Yolov3训练教程Keras

本是古典何须时尚 2022-11-13 15:28 262阅读 0赞

欢迎关注的公众号：  
不定期发布各类教程、理论笔记、搬运前沿动态。  
![在这里插入图片描述][20210327164231139.png]

环境搭建教程在上一篇博客[Keras yolov3环境搭建][Keras yolov3]  
1、打开文件夹  
用 pycharm 打开 keras-yolo3 文件夹打开的文件夹应该是这样的：![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70]2、新建voc2007数据集（存放自己的图片及标注信息）  
新建的文件夹（ImageSets 文件夹下还有个名为 Main 的小文件夹自己创建吧没截图）如下：  
![在这里插入图片描述][20210327162807584.png]![在这里插入图片描述][20210327162801881.png]  
3、将要训练的图片放在 JPEGImages 里面：  
labelimg 标注的 xlm 文件放在 Annotations 里面  
![在这里插入图片描述][20210327162904721.png]  
4、在 VOC2007 里新建一个 py 文件，在此取名 voc.py  
![在这里插入图片描述][20210327162930842.png]  
VOC中的代码如下：

import os
    import random
    
    trainval_percent = 0.2 #测试集占0.2
    train_percent = 0.8    #训练集占0.8
    xmlfilepath = 'Annotations'
    txtsavepath = 'ImageSets\Main'
    total_xml = os.listdir(xmlfilepath)
    
    num = len(total_xml)
    list = range(num)
    tv = int(num * trainval_percent)
    tr = int(tv * train_percent)
    trainval = random.sample(list, tv)
    train = random.sample(trainval, tr)
    
    ftrainval = open('ImageSets/Main/trainval.txt', 'w')
    ftest = open('ImageSets/Main/test.txt', 'w')
    ftrain = open('ImageSets/Main/train.txt', 'w')
    fval = open('ImageSets/Main/val.txt', 'w')
    
    for i in list:
        name = total_xml[i][:-4] + '\n'
        if i in trainval:
            ftrainval.write(name)
            if i in train:
                ftest.write(name)
            else:
                fval.write(name)
        else:
            ftrain.write(name)
    
    ftrainval.close()
    ftrain.close()
    fval.close()
    ftest.close()

直接复制以上代码即可，然后运行 voc.py 文件  
运行后会在mian 文件夹里会多了四个 txt 文件  
![在这里插入图片描述][20210327163300236.png]  
5、修改 voc\_annotation.py 文件并运行  
更改这里的 classes 的数量，你voc2007里标注了哪几种，你就留哪几种就行  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 1]  
比如voc中只标注将 coco\_classes.txt 和 voc\_classes.txt 中也只留下VOC2007 中所标注的那个类型rson”，那只留下“person”，然后再运行一下就行，运行完成后会多出这几个 txt 文件  
![在这里插入图片描述][20210327163400874.png]  
6、修改 model\_data  
将 coco\_classes.txt 和 voc\_classes.txt 中也只留下VOC2007 中所标注的那个类型![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 2]比如标注的只有 “person”  
那只留下“person”  
![在这里插入图片描述][2021032716343796.png]![在这里插入图片描述][20210327163443998.png]  
7、修改 yolo3.cfg  
大概在 610、696 和 783 行的位置，把 classes 的数值都改为 1  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 3]![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 4]  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 5]  
8、添加官方权重  
将 yolo.h5 改名为 yolo\_weights.h5  
![在这里插入图片描述][20210327163559566.png]![在这里插入图片描述][20210327163613438.png]

9、新建 logs 文件夹存放训练的权重文件。![在这里插入图片描述][20210327163623295.png]

10、开始训练  
在 keras-yolo3-master 文件夹下新建 一个名为 trainyolo.py 的文件  
trainyolo代码如下：

import numpy as np
    import tensorflow as tf
    import keras.backend as K
    from keras.layers import Input, Lambda
    from keras.models import Model
    from keras.optimizers import Adam
    from keras.callbacks import TensorBoard, ModelCheckpoint, ReduceLROnPlateau, EarlyStopping
    from yolo3.model import yolo_body
    from yolo3.model import yolo_loss
    from keras.backend.tensorflow_backend import set_session
    from yolo3.utils import get_random_data
    
    def get_classes(classes_path):
        '''loads the classes'''
        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(anchors_path):
        '''loads the anchors from a file'''
        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 data_generator(annotation_lines, batch_size, input_shape, anchors, num_classes):
        '''data generator for fit_generator'''
        n = len(annotation_lines)
        i = 0
        while True:
            image_data = []
            box_data = []
            for b in range(batch_size):
                if i==0:
                    np.random.shuffle(annotation_lines)
                image, box = get_random_data(annotation_lines[i], input_shape, random=True)
                image_data.append(image)
                box_data.append(box)
                i = (i+1) % n
            image_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 preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
    
