Python cntk.reduce_sum() Examples
The following are 30
code examples of cntk.reduce_sum().
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 |
def l2_normalize(x, axis=None): axis = [axis] axis = _normalize_axis(axis, x) norm = C.sqrt(C.reduce_sum(C.square(x), axis=axis[0])) return x / norm
Example #2
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
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 |
def sum(x, axis=None, keepdims=False): axis = _normalize_axis(axis, x) output = _reduce_on_axis(x, axis, 'reduce_sum') return _remove_dims(output, axis, keepdims)
Example #4
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def any(x, axis=None, keepdims=False): reduce_result = sum(x, axis, keepdims=keepdims) any_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(any_matrix) else: return any_matrix
Example #5
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def all(x, axis=None, keepdims=False): reduce_result = prod(x, axis, keepdims=keepdims) all_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(all_matrix) else: return all_matrix
Example #6
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def l2_normalize(x, axis=None): axis = [axis] axis = _normalize_axis(axis, x) norm = C.sqrt(C.reduce_sum(C.square(x), axis=axis[0])) return x / norm
Example #7
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def sum(x, axis=None, keepdims=False): axis = _normalize_axis(axis, x) output = _reduce_on_axis(x, axis, 'reduce_sum') return _remove_dims(output, axis, keepdims)
Example #8
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def any(x, axis=None, keepdims=False): reduce_result = sum(x, axis, keepdims=keepdims) any_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(any_matrix) else: return any_matrix
Example #9
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def all(x, axis=None, keepdims=False): reduce_result = prod(x, axis, keepdims=keepdims) all_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(all_matrix) else: return all_matrix
Example #10
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def l2_normalize(x, axis=None): axis = [axis] axis = _normalize_axis(axis, x) norm = C.sqrt(C.reduce_sum(C.square(x), axis=axis[0])) return x / norm
Example #11
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
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 #12
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def any(x, axis=None, keepdims=False): reduce_result = sum(x, axis, keepdims=keepdims) any_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(any_matrix) else: return any_matrix
Example #13
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def all(x, axis=None, keepdims=False): reduce_result = prod(x, axis, keepdims=keepdims) all_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(all_matrix) else: return all_matrix
Example #14
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def all(x, axis=None, keepdims=False): reduce_result = prod(x, axis, keepdims=keepdims) all_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(all_matrix) else: return all_matrix
Example #15
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
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 #16
Source File: cntk_backend.py From deepQuest with BSD 3-Clause "New" or "Revised" License | 5 votes |
def sum(x, axis=None, keepdims=False): axis = _normalize_axis(axis, x) output = _reduce_on_axis(x, axis, 'reduce_sum') return _remove_dims(output, axis, keepdims)
Example #17
Source File: cntk_backend.py From deepQuest with BSD 3-Clause "New" or "Revised" License | 5 votes |
def any(x, axis=None, keepdims=False): reduce_result = sum(x, axis, keepdims=keepdims) any_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(any_matrix) else: return any_matrix
Example #18
Source File: cntk_backend.py From deepQuest with BSD 3-Clause "New" or "Revised" License | 5 votes |
def all(x, axis=None, keepdims=False): reduce_result = prod(x, axis, keepdims=keepdims) all_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(all_matrix) else: return all_matrix
Example #19
Source File: cntk_backend.py From deepQuest with BSD 3-Clause "New" or "Revised" License | 5 votes |
def l2_normalize(x, axis=None): axis = [axis] axis = _normalize_axis(axis, x) norm = C.sqrt(C.reduce_sum(C.square(x), axis=axis[0])) return x / norm
Example #20
Source File: cntk_backend.py From deepQuest with BSD 3-Clause "New" or "Revised" License | 5 votes |
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 #21
Source File: cntk_backend.py From keras-lambda with MIT License | 5 votes |
def sum(x, axis=None, keepdims=False): axis = _normalize_axis(axis, x) output = _reduce_on_axis(x, axis, 'reduce_sum') return _remove_dims(output, axis, keepdims)
Example #22
Source File: cntk_backend.py From keras-lambda with MIT License | 5 votes |
def any(x, axis=None, keepdims=False): reduce_result = sum(x, axis, keepdims=keepdims) any_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(any_matrix) else: return any_matrix
Example #23
Source File: cntk_backend.py From keras-lambda with MIT License | 5 votes |
def all(x, axis=None, keepdims=False): reduce_result = prod(x, axis, keepdims=keepdims) all_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(all_matrix) else: return all_matrix
Example #24
Source File: cntk_backend.py From keras-lambda with MIT License | 5 votes |
def l2_normalize(x, axis): axis = [axis] axis = _normalize_axis(axis, x) norm = C.sqrt(C.reduce_sum(C.square(x), axis=axis[0])) return x / norm
Example #25
Source File: cntk_backend.py From keras-lambda with MIT License | 5 votes |
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 #26
Source File: cntk_backend.py From DeepLearning_Wavelet-LSTM with MIT License | 5 votes |
def l2_normalize(x, axis=None): axis = [axis] axis = _normalize_axis(axis, x) norm = C.sqrt(C.reduce_sum(C.square(x), axis=axis[0])) return x / norm
Example #27
Source File: cntk_backend.py From GraphicDesignPatternByPython with MIT License | 5 votes |
def sum(x, axis=None, keepdims=False): axis = _normalize_axis(axis, x) output = _reduce_on_axis(x, axis, 'reduce_sum') return _remove_dims(output, axis, keepdims)
Example #28
Source File: cntk_backend.py From GraphicDesignPatternByPython with MIT License | 5 votes |
def any(x, axis=None, keepdims=False): reduce_result = sum(x, axis, keepdims=keepdims) any_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(any_matrix) else: return any_matrix
Example #29
Source File: cntk_backend.py From GraphicDesignPatternByPython with MIT License | 5 votes |
def all(x, axis=None, keepdims=False): reduce_result = prod(x, axis, keepdims=keepdims) all_matrix = C.element_select( reduce_result, ones_like(reduce_result), zeros_like(reduce_result)) if len(reduce_result.shape) == 0 and _get_dynamic_axis_num(x) == 0: return C.reduce_sum(all_matrix) else: return all_matrix
Example #30
Source File: cntk_backend.py From GraphicDesignPatternByPython with MIT License | 5 votes |
def l2_normalize(x, axis=None): axis = [axis] axis = _normalize_axis(axis, x) norm = C.sqrt(C.reduce_sum(C.square(x), axis=axis[0])) return x / norm