open in Terminal” ，然后输入上述指令。神奇的是，大家都说要这么做，但是我运行结果就一句"Using TensorFlow backend."根本没有输入图片的提示。。。查了很多博客，最后让我在评论里找到办法了哈哈哈哈哈哈。

方法一：“open in Terminal” ，输入"python yolo_video.py --image"（亲测有效）

之后就是按照提示，输入图像路径+名称。若将测试图像放在keras-yolo3文件夹里则只需输入文件名；不在同一文件夹则输入绝对路径。如下图：

第4步 步骤示意图

结果

 

第4步之输入绝对路径

方法二：给yolo.py 文件加以下代码段（亲测有效）

def detect_img(yolo):
    while True:
        img = input('Input image filename:')
        try:
            image = Image.open(img)
        except:
            print('Open Error! Try again!')
            continue
        else:
            r_image = yolo.detect_image(image)
            r_image.show()
    yolo.close_session()

if __name__ == '__main__':
    detect_img(YOLO()) 

改动之后，右键open in terminal，然后键入“python yolo.py”，输入图像名称即可。

以上参考https://blog.youkuaiyun.com/nofish_xp/article/details/81320314#commentsedit 文章和评论都不容错过

完成以上的两天后，我安装了tensorflow-gpu版本，安装过程一言难尽可看我另一篇博客。安装好gpu版本之后我就想再加载一下权重走一遍上述过程，第一次成功显示了上面那张图像，第二次我删除了yolo.py 的detect image(yolo)函数中的“continue”，按理来说不会影响结果，但是报错：cuda初始化失败。我重启pycharm之后把continue加回去试了一下成功，删掉continue再试，成功！！！所以continue删掉没关系啊，之前报错cuda初始化失败的原因目前不清楚。

四、运行视频

下面代码用于测试视频效果，需要修改两处（已在代码中标注）：1.自己的训练权重路径   2.测试视频路径和保存路径，我代码中默认保存在该代码当前文件夹中。

# -*- 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

class YOLO(object):
    _defaults = {
        "model_path": 'model_data/yolo.h5',#【改1】自己的权重文件路径
        "anchors_path": 'model_data/yolo_anchors.txt',
        "classes_path": 'model_data/coco_classes.txt',
        "score" : 0.3,
        "iou" : 0.45,
        "model_image_size" : (416, 416),
        "gpu_num" : 1,
    }

    @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, encoding="utf-8") 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)
            self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
        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.
        np.random.shuffle(self.colors)  # Shuffle colors to decorrelate adjacent classes.
        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)
        return boxes, scores, classes

    def detect_image(self, image):
        start = timer()

        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
            })

        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]) // 300

        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))

            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

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

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

def detect_video(yolo, video_path, output_path=""):
    import cv2
    vid = cv2.VideoCapture(video_path)
    if not vid.isOpened():
        raise IOError("Couldn't open webcam or video")
    video_FourCC    = int(vid.get(cv2.CAP_PROP_FOURCC))
    video_fps       = vid.get(cv2.CAP_PROP_FPS)
    video_size      = (int(vid.get(cv2.CAP_PROP_FRAME_WIDTH)),
                        int(vid.get(cv2.CAP_PROP_FRAME_HEIGHT)))
    isOutput = True if output_path != "" else False
    if isOutput:
        print("!!! TYPE:", type(output_path), type(video_FourCC), type(video_fps), type(video_size))
        out = cv2.VideoWriter("./video/test1.mp4",video_FourCC, video_fps, video_size)
    accum_time = 0
    curr_fps = 0
    fps = "FPS: ??"
    prev_time = timer()
    while True:
        return_value, frame = vid.read()
        image = Image.fromarray(frame)
        image = yolo.detect_image(image)
        result = np.asarray(image)
        curr_time = timer()
        exec_time = curr_time - prev_time
        prev_time = curr_time
        accum_time = accum_time + exec_time
        curr_fps = curr_fps + 1
        if accum_time > 1:
            accum_time = accum_time - 1
            fps = "FPS: " + str(curr_fps)
            curr_fps = 0
        cv2.putText(result, text=fps, org=(3, 15), fontFace=cv2.FONT_HERSHEY_SIMPLEX,
                    fontScale=0.50, color=(255, 0, 0), thickness=2)
        cv2.namedWindow("result", cv2.WINDOW_NORMAL)
        cv2.imshow("result", result)
        if isOutput:
            out.write(result)
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break
    yolo.close_session()

if __name__ =='__main__':
    yolo=YOLO()
    detect_video(yolo, video_path = '你的视频路径', output_path="output.mp4") #【改2】