yolo v3 keras版本增加图形界面UI

前一阵在看yolo v3 keras版本的代码，看完后自己重新训练了一个自己的数据集，但在测试时总觉得不太方便，于是尝试着在代码基础上增加一个可视化界面，可以进行图片的测试和视频的测试，由于是python新手，界面不求美观，但求基础功能能用，下面是最终的界面图：

界面左上部分显示检测的结果图片，右上半部分是选择图片和视频的按钮，其中点击视频检测时，选择mp4文件后，会弹出另一个视频实时检测的界面。
图片检测时，下面每一行显示一个检测结果，单击对应的结果后，图片上会只显示此结果的对应框，如下图：

目前这个代码基本功能可用，因此分享出来，修改的地方主要是修改了yolo_video.py和yolo.py模块。
感兴趣的童鞋可以在下面链接中下载源码（不包括.h5模型库）：
https://github.com/markwentian/AI.git

yolo_video.py模块主要是添加界面功能，修改后代码为：

import sys
import argparse
from yolo import YOLO, detect_video
from tkinter import *
from tkinter import ttk
from tkinter import filedialog
from PIL import Image,ImageFont,ImageDraw,ImageTk
import numpy as np
from timeit import default_timer as timer
import time
def detect_img(yolo):
    while True:
        img = input('Input image filename:')
        try:
            image = Image.open('./'+img)
        except:
            print('Open Error! Try again!')
            break
        else:
            r_image = yolo.detect_image(image)
            r_image.show()
    yolo.close_session()

FLAGS = None
class App:
    def __init__(self,master,yolo):
        self.master=master
        self.initWidgets()
        self.yolo=yolo
        
    def initWidgets(self):
        topF=Frame(self.master)
        topF.pack(side=TOP,fill=BOTH)
        self.cv=Canvas(topF,background='white',width=450,height=450)
        self.cv.pack(side=LEFT,fill=BOTH,expand=YES)
        
        
        
        
        ttk.Button(topF,text='打开图片文件',command=self.open_file).pack(side=RIGHT,fill=Y,expand=YES,anchor=CENTER)
        ttk.Button(topF,text='打开MP4视频文件',command=self.open_video).pack(side=RIGHT,fill=Y,expand=YES,anchor=CENTER)
        self.yolo_result=StringVar()
        topF3=Frame(self.master)
        topF3.pack(side=BOTTOM,fill=BOTH)
        ttk.Label(topF3,text='检测结果',padding=20).pack(side=TOP,fill=X,expand=YES)
        self.lb=Listbox(topF3,listvariable=self.yolo_result,selectmode='single')
        self.lb.pack(side=BOTTOM,fill=X,expand=YES)
        self.lb.bind("<ButtonRelease-1>",self.click)
        
        
        
        self.yolo_result_store=[]
        self.class_names=[]
        self.colors=[]
        
        
    def click(self,event):
        index_temp=self.lb.curselection()
        index_temp2=index_temp[0]
        yolo_result_click=self.yolo_result_store[index_temp2]
        wdawdaw=self.yolo_result_store
        predicted_class_click=yolo_result_click[0]
        score_click=yolo_result_click[1]
        box_click=yolo_result_click[2]
        thickness_click=yolo_result_click[3]
        c_click=yolo_result_click[4]
        
        
        
        image_click=self.image.crop()
        predicted_class=predicted_class_click
        box=box_click
        score=score_click
        
        label='{} {:.2f}'.format(predicted_class,score)
        draw=ImageDraw.Draw(image_click)
        label_size=draw.textsize(label,self.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(self.image.size[1], np.floor(bottom + 0.5).astype('int32'))
        right = min(self.image.size[0], np.floor(right + 0.5).astype('int32'))

