Python 以Keras为权重的自定义损失函数

Python 以Keras为权重的自定义损失函数,python,tensorflow,keras,neural-network,loss-function,Python,Tensorflow,Keras,Neural Network,Loss Function,我是神经网络新手。我想在TensorFlow中制作一个自定义损失函数,但我需要得到一个权重向量,所以我这样做: def my_loss(weights): def custom_loss(y, y_pred): return weights*(y - y_pred) return custom_loss model.compile(optimizer='adam', loss=my_loss(weights), metrics=['accuracy']) model.fit(x_

我是神经网络新手。我想在TensorFlow中制作一个自定义损失函数,但我需要得到一个权重向量,所以我这样做:

def my_loss(weights):
  def custom_loss(y, y_pred):
    return weights*(y - y_pred)
  return custom_loss
model.compile(optimizer='adam', loss=my_loss(weights), metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=None,  validation_data=(x_test, y_test), epochs=100)

启动时,我收到以下错误:

InvalidArgumentError:  Incompatible shapes: [50000,10] vs. [32,10]
这些形状是:

print(weights.shape)
print(y_train.shape)
所以我认为这是批处理的问题,我对TensorFlow没有很强的背景,所以我尝试用一个全局变量以一种简单的方式来解决

batch_index = 0
然后在自定义回调中将其更新到“on_batch_begin”钩子中。但它不起作用,这是一个可怕的解决方案。那么,我怎样才能得到相应y的权重的精确部分呢?我有办法在自定义损失中获取当前批次索引吗?
提前感谢您的帮助

Keras允许您从全局范围获取任何张量。实际上,
y_-true
y_-pred
甚至可能不被使用

您的模型可以有多个输入(您可以在推理时使此输入为虚拟输入,或者使用单个输入将权重加载到模型中)。请注意,您仍然需要它进行验证

import keras
from keras.layers import *
from keras import backend as K

import numpy as np

inputs_x = Input(shape=(10,))
inputs_w = Input(shape=(10,))

y = Dense(10,kernel_initializer='glorot_uniform' )(inputs_x)

model = keras.Model(inputs=[inputs_x, inputs_w], outputs=[y])

def my_loss(y_true, y_pred):
    return K.abs((y_true-y_pred)*inputs_w)

def my_metrics(y_true, y_pred):
    # just to output something
    return K.mean(inputs_w)



model.compile(optimizer='adam', loss=[my_loss], metrics=[my_metrics])

data = np.random.normal(size=(50000, 10))
labels = np.random.normal(size=(50000, 10))
weights = np.random.normal(size=(50000, 10))


model.fit([data, weights], labels, batch_size=256, validation_data=([data[:100], weights[:100]], labels[:100]), epochs=100)
要在不使用权重的情况下进行验证,需要编译具有不同损失的模型的另一个版本,该版本不使用权重

UPD:还要注意,如果Keras返回的是数组而不是标量,那么它将汇总所有损失元素


UPD:Tor tensorflow 2.1.0看起来事情变得更复杂了。前进的方向是@marco cerliani指出的方向(标签、重量和数据被输入模型,自定义损耗张量通过
.add_loss()
)添加),但是他的解决方案对我来说不是现成的。首先,模型不希望在没有损失的情况下工作,拒绝接受输入和输出。所以,我引入了额外的虚拟损失函数。第二个问题出现在数据集大小不能被批大小整除时。在keras和tf 1.x中,最后一批问题通常通过
每个历元的步骤
验证步骤
参数来解决,但在这里,如果历元2的第一批开始失败。所以我需要制作一个简单的自定义数据生成器

import tensorflow.keras as keras
from tensorflow.keras.layers import *
from tensorflow.keras import backend as K

import numpy as np

inputs_x = Input(shape=(10,))
inputs_w = Input(shape=(10,))
inputs_l = Input(shape=(10,))


y = Dense(10,kernel_initializer='glorot_uniform' )(inputs_x)

model = keras.Model(inputs=[inputs_x, inputs_w, inputs_l], outputs=[y])

def my_loss(y_true, y_pred):
    return K.abs((y_true-y_pred)*inputs_w)

def my_metrics():
    # just to output something
    return K.mean(inputs_w)

def dummy_loss(y_true, y_pred):
    return 0.


