对Keras自带Loss Function的深入研究

1. categorical_crossentropy VS. sparse_categorical_crossentropy

```(类别数5)
Integer target: [1,2,4]
Categorical target： [[0. 1. 0. 0. 0.]
[0. 0. 1. 0. 0.]
[0. 0. 0. 0. 1.]]
```

```from keras.utils import to_categorical
categorical_labels = to_categorical(int_labels, num_classes=None)
```

```https://github.com/tensorflow/tensorflow/blob/r1.13/tensorflow/python/keras/backend.py
--------------------------------------------------------------------------------------------------------------------
def categorical_crossentropy(target, output, 编程客栈from_logits=False, axis=-1):
"""Categorical crossentropy between an output tensor and a target tensor.
Arguments:
target: A tensor of the same shape as `output`.
output: A tensor resulting from a softmax
(unless `from_logits` is True, in which
case `output` is expected to be the logits).
from_logits: Boolean, whether `output` is the
result of a softmax, or is a tensor of logits.
axis: Int specifying the channels axis. `axis=-1` corresponds to data
format `channels_last', and `axis=1` corresponds to data format
`channels_first`.
Returns:
Output tensor.
Raises:
ValueError: if `axis` is neither -1 nor one of the axes of `output`.
"""
rank = len(output.shape)
axis = axis % rank
# Note: nn.softmax_cross_entropy_with_logits_v2
# expects logits, Keras expects probabilities.
if not from_logits:
# scale preds so that the class probas of each sample sum to 1
output = output / math_ops.reduce_sum(output, axis, True)
# manual computation of crossentropy
epsilon_ = _to_tensor(epsilon(), output.dtype.base_dtype)
output = clip_ops.clip_by_value(output, epsilon_, 1. - epsilon_)
return -math_ops.reduce_sum(target * math_ops.log(output), axis)
else:
return nn.softmax_cross_entropy_with_logits_v2(labels=target, logits=output)
------------www.cppcns.com--------------------------------------------------------------------------------------------------------
def sparse_categorical_crossentropy(target, output, from_logits=False, axis=-1):
"""Categorical crossentropy with integer targets.
Arguments:
target: An integer tensor.
output: A tensor resulting from a softmax
(unless `from_logits` is True, in which
case `output` is expected to be the logits).
from_logits: Boolean, whether `output` is the
result of a softmax, or is a tensor of logits.
axis: Int specifying the channels axis. `axis=-1` corresponds to data
format `channels_last', and `axis=1` corresponds to data format
`channels_first`.
Returns:
Output tensor.
Raises:
ValueError: if `axis` is neither -1 nor one of the axes of `output`.
"""
rank = len(output.shape)
axis = axis % rank
if axis != rank - 1:
permutation = list(range(axis)) + list(range(axis + 1, rank)) + [axis]
output = array_ops.transpose(output, perm=permutation)
# Note: nn.sparse_softmax_cross_entropy_with_logits
# expects logits, Keras expects probabilities.
if not from_logits:
epsilon_ = _to_tensor(epsilon(), output.dtype.base_dtype)
output = clip_ops.clip_by_value(output, epsilon_, 1 - epsilon_)
output = math_ops.log(output)
output_shape = output.shape
targets = cast(flatten(target), 'int64')
logits = array_ops.reshape(output, [-1, int(output_shape[-1])])
res = nn.sparse_sof编程客栈tmax_cross_entropy_with_logits(
labels=targets, logits=logits)
if len(output_shape) >= 3:
# If our output includes timesteps or spatial dimensions we need to reshape
return array_ops.reshape(res, array_ops.shape(output)[:-1])
else:
return res
```

categorical_crossentropy计算交叉熵时使用的是nn.softmax_cross_entropy_with_logits_v2( labels=targets, logits=logits)，而sparse_categorical_crossentropy使用的是nn.sparse_softmax_cross_entropy_with_logits( labels=targets, logits=logits)，二者本质并无区别，只是对输入参数logits的要求不同，v2要求的是logits与labels格式相同（即元素也是独热的），而sparse则要求logits的元素是个数值，与上面Integer format和Categorical format的对比含义类似。

2. Binary_crossentropy

```https://github.com/tensorflow/tensorflow/blob/r1.13/tensorflow/python/keras/backend.py
--------------------------------------------------------------------------------------------------------------------
def binary_crossentropy(target, output, from_logits=False):
"""Binary crossentropy between an output tensor and a target tensor.
Arguments:
target: A tensor with the same shape as `output`.
output: A tensor.
from_logits: Whether `output` is expected to be a logits tensor.
By default, we consider that `output`
encodes a probability distribution.
Returns:
A tensor.
"""
# Note: nn.sigmoid_cross_entropy_with_logits
# expects logits, Keras expects probabilities.
if not from_logits:
# transform back to logits
epsilon_ = _to_tensor(epsilon(), output.dtype.base_dtype)
output = clip_ops.clip_by_value(output, epsilon_, 1 - epsilon_)
output = math_ops.log(output / (1 - output))
return nn.sigmoid_cross_entropy_with_logits(labels=target, logits=output)
```

```from keras import backend as K
def mean_squared_error(y_true, y_pred):
return K.mean(K.square(y_pred - y_true), axis=-1)
def mean_absolute_error(y_true, y_pred):
return K.mean(K.abs(y_pred - y_true), axis=-1)
def mean_absolute_percentage_error(y_true, y_pred):
diff = K.abs((y_true - y_pred) / K.clip(K.abs(y_true), K.epsilon(), np.inf))
return 100. * K.mean(diff, axis=-1)
def categorical_crossentropy(y_true, y_pred):
'''Expects a binary class matrix instead of a vector of scalar classes.
'''
return K.categorical_crossentropy(y_pred, y_true)
def sparse_categorical_crossentropy(y_true, y_pred):
'''expects an array of integer classes.
Note: labels shape must have the same number of dimensions as output shape.
If you get a shape error, add a length-1 dimension to labels.
'''
return K.sparse_categorical_crossentropy(y_pred, y_true)
def binary_crossentropy(y_true, y_pred):
return K.mean(K.binary_crossentropy(y_pred, y_true), axis=-1)
def kullback_leibler_divergence(y_true, y_pred):
y_true = K.clip(y_true, K.epsilon(), 1)
y_pred = K.clip(y_pred, K.epsilon(), 1)
return K.sum(y_true * K.log(y_true / y_pred), axi编程客栈s=-1)
def poisson(y_true, y_pred):
return K.mean(y_pred - y_true * K.log(y_pred + K.epsilon()), axis=-1)
def cosine_proximity(y_true, y_pred):
y_true = K.l2_normalize(y_true, axis=-1)
y_pred = K.l2_normalize(y_pred, axis=-1)
return -K.mean(y_true * y_pred, axis=-1)
```

```from keras import backend as K
def new_loss(y_true,y_pred):
return K.mean((y_pred-y_true),axis = -1)```

```from keras import backend as K
def my_loss(y_true,y_pred):
return K.mean((y_pred-y_true),axis = -1)
model.compile(optimizer=optimizers.RMSprop(lr)，loss=my_loss,
metrics=['accuracy'])```