        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_click):
            draw.rectangle(
                [left + i, top + i, right - i, bottom - i],
                outline=self.colors[c_click])
        draw.rectangle(
            [tuple(text_origin), tuple(text_origin + label_size)],
            fill=self.colors[c_click])
        draw.text(text_origin, label, fill=(0, 0, 0), font=self.font)
        del draw
        image_click=image_click.resize((416,416))
        size0=image_click.size[0]
        size1=image_click.size[1]
        self.cv.bm=ImageTk.PhotoImage(image_click)
        self.cv.create_image(size0/2+17,size1/2+17,image=self.cv.bm)
    def open_file(self):
        self.yolo_result.set('')
        self.yolo_result_store.clear()
        img=filedialog.askopenfilename(title='打开单个文件',filetypes=[("JPEG图像","*.jpg"),("JPEG图像","*.jpeg"),('PNG图像','*.png')],initialdir='F:/')
        print(img)
        print(type(img))
        try:
            self.image=Image.open(img)
        except:    
            print('Open Error! Try again!')
            
        else:
           r_image,out_boxes,out_scores,out_classes,self.font,thickness,calculate_time,self.class_names,self.colors = self.yolo.detect_image(self.image) 
        image_main=self.image.crop()
        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_main)
            label_size = draw.textsize(label, self.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(self.image.size[1], np.floor(bottom + 0.5).astype('int32'))
            right = min(self.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=self.font)
            del draw
            
            self.yolo_result_store.append((predicted_class,score,box,thickness,c))
            
            self.lb.insert(END,str(predicted_class)+' -->'+'    score:   '+str(score)+'    position:    '+str(box))
        image_main=image_main.resize((416,416))
        size0=image_main.size[0]
        size1=image_main.size[1]
        self.cv.bm=ImageTk.PhotoImage(image_main)
        self.cv.create_image(size0/2+17,size1/2+17,image=self.cv.bm)
        
    def open_video(self):
        
        video_path=filedialog.askopenfilename(title='打开单个文件',filetypes=[("视频文件","*.mp4")],initialdir='F:/')

        detect_video(self.yolo,video_path)            
        
    def detect_img(self):
        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()
            #self.yolo.close_session()    
            
if __name__ == '__main__':
    # class YOLO defines the default value, so suppress any default here
    parser = argparse.ArgumentParser(argument_default=argparse.SUPPRESS)
    '''
    Command line options
    '''
    parser.add_argument(
        '--model', type=str,
        help='path to model weight file, default ' + YOLO.get_defaults("model_path")
    )

    parser.add_argument(
        '--anchors', type=str,
        help='path to anchor definitions, default ' + YOLO.get_defaults("anchors_path")
    )

    parser.add_argument(
        '--classes', type=str,
        help='path to class definitions, default ' + YOLO.get_defaults("classes_path")
    )

    parser.add_argument(
        '--gpu_num', type=int,
        help='Number of GPU to use, default ' + str(YOLO.get_defaults("gpu_num"))
    )

    parser.add_argument(
        '--image', default=False, action="store_true",
        help='Image detection mode, will ignore all positional arguments'
    )
    '''
    Command line positional arguments -- for video detection mode
    '''
    parser.add_argument(
        "--input", nargs='?', type=str,required=False,default='./path2your_video',
        help = "Video input path"
    )

    parser.add_argument(
        "--output", nargs='?', required=False, type=str, default="dayu.avi",
        help = "[Optional] Video output path"
    )

    FLAGS = parser.parse_args()
    #if FLAGS.image:
    root=Tk()
    root.title('YOLO图形识别')
        
        
        
        
        
    App_inst=App(root,YOLO(**vars(FLAGS)))
    root.resizable(width=True,height=True)
    root.mainloop()

yolo.py的代码为：

# -*- 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',
        "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()
        self.model_path='model_data/yolo.h5'
        self.anchors_path='model_data/yolo_anchors.txt'
        self.classes_path='model_data/voc_class.txt'
        self.gpu_num=1
        self.model_image_size=(416,416)

    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)
            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

        end = timer()
        calculate_time=end - start
        print(calculate_time)
        return image,out_boxes,out_scores,out_classes,font,thickness,calculate_time,self.class_names,self.colors

    def close_session(self):
        self.sess.close()
    
    def detect_image2(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 detect_video(yolo, video_path, output_path=""):
    import cv2
    output_path='./test.mp4'
    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(output_path, 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_image2(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()