【目标跟踪】Tensorflow环境下的deep_sort_yolov3代码实现

一、源码下载

源码下载：https://github.com/Qidian213/deep_sort_yolov3

该代码将下面的deep_sort与keras-yolo3相结合。项目中的demo虽然可以完美运行，但是更换成自己训练好的.h5模型就会报错，对比其中的yolo代码发现与keras-yolo3还是有一些不同，所以参照keras-yolo3对代码进行修改，以实现运行自己训练好的模型。
https://github.com/nwojke/deep_sort
https://github.com/qqwweee/keras-yolo3

下面是笔者的运行环境和安装的依赖，在版本下可成功运行。

运行环境

Window10
Cuda9.0
Python3.6
Pycharm + Anaconda

主要依赖

keras-gpu 2.24
tensorflow-gpu 1.12.0
opencv 3.3.1
pillow 6.2.1
numpy
scipy
pyyaml
sklearn

二、代码修改

下载yolo.h5后即可运行demo，通过笔记本自带摄像头实现对人（以及其他的物体）的识别与跟踪。

如果已经有训练好的.h5文件，则需要添加或修改以下文件。自己训练的.h5，自己定义的类，以及参照keras-yolo3对下面四个文件的修改。

model_data/yolo.h5
model_data/my_classes.txt
yolo3/model.py
yolo3/utils.py
yolo.py
yolov3.cfg

下面我们逐一尝试。

2.1 运行demo

可在YOLO网站下载yolo或tiny-yolo的权重。并通过python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5命令将YOLO模型转换为Keras模型。或则直接下载yolo.h5文件（被墙），并将其放入model_data目录下。

运行demo.py即可。

2.2 使用自己的h5

通过(【目标检测】YOLOv3目标检测使用自己的数据集详细流程）我已经训练出属于自己的模型，但是将其自己放入modal_data内，并修改yolo.py和yolov3.cfg的参数后运行demo.py报错。所以我依照keras-yolo3修改代码。

2.2.1 my_classes.txt

在model_data目录下创建my_classes.txt文件，并写入自己的分类。

2.2.2 model.py

修改yolo3目录下的model.py。

"""YOLO_v3 Model Defined in Keras."""

from functools import wraps

import numpy as np
import tensorflow as tf
from keras import backend as K
from keras.layers import Conv2D, Add, ZeroPadding2D, UpSampling2D, Concatenate, MaxPooling2D
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras.regularizers import l2

from yolo3.utils import compose


@wraps(Conv2D)
def DarknetConv2D(*args, **kwargs):
    """Wrapper to set Darknet parameters for Convolution2D."""
    darknet_conv_kwargs = {'kernel_regularizer': l2(5e-4)}
    darknet_conv_kwargs['padding'] = 'valid' if kwargs.get('strides')==(2,2) else 'same'
    darknet_conv_kwargs.update(kwargs)
    return Conv2D(*args, **darknet_conv_kwargs)

def DarknetConv2D_BN_Leaky(*args, **kwargs):
    """Darknet Convolution2D followed by BatchNormalization and LeakyReLU."""
    no_bias_kwargs = {'use_bias': False}
    no_bias_kwargs.update(kwargs)
    return compose(
        DarknetConv2D(*args, **no_bias_kwargs),
        BatchNormalization(),
        LeakyReLU(alpha=0.1))

def resblock_body(x, num_filters, num_blocks):
    '''A series of resblocks starting with a downsampling Convolution2D'''
    # Darknet uses left and top padding instead of 'same' mode
    x = ZeroPadding2D(((1,0),(1,0)))(x)
    x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
    for i in range(num_blocks):
        y = compose(
                DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
                DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
        x = Add()([x,y])
    return x

def darknet_body(x):
    '''Darknent body having 52 Convolution2D layers'''
    x = DarknetConv2D_BN_Leaky(32, (3,3))(x)
    x = resblock_body(x, 64, 1)
    x = resblock_body(x, 128, 2)
    x = resblock_body(x, 256, 8)
    x = resblock_body(x, 512, 8)
    x = resblock_body(x, 1024, 4)
    return x

def make_last_layers(x, num_filters, out_filters):
    '''6 Conv2D_BN_Leaky layers followed by a Conv2D_linear layer'''
    x = compose(
            DarknetConv2D_BN_Leaky(num_filters, (1,1)),
            DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
            DarknetConv2D_BN_Leaky(num_filters, (1,1)),
            DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
            DarknetConv2D_BN_Leaky(num_filters, (1,1)))(x)
    y = compose(
            DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
            DarknetConv2D(out_filters, (1,1)))(x)
    return x, y