        assert (true_boxes[..., 4]<num_classes).all(), 'class id must be less than num_classes'
        
        num_layers = len(anchors)//3 
        anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]
    
        true_boxes = np.array(true_boxes, dtype='float32')
        input_shape = np.array(input_shape, dtype='int32') # 416,416
        boxes_xy = (true_boxes[..., 0:2] + true_boxes[..., 2:4]) // 2
        boxes_wh = true_boxes[..., 2:4] - true_boxes[..., 0:2]
        true_boxes[..., 0:2] = boxes_xy/input_shape[:]
        true_boxes[..., 2:4] = boxes_wh/input_shape[:]
    
        m = true_boxes.shape[0]
        grid_shapes = [input_shape//{ 0:32, 1:16, 2:8}[l] for l in range(num_layers)]
        y_true = [np.zeros((m,grid_shapes[l][0],grid_shapes[l][1],len(anchor_mask[l]),5+num_classes),
            dtype='float32') for l in range(num_layers)]
        anchors = np.expand_dims(anchors, 0)
        anchor_maxes = anchors / 2.
        anchor_mins = -anchor_maxes
        valid_mask = boxes_wh[..., 0]>0
    
        for b in range(m):
            wh = boxes_wh[b, valid_mask[b]]
            if len(wh)==0: continue
            wh = np.expand_dims(wh, -2)
            box_maxes = wh / 2.
            box_mins = -box_maxes
    
            intersect_mins = np.maximum(box_mins, anchor_mins)
            intersect_maxes = np.minimum(box_maxes, anchor_maxes)
            intersect_wh = np.maximum(intersect_maxes - intersect_mins, 0.)
            intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
            box_area = wh[..., 0] * wh[..., 1]
            anchor_area = anchors[..., 0] * anchors[..., 1]
            iou = intersect_area / (box_area + anchor_area - intersect_area)
            best_anchor = np.argmax(iou, axis=-1)
    
            for t, n in enumerate(best_anchor):
                for l in range(num_layers):
                    if n in anchor_mask[l]:
                        i = np.floor(true_boxes[b,t,0]*grid_shapes[l][1]).astype('int32')
                        j = np.floor(true_boxes[b,t,1]*grid_shapes[l][0]).astype('int32')
                        k = anchor_mask[l].index(n)
                        c = true_boxes[b,t, 4].astype('int32')
                        y_true[l][b, j, i, k, 0:4] = true_boxes[b,t, 0:4]
                        y_true[l][b, j, i, k, 4] = 1
                        y_true[l][b, j, i, k, 5+c] = 1
    
        return y_true
    
    
    config = tf.ConfigProto()
    config.gpu_options.allocator_type = 'BFC'
    config.gpu_options.per_process_gpu_memory_fraction = 0.7
    config.gpu_options.allow_growth = True
    set_session(tf.Session(config=config)) 
    
    if __name__ == "__main__":
        annotation_path = '2007_train.txt'
        classes_path = 'model_data/voc_classes.txt'    
        anchors_path = 'model_data/yolo_anchors.txt'
        weights_path = 'model_data/yolo_weights.h5'
        class_names = get_classes(classes_path)
        anchors = get_anchors(anchors_path)
        num_classes = len(class_names)
        num_anchors = len(anchors)
        log_dir = 'logs/'
        input_shape = (416,416)
    
        K.clear_session()
    
        image_input = Input(shape=(None, None, 3))
        h, w = input_shape
    
        print('Create YOLOv3 model with {} anchors and {} classes.'.format(num_anchors, num_classes))
        model_body = yolo_body(image_input, num_anchors//3, num_classes)
        
        print('Load weights {}.'.format(weights_path))
        model_body.load_weights(weights_path, by_name=True, skip_mismatch=True)
        
        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)]
    
        loss_input = [*model_body.output, *y_true]
        model_loss = Lambda(yolo_loss, output_shape=(1,), name='yolo_loss',
            arguments={ 'anchors': anchors, 'num_classes': num_classes, 'ignore_thresh': 0.5})(loss_input)
    
        model = Model([model_body.input, *y_true], model_loss)
    
        freeze_layers = 249
        for i in range(freeze_layers): model_body.layers[i].trainable = False
        print('Freeze the first {} layers of total {} layers.'.format(freeze_layers, len(model_body.layers)))
    
