自有数据集上使用keras训练YOLOv3目标检测

images/images_all/86900fb6gy1fl4822o7qmj22ao328qv7.jpg 10,259,399,580,27
images/images_all/b95fe9cbgw1eyw88vlifjj20c70hsq46.jpg 10,353,439,640,29
images/images_all/005CsCZ0jw1f1n8kcj8m1j30ku0kumz6.jpg 75,141,343,321,27

    class yolo_args:
        annotation_path = ‘train.txt‘
        log_dir = ‘logs/003/‘
        classes_path = ‘model_data/class_file_en.txt‘
        anchors_path = ‘model_data/yolo_anchors.txt‘
        input_shape = (416,416) # multiple of 32, hw
        # 608*608  416*416  320*320
        val_split = 0.1
        batch_size = 16
        epochs_stage_1 = 10
        stage_1_train = False
        epochs_finally = 100
        finally_train = True
        weights_path =   ‘logs/003/ep009-loss33.297-val_loss32.851.h5‘

        # 可以使用‘model_data/tiny_yolo_weights.h5‘ 也可以使用tiny_yolo的：‘model_data/yolo_weights.h5‘
    # train
    _main(yolo_args)

annotation_path就是数据集准备的txt
log_dir ，Model存放地址，譬如：events.out.tfevents.1545966202、ep077-loss19.318-val_loss19.682.h5
classes_path ，分类内容
anchors_path ，yolo anchors，可自行调整，也可以使用默认的
input_shape ，一般是416
epochs_stage_1 = 10和 stage_1_train = False，是同一个，也就是是否进行迁移学习（stage_1_train ），要学习的话，学习几个epoch（epochs_stage_1 ）
epochs_finally = 100和 finally_train = True ，是，是否进行后面开放所有层的学习（finally_train ），学习几个epoch（epochs_finally）
weights_path ，调用model的路径

import sys
import argparse
from yolo import YOLO, detect_video
from PIL import Image

yolo_test_args = {
    "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,
}

yolo_test = YOLO(**yolo_test_args)
image = Image.open(‘images/part1/path1.jpg‘)
r_image = yolo_test.detect_image(image)
r_image.show()

import sys
import argparse
from yolo_matt import YOLO, detect_video
from PIL import Image

yolo_test_args = {
    "model_path": ‘logs/003/ep077-loss19.318-val_loss19.682.h5‘,
    "anchors_path": ‘model_data/yolo_anchors.txt‘,
    "classes_path": ‘model_data/class_file_en.txt‘,
    "score" : 0.2,# 0.2
    "iou" : 0.1,# 0.45
    "model_image_size" : (416, 416),
    "gpu_num" : 1,
}

yolo_test = YOLO(**yolo_test_args)

# 输出内容整理
def _get_class(classes_path):
    classes_path = os.path.expanduser(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 yolov3_output(image,out_boxes,out_scores,out_classes):
    output = []
    yolo_classes = _get_class(yolo_test_args[‘classes_path‘])
    for n,box in enumerate(out_boxes):
        y_min, x_min, y_max, x_max = box
        y_min = max(0, np.floor(y_min + 0.5).astype(‘int32‘))
        x_min = max(0, np.floor(x_min + 0.5).astype(‘int32‘))
        y_max = min(image.size[1], np.floor(y_max + 0.5).astype(‘int32‘))
        x_max = min(image.size[0], np.floor(x_max + 0.5).astype(‘int32‘))
        score = out_scores[n]
        yo_class = yolo_classes[out_classes[n]]
        output.append({ ‘y_min‘:y_min, ‘x_min‘:x_min, ‘y_max‘:y_max, ‘x_max‘:x_max,\
                       ‘width‘:image.size[0],‘height‘:image.size[1],\
                       ‘score‘:score,‘yo_class‘:yo_class})
    return output
    
image = Image.open(‘images/images_all/path1.jpg‘)
r_image,out_boxes, out_scores, out_classes = yolo_test.detect_image(image)
output = yolov3_output(r_image,out_boxes,out_scores,out_classes)

{
‘path1.jpg‘: 
[{‘y_min‘: 416,   ‘x_min‘: 34,   ‘y_max‘: 754,   ‘x_max‘: 367,   ‘width‘: 440,   ‘height‘: 783,   ‘score‘: 0.9224778,   ‘yo_class‘: ‘class1‘},
  {‘y_min‘: 428,   ‘x_min‘: 3,   ‘y_max‘: 783,   ‘x_max‘: 352,   ‘width‘: 440,   ‘height‘: 783,   ‘score‘: 0.2180994,   ‘yo_class‘: ‘class2‘}]
  }