def yolo_body(inputs, num_anchors, num_classes):
    """Create YOLO_V3 model CNN body in Keras."""
    darknet = Model(inputs, darknet_body(inputs))
    x, y1 = make_last_layers(darknet.output, 512, num_anchors*(num_classes+5))

    x = compose(
            DarknetConv2D_BN_Leaky(256, (1,1)),
            UpSampling2D(2))(x)
    x = Concatenate()([x,darknet.layers[152].output])
    x, y2 = make_last_layers(x, 256, num_anchors*(num_classes+5))

    x = compose(
            DarknetConv2D_BN_Leaky(128, (1,1)),
            UpSampling2D(2))(x)
    x = Concatenate()([x,darknet.layers[92].output])
    x, y3 = make_last_layers(x, 128, num_anchors*(num_classes+5))

    return Model(inputs, [y1,y2,y3])

def tiny_yolo_body(inputs, num_anchors, num_classes):
    '''Create Tiny YOLO_v3 model CNN body in keras.'''
    x1 = compose(
            DarknetConv2D_BN_Leaky(16, (3,3)),
            MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
            DarknetConv2D_BN_Leaky(32, (3,3)),
            MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
            DarknetConv2D_BN_Leaky(64, (3,3)),
            MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
            DarknetConv2D_BN_Leaky(128, (3,3)),
            MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
            DarknetConv2D_BN_Leaky(256, (3,3)))(inputs)
    x2 = compose(
            MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
            DarknetConv2D_BN_Leaky(512, (3,3)),
            MaxPooling2D(pool_size=(2,2), strides=(1,1), padding='same'),
            DarknetConv2D_BN_Leaky(1024, (3,3)),
            DarknetConv2D_BN_Leaky(256, (1,1)))(x1)
    y1 = compose(
            DarknetConv2D_BN_Leaky(512, (3,3)),
            DarknetConv2D(num_anchors*(num_classes+5), (1,1)))(x2)

    x2 = compose(
            DarknetConv2D_BN_Leaky(128, (1,1)),
            UpSampling2D(2))(x2)
    y2 = compose(
            Concatenate(),
            DarknetConv2D_BN_Leaky(256, (3,3)),
            DarknetConv2D(num_anchors*(num_classes+5), (1,1)))([x2,x1])

    return Model(inputs, [y1,y2])


def yolo_head(feats, anchors, num_classes, input_shape, calc_loss=False):
    """Convert final layer features to bounding box parameters."""
    num_anchors = len(anchors)
    # Reshape to batch, height, width, num_anchors, box_params.
    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    grid_shape = K.shape(feats)[1:3] # height, width
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])

    # Adjust preditions to each spatial grid point and anchor size.
    box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
    box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    if calc_loss == True:
        return grid, feats, box_xy, box_wh
    return box_xy, box_wh, box_confidence, box_class_probs


def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes


def yolo_boxes_and_scores(feats, anchors, num_classes, input_shape, image_shape):
    '''Process Conv layer output'''
    box_xy, box_wh, box_confidence, box_class_probs = yolo_head(feats,
        anchors, num_classes, input_shape)
    boxes = yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape)
    boxes = K.reshape(boxes, [-1, 4])
    box_scores = box_confidence * box_class_probs
    box_scores = K.reshape(box_scores, [-1, num_classes])
    return boxes, box_scores


def yolo_eval(yolo_outputs,
              anchors,
              num_classes,
              image_shape,
              max_boxes=20,
              score_threshold=.6,
              iou_threshold=.5):
    """Evaluate YOLO model on given input and return filtered boxes."""
    num_layers = len(yolo_outputs)
    anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]] # default setting
    input_shape = K.shape(yolo_outputs[0])[1:3] * 32
    boxes = []
    box_scores = []
    for l in range(num_layers):
        _boxes, _box_scores = yolo_boxes_and_scores(yolo_outputs[l],
            anchors[anchor_mask[l]], num_classes, input_shape, image_shape)
        boxes.append(_boxes)
        box_scores.append(_box_scores)
    boxes = K.concatenate(boxes, axis=0)
    box_scores = K.concatenate(box_scores, axis=0)

