python - 为 Keras 制作自定义损失函数
问题描述
我将实现本文中解释的焦点损失的自定义 Keras 损失函数;但是,我必须得到可训练层的权重。那么,有没有什么方法可以在损失函数内部读取训练过程中层的权重呢?
def focal_coef(model, y_true, y_pred, content, label_remap, gamma_focal=2, w_d=1e-4):
w = np.empty(len(content))
f = np.empty(len(content))
for key in content:
e = 0.001
f_c = content[key]
f[label_remap[key]] = f_c
w[label_remap[key]] = 1 / (f_c + e)
median_freq = np.median(f)
print("\nFrequencies of classes:\n", f)
print("\nMedian freq:\n", median_freq)
print("\nWeights for loss function (1/frec(c)):\n", w)
w = median_freq * w
print("\nWeights for loss function (median frec/frec(c)):\n", w)
w_mask = w.astype(np.bool).astype(np.float32)
print("w_mask", w_mask)
softmax = k.softmax(y_pred)
softmax_mat = k.reshape(softmax, (-1, len(content)))
zerohot_softmax_mat = 1 - softmax_mat
# make the labels one-hot for the cross-entropy
print("datatype", y_true.type)
onehot_mat = k.reshape(k.one_hot(y_true, len(content)),
(-1, len(content)))
# make the zero hot to punish the false negatives, but ignore the
# zero-weight classes
masked_sum = k.reduce_sum(onehot_mat * w_mask, axis=1)
zeros = onehot_mat * 0.0
zerohot_mat = k.where(k.less(masked_sum, 1e-5),
x=zeros,
y=1 - onehot_mat)
# focal loss p and gamma
loss_epsilon = 1e-10
gamma = np.full(onehot_mat.get_shape().as_list(), fill_value=gamma_focal)
gamma_tf = k.constant(gamma, dtype=k.float32)
focal_softmax = k.pow(1 - softmax_mat, gamma_tf) * \
k.log(softmax_mat + loss_epsilon)
zerohot_focal_softmax = k.pow(1 - zerohot_softmax_mat, gamma_tf) * \
k.log(zerohot_softmax_mat + loss_epsilon)
# calculate xentropy
cross_entropy = - k.reduce_sum(k.multiply(focal_softmax * onehot_mat +
zerohot_focal_softmax * zerohot_mat, w),
axis=[1])
loss = k.reduce_mean(cross_entropy, name='xentropy_mean')
for layer in model.layers:
if layer.trainable == True:
loss += w_d * (k.sum(layer ** 2) / 2)
return loss
def focal_loss(model, content, label_remap, gamma_focal=2, w_d=1e-4):
def focal(y_true, y_pred):
return -focal_coef(model, y_true, y_pred, content, label_remap, gamma_focal, w_d)
return focal
解决方案
您的自定义损失函数必须有两个参数,它们是 y_true 和 y_pred,如果您想要更多参数,您可以在损失函数内部调用一个函数来获取参数,因为您需要来自层的权重,您的自定义损失函数必须可以访问您的模型
model = ...
def custom_loss(y_true, y_pred):
w1 = model.get_layers[0].get_weights()[0] # weights of the first layer
b1 = model.get_layers[0].get_weights()[1] # bias of the first layer
w2 = model.get_layers[1].get_weights()[0] # weights of the second layer
.
.
.
loss = ...
return loss
model.compile(loss=custom_loss, optimizer = ...)
model.fit(...)
如果你想要所有的重量,你可以做model.get_weights()
推荐阅读
- jquery - 无法弄清楚如何获得此功能来仅更改与我单击的图像相关联的标题。总是更改所有标题
- javascript - jQuery 样式表不会加载
- c# - 为什么 TcpClient.Connected() 被 TcpListener 关闭后显示为 true?F#
- haskell - Haskell Lambda 案例或
- java - 为什么 xerces 向我显示“org.xml.sax.SAXParseException:发现以元素开头的无效内容”?
- php - php - 错误文本:字段列表中的未知列“”
- c - 带有 stdcall 的 MinGW 自定义导出函数名称
- spring-boot - 带有 SpringBoot RestController 的 MediaTypeNotAcceptable
- python - 未记录模拟对象的初始化
- bash - XARGS 长参数和命令之间的暂停