广西民族大学高级人工智能课程—头歌实践教学实践平台-目标检测

代码文件

"""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 yolov3.utils import compose

# your code
K.clear_session()

@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):
    '''Darknet body having 52 Convolution2D layers'''
    x = DarknetConv2D_BN_Leaky(32, (3, 3))(x)
    x = resblock_body(x, 64, 1)

    # 添加缺失的两层 resn 层
    x = resblock_body(x, 128, 2)  # 第一层 resn 层，num_filters 为 128
    x = resblock_body(x, 256, 8)  # 第二层 resn 层，num_filters 为 256

    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)

    # 添加最后的两层
    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))

    # 添加中间层
    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))

    # 添加最后的层
    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])

# 其余代码保持不变

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_ &