    mask = box_scores >= score_threshold
    max_boxes_tensor = K.constant(max_boxes, dtype='int32')
    boxes_ = []
    scores_ = []
    classes_ = []
    for c in range(num_classes):
        # TODO: use keras backend instead of tf.
        class_boxes = tf.boolean_mask(boxes, mask[:, c])
        class_box_scores = tf.boolean_mask(box_scores[:, c], mask[:, c])
        nms_index = tf.image.non_max_suppression(
            class_boxes, class_box_scores, max_boxes_tensor, iou_threshold=iou_threshold)
        class_boxes = K.gather(class_boxes, nms_index)
        class_box_scores = K.gather(class_box_scores, nms_index)
        classes = K.ones_like(class_box_scores, 'int32') * c
        boxes_.append(class_boxes)
        scores_.append(class_box_scores)
        classes_.append(classes)
    boxes_ = K.concatenate(boxes_, axis=0)
    scores_ = K.concatenate(scores_, axis=0)
    classes_ = K.concatenate(classes_, axis=0)

    return boxes_, scores_, classes_


def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
    '''Preprocess true boxes to training input format

    Parameters
    ----------
    true_boxes: array, shape=(m, T, 5)
        Absolute x_min, y_min, x_max, y_max, class_id relative to input_shape.
    input_shape: array-like, hw, multiples of 32
    anchors: array, shape=(N, 2), wh
    num_classes: integer

    Returns
    -------
    y_true: list of array, shape like yolo_outputs, xywh are reletive value

    '''
    assert (true_boxes[..., 4]<num_classes).all(), 'class id must be less than num_classes'
    num_layers = len(anchors)//3 # default setting
    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')
    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[::-1]
    true_boxes[..., 2:4] = boxes_wh/input_shape[::-1]

    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)]

    # Expand dim to apply broadcasting.
    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):
        # Discard zero rows.
        wh = boxes_wh[b, valid_mask[b]]
        if len(wh)==0: continue
        # Expand dim to apply broadcasting.
        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)

        # Find best anchor for each true box
        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


def box_iou(b1, b2):
    '''Return iou tensor

    Parameters
    ----------
    b1: tensor, shape=(i1,...,iN, 4), xywh
    b2: tensor, shape=(j, 4), xywh

    Returns
    -------
    iou: tensor, shape=(i1,...,iN, j)

    '''

    # Expand dim to apply broadcasting.
    b1 = K.expand_dims(b1, -2)
    b1_xy = b1[..., :2]
    b1_wh = b1[..., 2:4]
    b1_wh_half = b1_wh/2.
    b1_mins = b1_xy - b1_wh_half
    b1_maxes = b1_xy + b1_wh_half

    # Expand dim to apply broadcasting.
    b2 = K.expand_dims(b2, 0)
    b2_xy = b2[..., :2]
    b2_wh = b2[..., 2:4]
    b2_wh_half = b2_wh/2.
    b2_mins = b2_xy - b2_wh_half
    b2_maxes = b2_xy + b2_wh_half

    intersect_mins = K.maximum(b1_mins, b2_mins)
    intersect_maxes = K.minimum(b1_maxes, b2_maxes)
    intersect_wh = K.maximum(intersect_maxes - intersect_mins, 0.)
    intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
    b1_area = b1_wh[..., 0] * b1_wh[..., 1]
    b2_area = b2_wh[..., 0] * b2_wh[..., 1]
    iou = intersect_area / (b1_area + b2_area - intersect_area)

    return iou


def yolo_loss(args, anchors, num_classes, ignore_thresh=.5, print_loss=False):
    '''Return yolo_loss tensor

    Parameters
    ----------
    yolo_outputs: list of tensor, the output of yolo_body or tiny_yolo_body
    y_true: list of array, the output of preprocess_true_boxes
    anchors: array, shape=(N, 2), wh
    num_classes: integer
    ignore_thresh: float, the iou threshold whether to ignore object confidence loss

    Returns
    -------
    loss: tensor, shape=(1,)

    '''
    num_layers = len(anchors)//3 # default setting
    yolo_outputs = args[:num_layers]
    y_true = args[num_layers:]
    anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]
    input_shape = K.cast(K.shape(yolo_outputs[0])[1:3] * 32, K.dtype(y_true[0]))
    grid_shapes = [K.cast(K.shape(yolo_outputs[l])[1:3], K.dtype(y_true[0])) for l in range(num_layers)]
    loss = 0
    m = K.shape(yolo_outputs[0])[0] # batch size, tensor
    mf = K.cast(m, K.dtype(yolo_outputs[0]))

    for l in range(num_layers):
        object_mask = y_true[l][..., 4:5]
        true_class_probs = y_true[l][..., 5:]

        grid, raw_pred, pred_xy, pred_wh = yolo_head(yolo_outputs[l],
             anchors[anchor_mask[l]], num_classes, input_shape, calc_loss=True)
        pred_box = K.concatenate([pred_xy, pred_wh])

