Python cntk.log() Examples

The following are 30 code examples of cntk.log(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module cntk , or try the search function .
Example #1
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #2
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def categorical_crossentropy(target, output, from_logits=False):
    if from_logits:
        result = C.cross_entropy_with_softmax(output, target)
        # cntk's result shape is (batch, 1), while keras expect (batch, )
        return C.reshape(result, ())
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= C.reduce_sum(output, axis=-1)
        # avoid numerical instability with epsilon clipping
        output = C.clip(output, epsilon(), 1.0 - epsilon())
        return -sum(target * C.log(output), axis=-1)
Example #3
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))
Example #4
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def log(x):
    return C.log(x)
Example #5
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #6
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))
Example #7
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def log(x):
    return C.log(x)
Example #8
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #9
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def categorical_crossentropy(target, output, from_logits=False):
    if from_logits:
        result = C.cross_entropy_with_softmax(output, target)
        # cntk's result shape is (batch, 1), while keras expect (batch, )
        return C.reshape(result, ())
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= C.reduce_sum(output, axis=-1)
        # avoid numerical instability with epsilon clipping
        output = C.clip(output, epsilon(), 1.0 - epsilon())
        return -sum(target * C.log(output), axis=-1)
Example #10
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))
Example #11
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #12
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def categorical_crossentropy(target, output, from_logits=False):
    if from_logits:
        result = C.cross_entropy_with_softmax(output, target)
        # cntk's result shape is (batch, 1), while keras expect (batch, )
        return C.reshape(result, ())
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= C.reduce_sum(output, axis=-1)
        # avoid numerical instability with epsilon clipping
        output = C.clip(output, epsilon(), 1.0 - epsilon())
        return -sum(target * C.log(output), axis=-1)
Example #13
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))
Example #14
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def log(x):
    return C.log(x)
Example #15
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #16
Source File: cntk_backend.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def categorical_crossentropy(target, output, from_logits=False):
    if from_logits:
        result = C.cross_entropy_with_softmax(output, target)
        # cntk's result shape is (batch, 1), while keras expect (batch, )
        return C.reshape(result, ())
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= C.reduce_sum(output, axis=-1)
        # avoid numerical instability with epsilon clipping
        output = C.clip(output, epsilon(), 1.0 - epsilon())
        return -sum(target * C.log(output), axis=-1)
Example #17
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))
Example #18
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def log(x):
    return C.log(x)
Example #19
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def binary_crossentropy(output, target, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, _EPSILON, 1.0 - _EPSILON)
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #20
Source File: cntk_backend.py    From keras-lambda with MIT License 5 votes vote down vote up 
def categorical_crossentropy(output, target, from_logits=False):
    if from_logits:
        result = C.cross_entropy_with_softmax(output, target)
        # cntk's result shape is (batch, 1), while keras expect (batch, )
        return C.reshape(result, ())
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= C.reduce_sum(output, axis=-1)
        # avoid numerical instability with _EPSILON clipping
        output = C.clip(output, _EPSILON, 1.0 - _EPSILON)
        return -sum(target * C.log(output), axis=-1)
Example #21
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #22
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))
Example #23
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def log(x):
    return C.log(x)
Example #24
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #25
Source File: cntk_backend.py    From GraphicDesignPatternByPython with MIT License 5 votes vote down vote up 
def categorical_crossentropy(target, output, from_logits=False, axis=-1):
    # Here, unlike other backends, the tensors lack a batch dimension:
    axis_without_batch = -1 if axis == -1 else axis - 1
    output_dimensions = list(range(len(output.shape)))
    if axis_without_batch != -1 and axis_without_batch not in output_dimensions:
        raise ValueError(
            '{}{}{}'.format(
                'Unexpected channels axis {}. '.format(axis_without_batch),
                'Expected to be -1 or one of the axes of `output`, ',
                'which has {} dimensions.'.format(len(output.shape))))
    # If the channels are not in the last axis, move them to be there:
    if axis_without_batch != -1 and axis_without_batch != output_dimensions[-1]:
        permutation = output_dimensions[:axis_without_batch]
        permutation += output_dimensions[axis_without_batch + 1:]
        permutation += [axis_without_batch]
        output = C.transpose(output, permutation)
        target = C.transpose(target, permutation)
    if from_logits:
        result = C.cross_entropy_with_softmax(output, target)
        # cntk's result shape is (batch, 1), while keras expect (batch, )
        return C.reshape(result, ())
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= C.reduce_sum(output, axis=-1)
        # avoid numerical instability with epsilon clipping
        output = C.clip(output, epsilon(), 1.0 - epsilon())
        return -sum(target * C.log(output), axis=-1)
Example #26
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))
Example #27
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def log(x):
    return C.log(x)
Example #28
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def binary_crossentropy(target, output, from_logits=False):
    if from_logits:
        output = C.sigmoid(output)
    output = C.clip(output, epsilon(), 1.0 - epsilon())
    output = -target * C.log(output) - (1.0 - target) * C.log(1.0 - output)
    return output
Example #29
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def categorical_crossentropy(target, output, from_logits=False):
    if from_logits:
        result = C.cross_entropy_with_softmax(output, target)
        # cntk's result shape is (batch, 1), while keras expect (batch, )
        return C.reshape(result, ())
    else:
        # scale preds so that the class probas of each sample sum to 1
        output /= C.reduce_sum(output, axis=-1)
        # avoid numerical instability with epsilon clipping
        output = C.clip(output, epsilon(), 1.0 - epsilon())
        return -sum(target * C.log(output), axis=-1)
Example #30
Source File: cntk_backend.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def logsumexp(x, axis=None, keepdims=False):
    return log(sum(exp(x), axis=axis, keepdims=keepdims))