        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=False, period=2)
        reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=2, verbose=1)
        early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=6, verbose=1)
    
        val_split = 0.2
        with open(annotation_path) as f:
            lines = f.readlines()
        np.random.seed(10101)
        np.random.shuffle(lines)
        np.random.seed(None)
        num_val = int(len(lines)*val_split)
        num_train = len(lines) - num_val
        
        if True:
            model.compile(optimizer=Adam(lr=1e-3), loss={ 
                'yolo_loss': lambda y_true, y_pred: y_pred})
    
            batch_size = 1
            print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
            model.fit_generator(data_generator(lines[:num_train], batch_size, input_shape, anchors, num_classes),
                    steps_per_epoch=max(1, num_train//batch_size),
                    validation_data=data_generator(lines[num_train:], batch_size, input_shape, anchors, num_classes),
                    validation_steps=max(1, num_val//batch_size),
                    epochs=50,
                    initial_epoch=0,
                    callbacks=[logging, checkpoint])
            model.save_weights(log_dir + 'trained_weights_stage_1.h5')
    
        for i in range(freeze_layers): model_body.layers[i].trainable = True
    
        if True:
            model.compile(optimizer=Adam(lr=1e-4), loss={ 
                'yolo_loss': lambda y_true, y_pred: y_pred})
    
            batch_size = 1
            print('Train on {} samples, val on {} samples, with batch size {}.'.format(num_train, num_val, batch_size))
            model.fit_generator(data_generator(lines[:num_train], batch_size, input_shape, anchors, num_classes),
                    steps_per_epoch=max(1, num_train//batch_size),
                    validation_data=data_generator(lines[num_train:], batch_size, input_shape, anchors, num_classes),
                    validation_steps=max(1, num_val//batch_size),
                    epochs=100,
                    initial_epoch=50,
                    callbacks=[logging, checkpoint])
            model.save_weights(log_dir + 'last1.h5')

11、然后运行trainyolo.py 的代码  
开始训练了。![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 6]  
当出现下图所示，训练完成  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 7]  
训练好的权重都放在 logs 文件夹下的 000 文件夹里：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 8]  
这两个权重文件都可以用一样的  
![在这里插入图片描述][20210327163927398.png]  
然后和之前一样加载权重，识别照片就可以了！

[20210327164231139.png]: /images/20221022/21ff613f917b47509390046719175d1e.png
[Keras yolov3]: https://blog.csdn.net/weixin_41967600/article/details/107753260
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70]: /images/20221022/88dc9ecef3004de2a3d3190bd5fb7f42.png
[20210327162807584.png]: https://img-blog.csdnimg.cn/20210327162807584.png
[20210327162801881.png]: /images/20221022/35a47c3755544bb9bf8b2687e8d94c6f.png
[20210327162904721.png]: /images/20221022/592511e9143a4561a1f77eda67d8eccc.png
[20210327162930842.png]: /images/20221022/185a72e4894743a09747aa48523df4ec.png
[20210327163300236.png]: /images/20221022/a20bed9017464b728da72f58390f0611.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 1]: /images/20221022/e093dd5631c741ca8db28b6f40ebe718.png
[20210327163400874.png]: https://img-blog.csdnimg.cn/20210327163400874.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 2]: https://img-blog.csdnimg.cn/20210327163415354.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA==,size_16,color_FFFFFF,t_70
[2021032716343796.png]: https://img-blog.csdnimg.cn/2021032716343796.png
[20210327163443998.png]: https://img-blog.csdnimg.cn/20210327163443998.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 3]: https://img-blog.csdnimg.cn/20210327163500295.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 4]: https://img-blog.csdnimg.cn/20210327163536548.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 5]: https://img-blog.csdnimg.cn/20210327163549903.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA==,size_16,color_FFFFFF,t_70
[20210327163559566.png]: https://img-blog.csdnimg.cn/20210327163559566.png
[20210327163613438.png]: https://img-blog.csdnimg.cn/20210327163613438.png
[20210327163623295.png]: https://img-blog.csdnimg.cn/20210327163623295.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 6]: https://img-blog.csdnimg.cn/20210327163812854.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 7]: https://img-blog.csdnimg.cn/20210327163859684.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA==,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA_size_16_color_FFFFFF_t_70 8]: https://img-blog.csdnimg.cn/20210327163911430.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MTk2NzYwMA==,size_16,color_FFFFFF,t_70
[20210327163927398.png]: https://img-blog.csdnimg.cn/20210327163927398.png