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

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

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

python yolo_video.py --image

import xml.etree.ElementTree as ET
from os import getcwdsets=[('2018', 'train'), ('2018', 'val'), ('2018', 'test'), ('2018', 'trainval')]classes = []def convert_annotation(year, image_id, list_file):in_file = open('VOCdevkit\VOC%s\Annotations\%s.xml'%(year, image_id), encoding = 'utf-8')tree=ET.parse(in_file)root = tree.getroot()for obj in root.iter('object'):difficult = obj.find('difficult').textcls = obj.find('name').textif cls not in classes or int(difficult)==1:continuecls_id = classes.index(cls)xmlbox = obj.find('bndbox')b = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))wd = getcwd()for year, image_set in sets:image_ids = open('VOCdevkit\VOC%s\ImageSets\Main\%s.txt'%(year, image_set)).read().strip().split()list_file = open('%s_%s.txt'%(year, image_set), 'w')for image_id in image_ids:list_file.write('%s\VOCdevkit\VOC%s\JPEGImages\%s.jpg'%(wd, year, image_id))convert_annotation(year, image_id, list_file)list_file.write('\n')list_file.close()

python convert.py -w yolov3.cfg yolov3.weights model_data/yolo_weights.h5

python train.py

"""
Retrain the YOLO model for your own dataset.
"""
import numpy as np
import keras.backend as K
from keras.layers import Input, Lambda
from keras.models import Model
from keras.callbacks import TensorBoard, ModelCheckpoint, EarlyStoppingfrom yolo3.model import preprocess_true_boxes, yolo_body, tiny_yolo_body, yolo_loss
from yolo3.utils import get_random_datadef _main():annotation_path = 'voc/2018_trainval.txt'log_dir = 'model_data/logs/'classes_path = 'model_data/my_classes.txt'anchors_path = 'model_data/yolo_anchors.txt'class_names = get_classes(classes_path)anchors = get_anchors(anchors_path)input_shape = (416,416) # multiple of 32, hwmodel = create_model(input_shape, anchors, len(class_names) )train(model, annotation_path, input_shape, anchors, len(class_names), log_dir=log_dir)def train(model, annotation_path, input_shape, anchors, num_classes, log_dir='logs/'):model.compile(optimizer='adam', loss={'yolo_loss': lambda y_true, y_pred: y_pred})logging = TensorBoard(log_dir=log_dir)checkpoint = ModelCheckpoint(log_dir + "ep{epoch:03d}-loss{loss:.3f}-val_loss{val_loss:.3f}.h5",monitor='val_loss', save_weights_only=True, save_best_only=True, period=1)batch_size = 10val_split = 0.2with open(annotation_path) as f:lines = f.readlines()np.random.shuffle(lines)num_val = int(len(lines)*val_split)num_train = len(lines) - num_valprint('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))model.fit_generator(data_generator_wrap(lines[:num_train], batch_size, input_shape, anchors, num_classes),steps_per_epoch=max(1, num_train//batch_size),validation_data=data_generator_wrap(lines[num_train:], batch_size, input_shape, anchors, num_classes),validation_steps=max(1, num_val//batch_size),epochs=20,initial_epoch=0)model.save_weights(log_dir + 'trained_weights.h5')def get_classes(classes_path):with open(classes_path) as f:class_names = f.readlines()class_names = [c.strip() for c in class_names]return class_namesdef get_anchors(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 create_model(input_shape, anchors, num_classes, load_pretrained=False, freeze_body=False,weights_path='model_data/yolo_weights.h5'):K.clear_session() # get a new sessionimage_input = Input(shape=(None, None, 3))h, w = input_shapenum_anchors = len(anchors)y_true = [Input(shape=(h//{0:32, 1:16, 2:8}[l], w//{0:32, 1:16, 2:8}[l], \num_anchors//3, num_classes+5)) for l in range(3)]model_body = yolo_body(image_input, num_anchors//3, num_classes)print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))if load_pretrained:model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)print('Load weights {}.'.format(weights_path))if freeze_body:# Do not freeze 3 output layers.num = len(model_body.layers)-3for i in range(num): model_body.layers[i].trainable = Falseprint('Freeze the first {} layers of total {} layers.'.format(num, len(model_body.layers)))model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',arguments={'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})([*model_body.output, *y_true])model = Model([model_body.input, *y_true], model_loss)return model
def data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):n = len(annotation_lines)np.random.shuffle(annotation_lines)i = 0while True:image_data = []box_data = []for b in range(batch_size):i %= nimage, box = get_random_data(annotation_lines[i], input_shape, random=True)image_data.append(image)box_data.append(box)i += 1image_data = np.array(image_data)box_data = np.array(box_data)y_true = preprocess_true_boxes(box_data, input_shape, anchors, num_classes)yield [image_data, *y_true], np.zeros(batch_size)def data_generator_wrap(annotation_lines, batch_size, input_shape, anchors, num_classes):n = len(annotation_lines)if n==0 or batch_size<=0: return Nonereturn data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes)if __name__ == '__main__':_main()