输出结果
设计思路
更新中
核心代码
def __create_pyramid_features(C3, C4, C5, feature_size=256):
""" Creates the FPN layers on top of the backbone features.
在ResNet基础上创建FPN金字塔特征：参照博客的框架图，输入[C3,C4,C5]，返回5个特征级别[P3, P4, P5, P6, P7]
参考博客：https://yunyaniu.blog.csdn.net/article/details/100010853
Args
C3 : Feature stage C3 from the backbone.
C4 : Feature stage C4 from the backbone.
C5 : Feature stage C5 from the backbone.
feature_size : The feature size to use for the resulting feature levels.
Returns
A list of feature levels [P3, P4, P5, P6, P7].
"""
# upsample C5 to get P5 from the FPN paper
P5 = keras.layers.Conv2D(feature_size, kernel_size=1, strides=1, padding='same', name='C5_reduced')(C5)
P5_upsampled = layers.UpsampleLike(name='P5_upsampled')([P5, C4])
P5 = keras.layers.Conv2D(feature_size, kernel_size=3, strides=1, padding='same', name='P5')(P5)
# add P5 elementwise to C4
P4 = keras.layers.Conv2D(feature_size, kernel_size=1, strides=1, padding='same', name='C4_reduced')(C4)
P4 = keras.layers.Add(name='P4_merged')([P5_upsampled, P4])
P4_upsampled = layers.UpsampleLike(name='P4_upsampled')([P4, C3])
P4 = keras.layers.Conv2D(feature_size, kernel_size=3, strides=1, padding='same', name='P4')(P4)
# add P4 elementwise to C3
P3 = keras.layers.Conv2D(feature_size, kernel_size=1, strides=1, padding='same', name='C3_reduced')(C3)
P3 = keras.layers.Add(name='P3_merged')([P4_upsampled, P3])
P3 = keras.layers.Conv2D(feature_size, kernel_size=3, strides=1, padding='same', name='P3')(P3)
# "P6 is obtained via a 3x3 stride-2 conv on C5"
P6 = keras.layers.Conv2D(feature_size, kernel_size=3, strides=2, padding='same', name='P6')(C5)
# "P7 is computed by applying ReLU followed by a 3x3 stride-2 conv on P6"
P7 = keras.layers.Activation('relu', name='C6_relu')(P6)
P7 = keras.layers.Conv2D(feature_size, kernel_size=3, strides=2, padding='same', name='P7')(P7)
return [P3, P4, P5, P6, P7]
def default_submodels(num_classes, num_anchors):
""" Create a list of default submodels used for object detection.
两个子模型：目标分类子模型default_classification_model、框回归子模型default_regression_model
The default submodels contains a regression submodel and a classification submodel.
Args
num_classes : Number of classes to use.
num_anchors : Number of base anchors.
Returns
A list of tuple, where the first element is the name of the submodel and the second element is the submodel itself.
"""
return [
('regression', default_regression_model(4, num_anchors)),
('classification', default_classification_model(num_classes, num_anchors))
]
def __build_model_pyramid(name, model, features):
""" Applies a single submodel to each FPN level.
真正的构造金字塔模型
Args
name : Name of the submodel.
model : The submodel to evaluate.
features : The FPN features.
Returns
A tensor containing the response from the submodel on the FPN features.
"""
return keras.layers.Concatenate(axis=1, name=name)([model(f) for f in features])
"""
The default anchor parameters. 默认的anchors参数，组合以后有9个anchors
"""
AnchorParameters.default = AnchorParameters(
sizes = [32, 64, 128, 256, 512],
strides = [8, 16, 32, 64, 128],
ratios = np.array([0.5, 1, 2], keras.backend.floatx()),
scales = np.array([2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)], keras.backend.floatx()),
)
def anchor_targets_bbox(
anchors,
image_group,
annotations_group,
num_classes,
#negative_overlap和positive_overlap，根据IOU区分
negative_overlap=0.4,
positive_overlap=0.5
):
def focal(alpha=0.25, gamma=2.0):
""" Create a functor for computing the focal loss.
Args
alpha: Scale the focal weight with alpha.
gamma: Take the power of the focal weight with gamma.
Returns
A functor that computes the focal loss using the alpha and gamma.
"""
def _focal(y_true, y_pred):
""" Compute the focal loss given the target tensor and the predicted tensor.
As defined in https://arxiv.org/abs/1708.02002
Args
y_true: Tensor of target data from the generator with shape (B, N, num_classes).
y_pred: Tensor of predicted data from the network with shape (B, N, num_classes).
Returns
The focal loss of y_pred w.r.t. y_true.
"""
labels = y_true[:, :, :-1]
anchor_state = y_true[:, :, -1] # -1 for ignore, 0 for background, 1 for object
classification = y_pred
# filter out "ignore" anchors
indices = backend.where(keras.backend.not_equal(anchor_state, -1))
labels = backend.gather_nd(labels, indices)
classification = backend.gather_nd(classification, indices)
# compute the focal loss
alpha_factor = keras.backend.ones_like(labels) * alpha
alpha_factor = backend.where(keras.backend.equal(labels, 1), alpha_factor, 1 - alpha_factor)
focal_weight = backend.where(keras.backend.equal(labels, 1), 1 - classification, classification)
focal_weight = alpha_factor * focal_weight ** gamma
#定义分类损失： 权重*原来的交叉熵损失
cls_loss = focal_weight * keras.backend.binary_crossentropy(labels, classification)
# compute the normalizer: the number of positive anchors
normalizer = backend.where(keras.backend.equal(anchor_state, 1))
normalizer = keras.backend.cast(keras.backend.shape(normalizer)[0], keras.backend.floatx())
normalizer = keras.backend.maximum(keras.backend.cast_to_floatx(1.0), normalizer)
return keras.backend.sum(cls_loss) / normalizer
return _focal
def smooth_l1(sigma=3.0): #框回归损失采用smooth_l1函数
""" Create a smooth L1 loss functor.
Args
sigma: This argument defines the point where the loss changes from L2 to L1.
Returns
A functor for computing the smooth L1 loss given target data and predicted data.
"""
sigma_squared = sigma ** 2
def _smooth_l1(y_true, y_pred):
""" Compute the smooth L1 loss of y_pred w.r.t. y_true.
Args
y_true: Tensor from the generator of shape (B, N, 5). The last value for each box is the state of the anchor (ignore, negative, positive).
y_pred: Tensor from the network of shape (B, N, 4).
Returns
The smooth L1 loss of y_pred w.r.t. y_true.
"""
# separate target and state
regression = y_pred
regression_target = y_true[:, :, :-1]
anchor_state = y_true[:, :, -1]
# filter out "ignore" anchors
indices = backend.where(keras.backend.equal(anchor_state, 1))
regression = backend.gather_nd(regression, indices)
regression_target = backend.gather_nd(regression_target, indices)
# compute smooth L1 loss
# f(x) = 0.5 * (sigma * x)^2 if |x| < 1 / sigma / sigma
# |x| - 0.5 / sigma / sigma otherwise
regression_diff = regression - regression_target
regression_diff = keras.backend.abs(regression_diff)
regression_loss = backend.where(
keras.backend.less(regression_diff, 1.0 / sigma_squared),
0.5 * sigma_squared * keras.backend.pow(regression_diff, 2),
regression_diff - 0.5 / sigma_squared
)
# compute the normalizer: the number of positive anchors
normalizer = keras.backend.maximum(1, keras.backend.shape(indices)[0])
normalizer = keras.backend.cast(normalizer, dtype=keras.backend.floatx())
return keras.backend.sum(regression_loss) / normalizer
return _smooth_l1