        # Darknet raw box to calculate loss.
        raw_true_xy = y_true[l][..., :2]*grid_shapes[l][::-1] - grid
        raw_true_wh = K.log(y_true[l][..., 2:4] / anchors[anchor_mask[l]] * input_shape[::-1])
        raw_true_wh = K.switch(object_mask, raw_true_wh, K.zeros_like(raw_true_wh)) # avoid log(0)=-inf
        box_loss_scale = 2 - y_true[l][...,2:3]*y_true[l][...,3:4]

        # Find ignore mask, iterate over each of batch.
        ignore_mask = tf.TensorArray(K.dtype(y_true[0]), size=1, dynamic_size=True)
        object_mask_bool = K.cast(object_mask, 'bool')
        def loop_body(b, ignore_mask):
            true_box = tf.boolean_mask(y_true[l][b,...,0:4], object_mask_bool[b,...,0])
            iou = box_iou(pred_box[b], true_box)
            best_iou = K.max(iou, axis=-1)
            ignore_mask = ignore_mask.write(b, K.cast(best_iou<ignore_thresh, K.dtype(true_box)))
            return b+1, ignore_mask
        _, ignore_mask = K.control_flow_ops.while_loop(lambda b,*args: b<m, loop_body, [0, ignore_mask])
        ignore_mask = ignore_mask.stack()
        ignore_mask = K.expand_dims(ignore_mask, -1)

        # K.binary_crossentropy is helpful to avoid exp overflow.
        xy_loss = object_mask * box_loss_scale * K.binary_crossentropy(raw_true_xy, raw_pred[...,0:2], from_logits=True)
        wh_loss = object_mask * box_loss_scale * 0.5 * K.square(raw_true_wh-raw_pred[...,2:4])
        confidence_loss = object_mask * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True)+ \
            (1-object_mask) * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True) * ignore_mask
        class_loss = object_mask * K.binary_crossentropy(true_class_probs, raw_pred[...,5:], from_logits=True)

        xy_loss = K.sum(xy_loss) / mf
        wh_loss = K.sum(wh_loss) / mf
        confidence_loss = K.sum(confidence_loss) / mf
        class_loss = K.sum(class_loss) / mf
        loss += xy_loss + wh_loss + confidence_loss + class_loss
        if print_loss:
            loss = tf.Print(loss, [loss, xy_loss, wh_loss, confidence_loss, class_loss, K.sum(ignore_mask)], message='loss: ')
    return loss

2.2.3 utils.py

修改yolo3目录下的utils.py。

"""Miscellaneous utility functions."""

from functools import reduce

from PIL import Image
import numpy as np
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb

def compose(*funcs):
    """Compose arbitrarily many functions, evaluated left to right.

    Reference: https://mathieularose.com/function-composition-in-python/
    """
    # return lambda x: reduce(lambda v, f: f(v), funcs, x)
    if funcs:
        return reduce(lambda f, g: lambda *a, **kw: g(f(*a, **kw)), funcs)
    else:
        raise ValueError('Composition of empty sequence not supported.')

def letterbox_image(image, size):
    '''resize image with unchanged aspect ratio using padding'''
    iw, ih = image.size
    w, h = size
    scale = min(w/iw, h/ih)
    nw = int(iw*scale)
    nh = int(ih*scale)

    image = image.resize((nw,nh), Image.BICUBIC)
    new_image = Image.new('RGB', size, (128,128,128))
    new_image.paste(image, ((w-nw)//2, (h-nh)//2))
    return new_image

def rand(a=0, b=1):
    return np.random.rand()*(b-a) + a

def get_random_data(annotation_line, input_shape, random=True, max_boxes=20, jitter=.3, hue=.1, sat=1.5, val=1.5, proc_img=True):
    '''random preprocessing for real-time data augmentation'''
    line = annotation_line.split()
    image = Image.open(line[0])
    iw, ih = image.size
    h, w = input_shape
    box = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])

    if not random:
        # resize image
        scale = min(w/iw, h/ih)
        nw = int(iw*scale)
        nh = int(ih*scale)
        dx = (w-nw)//2
        dy = (h-nh)//2
        image_data=0
        if proc_img:
            image = image.resize((nw,nh), Image.BICUBIC)
            new_image = Image.new('RGB', (w,h), (128,128,128))
            new_image.paste(image, (dx, dy))
            image_data = np.array(new_image)/255.

