from keras import backend as K

from keras.layers.core import Lambda

def sub_mean(x):
    x -= K.mean(x,axis=1,keepdims=True)
    return x
model.add( Lambda(sub_mean,output_shape=lambda input_shape:input_shape ))

def get_submean_model():
    model = Sequential()
    model.add(Dense(5,input_dim=7))
    def sub_mean(x):
        x -= K.mean(x,axis=1,keepdims=True)
        return x
    model.add( Lambda(sub_mean,output_shape=lambda input_shape:input_shape))
    model.compile(optimizer='rmsprop',loss='mse')
    return model
model = get_submean_model()
res=model.predict(np.random.random((3,7)))

from keras.engine.topology import Layer

class MyLayer(Layer):
    def __init__(self,output_dim,**kw):
        self.output_dim = output_dim
        super(MyLayer,self).__init__(**kw)
    def build(self,input_shape):
        input_dim = input_shape[1]
        assert(input_dim == self.output_dim)
        inital_SCALER = np.ones((input_dim,))*1000
        self.SCALER = K.variable(inital_SCALER)
        self.trainable_weights = [self.SCALER]
        super(MyLayer,self).build(input_shape)
    def call(self,x,mask=None):
        #return x - K.mean(x,axis=1,keepdims=True)
        x *= self.SCALER
        return x
    def get_output_shape_for(self,input_shape):
        return input_shape

def get_mylayer_model():
    model = Sequential()
    model.add(Dense(5,input_dim=7))
    model.add(MyLayer(5))
    model.compile(optimizer='rmsprop',loss='mse')
    return model
model = get_mylayer_model()
res=model.predict(np.random.random((3,7)))
print res

def mean_squared_error(y_true, y_pred):
    return K.mean(K.square(y_pred - y_true), axis=-1)

def my_object(y_true,y_pred):
    return K.mean(K.square(K.square(y_pred-y_true)),axis=-1)

def get_myobj_model():
    model = Sequential()
    model.add(Dense(5,input_dim=7))
    model.add(Dense(3))
    def my_object(y_true,y_pred):
        return K.mean(K.square(K.square(y_pred-y_true)),axis=-1)
    model.compile(optimizer='sgd',loss=my_object)
    return model
model = get_myobj_model()

rom keras.layers.recurrent import LSTM,Recurrent,time_distributed_dense
from keras import initializations,regularizers,activations
from keras.engine import InputSpec

# 標(biāo)準(zhǔn)化層
class InstanceNormalize(Layer):
    def __init__(self, **kwargs):
        super(InstanceNormalize, self).__init__(**kwargs)
        self.epsilon = 1e-3
            
    def call(self, x, mask=None):
        mean, var = tf.nn.moments(x, [1, 2], keep_dims=True)
        return tf.div(tf.subtract(x, mean), tf.sqrt(tf.add(var, self.epsilon)))
                                                 
    def compute_output_shape(self,input_shape):
        return input_shape
# 調(diào)用
inputs = keras.Input(shape=(None, None, 3))
x = InstanceNormalize()(inputs)

# 可以通過(guò)add_weight() 創(chuàng)建權(quán)重
class SimpleDense(Layer):
  def __init__(self, units=32):
      super(SimpleDense, self).__init__()
      self.units = units
  def build(self, input_shape):
      self.w = self.add_weight(shape=(input_shape[-1], self.units),
                               initializer='random_normal',
                               trainable=True)
      self.b = self.add_weight(shape=(self.units,),
                               initializer='random_normal',
                               trainable=True)
  def call(self, inputs):
      return tf.matmul(inputs, self.w) + self.b
# 調(diào)用
inputs = keras.Input(shape=(None, None, 3))
x = SimpleDense(units=64)(inputs)

from keras.models import Sequential
from keras.layers import Dense, Activation
model = Sequential()
model.add(Dense(units=64, input_dim=100))
model.add(Activation("relu"))
model.add(Dense(units=10))
model.add(Activation("softmax"))
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5, batch_size=32)

class CustomModel(keras.Model):
    def train_step(self, data):
        # Unpack the data. Its structure depends on your model and
        # on what you pass to `fit()`.
        x, y = data
        with tf.GradientTape() as tape:
            y_pred = self(x, training=True)  # Forward pass
            # Compute the loss value
            # (the loss function is configured in `compile()`)
            loss = self.compiled_loss(y, y_pred, regularization_losses=self.losses)
        # Compute gradients
        trainable_vars = self.trainable_variables
        gradients = tape.gradient(loss, trainable_vars)
        # Update weights
        self.optimizer.apply_gradients(zip(gradients, trainable_vars))
        # Update metrics (includes the metric that tracks the loss)
        self.compiled_metrics.update_state(y, y_pred)
        # Return a dict mapping metric names to current value
        return {m.name: m.result() for m in self.metrics}
import numpy as np
# Construct and compile an instance of CustomModel
inputs = keras.Input(shape=(32,))
outputs = keras.layers.Dense(1)(inputs)
model = CustomModel(inputs, outputs)
model.compile(optimizer="adam", loss="mse", metrics=["mae"])
# Just use `fit` as usual
x = np.random.random((1000, 32))
y = np.random.random((1000, 1))
model.fit(x, y, epochs=3)

def categorical_crossentropy(y_true, y_pred):
    return K.categorical_crossentropy(y_true, y_pred)
def mean_squared_error(y_true, y_pred):
    return K.mean(K.square(y_pred - y_true), axis=-1)

def focal_loss(weights=None, alpha=0.25, gamma=2):
    r"""Compute focal loss for predictions.
        Multi-labels Focal loss formula:
            FL = -alpha * (z-p)^gamma * log(p) -(1-alpha) * p^gamma * log(1-p)
                 ,which alpha = 0.25, gamma = 2, p = sigmoid(x), z = target_tensor.
    # https://github.com/ailias/Focal-Loss-implement-on-Tensorflow/blob/master/focal_loss.py
    Args:
     prediction_tensor: A float tensor of shape [batch_size, num_anchors,
        num_classes] representing the predicted logits for each class
     target_tensor: A float tensor of shape [batch_size, num_anchors,
        num_classes] representing one-hot encoded classification targets
     weights: A float tensor of shape [batch_size, num_anchors]
     alpha: A scalar tensor for focal loss alpha hyper-parameter
     gamma: A scalar tensor for focal loss gamma hyper-parameter
    Returns:
        loss: A (scalar) tensor representing the value of the loss function
    """
    def _custom_loss(y_true, y_pred):
        sigmoid_p = tf.nn.sigmoid(y_pred)
        zeros = array_ops.zeros_like(sigmoid_p, dtype=sigmoid_p.dtype)
        # For poitive prediction, only need consider front part loss, back part is 0;
        # target_tensor > zeros <=> z=1, so poitive coefficient = z - p.
        pos_p_sub = array_ops.where(y_true > zeros, y_true - sigmoid_p, zeros)
        # For negative prediction, only need consider back part loss, front part is 0;
        # target_tensor > zeros <=> z=1, so negative coefficient = 0.
        neg_p_sub = array_ops.where(y_true > zeros, zeros, sigmoid_p)
        per_entry_cross_ent = - alpha * (pos_p_sub ** gamma) * tf.log(tf.clip_by_value(sigmoid_p, 1e-8, 1.0)) \
                              - (1 - alpha) * (neg_p_sub ** gamma) * tf.log(
            tf.clip_by_value(1.0 - sigmoid_p, 1e-8, 1.0))
        return tf.reduce_sum(per_entry_cross_ent)
    return _custom_loss