loss = my_loss(y, inputs_l)
metric = my_metrics()

model.add_loss(loss)
model.add_metric(metric, name='my_metric', aggregation='mean')


model.compile(optimizer='adam', loss=dummy_loss)

data = np.random.normal(size=(50000, 10))
labels = np.random.normal(size=(50000, 10))
weights = np.random.normal(size=(50000, 10))

dummy = np.zeros(shape=(50000, 10)) # or in can be labels, no matter now


# looks like it does not like when len(data) % batch_size != 0
# If I set steps_per_epoch, it fails on the second epoch.

# So, I proceded with data generator

class DataGenerator(keras.utils.Sequence):
    'Generates data for Keras'
    def __init__(self, x, w, y, y2, batch_size, shuffle=True):
        'Initialization'
        self.x = x
        self.w = w
        self.y = y
        self.y2 = y2
        self.indices = list(range(len(self.x)))
        self.shuffle = shuffle
        self.batch_size = batch_size
        self.on_epoch_end()

    def __len__(self):
        'Denotes the number of batches per epoch'
        return len(self.indices) // self.batch_size

    def __getitem__(self, index):
        'Generate one batch of data'
        # Generate indexes of the batch

        ids = self.indices[index*self.batch_size:(index+1)*self.batch_size]

        # the last None to remove weird warning
        # https://stackoverflow.com/questions/59317919
        return [self.x[ids], self.w[ids], self.y[ids]], self.y2[ids], [None]

    def on_epoch_end(self):
        'Updates indexes after each epoch'
        if self.shuffle == True:
            np.random.shuffle(self.indices)

batch_size = 256

train_generator = DataGenerator(data,weights,labels, dummy, batch_size=batch_size, shuffle=True)

val_generator = DataGenerator(data[:2*batch_size],weights[:2*batch_size],labels[:2*batch_size], dummy[:2*batch_size], batch_size=batch_size, shuffle=True)

model.fit(x=train_generator, validation_data=val_generator,epochs=100)

这是一种将附加参数传递给自定义损失函数(在您的示例中是一个权重数组)的变通方法。诀窍在于使用假输入,这有助于以正确的方式构建和使用损失。不要忘记keras处理固定的批处理维度

我提供了一个回归问题的虚拟示例

def mse(y_true, y_pred, weights):
    error = y_true-y_pred
    return K.mean(K.square(error) + K.sqrt(weights))

X = np.random.uniform(0,1, (1000,10))
y = np.random.uniform(0,1, 1000)
w = np.random.uniform(0,1, 1000)

inp = Input((10,))
true = Input((1,))
weights = Input((1,))
x = Dense(32, activation='relu')(inp)
out = Dense(1)(x)

m = Model([inp,true,weights], out)
m.add_loss( mse( true, out, weights ) )
m.compile(loss=None, optimizer='adam')
m.fit(x=[X, y, w], y=None, epochs=3)

## final fitted model to compute predictions (remove W if not needed)
final_m = Model(inp, out)

我必须把它应用到CNN上,但它不起作用。这个解决方案似乎正是我所需要的,但我花了数小时试图让它发挥作用,但没有成功。我还在这个笔记本上做了一个玩具问题,只是为了有个想法。非常感谢你@Marccerliani,我不想滥用你的耐心
def mse(y_true, y_pred, weights):
    error = y_true-y_pred
    return K.mean(K.square(error) + K.sqrt(weights))

X = np.random.uniform(0,1, (1000,10))
y = np.random.uniform(0,1, 1000)
w = np.random.uniform(0,1, 1000)

inp = Input((10,))
true = Input((1,))
weights = Input((1,))
x = Dense(32, activation='relu')(inp)
out = Dense(1)(x)

m = Model([inp,true,weights], out)
m.add_loss( mse( true, out, weights ) )
m.compile(loss=None, optimizer='adam')
m.fit(x=[X, y, w], y=None, epochs=3)

## final fitted model to compute predictions (remove W if not needed)
final_m = Model(inp, out)