        # correct boxes
        box_data = np.zeros((max_boxes,5))
        if len(box)>0:
            np.random.shuffle(box)
            if len(box)>max_boxes: box = box[:max_boxes]
            box[:, [0,2]] = box[:, [0,2]]*scale + dx
            box[:, [1,3]] = box[:, [1,3]]*scale + dy
            box_data[:len(box)] = box

        return image_data, box_data

    # resize image
    new_ar = w/h * rand(1-jitter,1+jitter)/rand(1-jitter,1+jitter)
    scale = rand(.25, 2)
    if new_ar < 1:
        nh = int(scale*h)
        nw = int(nh*new_ar)
    else:
        nw = int(scale*w)
        nh = int(nw/new_ar)
    image = image.resize((nw,nh), Image.BICUBIC)

    # place image
    dx = int(rand(0, w-nw))
    dy = int(rand(0, h-nh))
    new_image = Image.new('RGB', (w,h), (128,128,128))
    new_image.paste(image, (dx, dy))
    image = new_image

    # flip image or not
    flip = rand()<.5
    if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)

    # distort image
    hue = rand(-hue, hue)
    sat = rand(1, sat) if rand()<.5 else 1/rand(1, sat)
    val = rand(1, val) if rand()<.5 else 1/rand(1, val)
    x = rgb_to_hsv(np.array(image)/255.)
    x[..., 0] += hue
    x[..., 0][x[..., 0]>1] -= 1
    x[..., 0][x[..., 0]<0] += 1
    x[..., 1] *= sat
    x[..., 2] *= val
    x[x>1] = 1
    x[x<0] = 0
    image_data = hsv_to_rgb(x) # numpy array, 0 to 1

    # correct boxes
    box_data = np.zeros((max_boxes,5))
    if len(box)>0:
        np.random.shuffle(box)
        box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
        box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
        if flip: box[:, [0,2]] = w - box[:, [2,0]]
        box[:, 0:2][box[:, 0:2]<0] = 0
        box[:, 2][box[:, 2]>w] = w
        box[:, 3][box[:, 3]>h] = h
        box_w = box[:, 2] - box[:, 0]
        box_h = box[:, 3] - box[:, 1]
        box = box[np.logical_and(box_w>1, box_h>1)] # discard invalid box
        if len(box)>max_boxes: box = box[:max_boxes]
        box_data[:len(box)] = box

    return image_data, box_data

2.2.4 yolo.py

按照下面代码对yolo.py修改后，还需要自己修改model_path、classes_path。

# -*- coding: utf-8 -*-


"""
Class definition of YOLO_v3 style detection model on image and video
"""

import colorsys
import os
import time
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/helmet_weights.h5',
        "anchors_path": 'model_data/yolo_anchors.txt',
        "classes_path": 'model_data/my_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.is_fixed_size = self.model_image_size != (None, None)

    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

        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_boxs(self, image):
        if self.is_fixed_size:
            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
            })
        return_boxs = []
        for i, c in reversed(list(enumerate(out_classes))):
            predicted_class = self.class_names[c]
            if predicted_class != 'person':
                continue
            box = out_boxes[i]
            # score = out_scores[i]
            x = int(box[1])
            y = int(box[0])
            w = int(box[3] - box[1])
            h = int(box[2] - box[0])
            if x < 0:
                w = w + x
                x = 0
            if y < 0:
                h = h + y
                y = 0
            return_boxs.append([x, y, w, h])

        return return_boxs

    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))        # 获得视频编码MPEG4/H264
    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)           # 从array转换成image
        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__':
#     image_path = "test/2.jpg"
#     image = Image.open(image_path)
#     yolo = YOLO()
#     r_image = yolo.detect_image(image=image)
#     r_image.show()


if __name__ == '__main__':
    video_path = "test/video3.mp4"
    yolo = YOLO()
    detect_video(yolo, video_path, "/test")

2.2.5 yolo3.cfg

打开yolo3.cfg，搜索yolo(共三处)，每次均按下图修改。

filters：3*(5+len(classes))

classes：训练的类别数

random：原来是1，显存小改为0

完成后，即可运行demo.py。