Python cntk.one_hot() Examples

def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1) 

def one_hot(indices, num_classes):
    return C.one_hot(indices, num_classes) 

def in_top_k(predictions, targets, k):
    _targets = C.one_hot(targets, predictions.shape[-1])
    result = C.classification_error(predictions, _targets, topN=k)
    return 1 - C.reshape(result, shape=()) 

def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1) 

def sparse_categorical_crossentropy(target, output, from_logits=False):
    target = C.one_hot(target, output.shape[-1])
    target = C.reshape(target, output.shape)
    return categorical_crossentropy(target, output, from_logits) 

def one_hot(indices, num_classes):
    return C.one_hot(indices, num_classes) 

def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1) 

def sparse_categorical_crossentropy(target, output, from_logits=False):
    target = C.one_hot(target, output.shape[-1])
    target = C.reshape(target, output.shape)
    return categorical_crossentropy(target, output, from_logits) 

def one_hot(indices, num_classes):
    return C.one_hot(indices, num_classes) 

def in_top_k(predictions, targets, k):
    _targets = C.one_hot(targets, predictions.shape[-1])
    result = C.classification_error(predictions, _targets, topN=k)
    return 1 - C.reshape(result, shape=()) 

def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1) 

def one_hot(indices, num_classes):
    return C.one_hot(indices, num_classes) 

def in_top_k(predictions, targets, k):
    _targets = C.one_hot(targets, predictions.shape[-1])
    result = C.classification_error(predictions, _targets, topN=k)
    return 1 - C.reshape(result, shape=()) 

def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will udpate with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_class = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_class)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1) 

def sparse_categorical_crossentropy(target, output, from_logits=False):
    target = C.one_hot(target, output.shape[-1])
    target = C.reshape(target, output.shape)
    return categorical_crossentropy(target, output, from_logits) 

def one_hot(indices, nb_classes):
    return C.one_hot(indices, nb_classes) 

def in_top_k(predictions, targets, k):
    _targets = C.one_hot(targets, predictions.shape[-1])
    result = C.classification_error(predictions, _targets, topN=k)
    return 1 - C.reshape(result, shape=()) 

def sparse_categorical_crossentropy(output, target, from_logits=False):
    target = C.one_hot(target, output.shape[-1])
    target = C.reshape(target, output.shape)
    return categorical_crossentropy(output, target, from_logits) 

def one_hot(indices, nb_classes):
    return C.one_hot(indices, nb_classes) 

def in_top_k(predictions, targets, k):
    _targets = C.one_hot(targets, predictions.shape[-1])
    result = C.classification_error(predictions, _targets, topN=k)
    return 1 - C.reshape(result, shape=()) 

def one_hot(indices, num_classes):
    return C.one_hot(indices, num_classes) 

def sparse_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))))
    target = C.one_hot(target, output.shape[axis_without_batch],
                       axis=axis_without_batch)
    target = C.reshape(target, output.shape)
    return categorical_crossentropy(target, output, from_logits, axis=axis) 

def one_hot(indices, num_classes):
    return C.one_hot(indices, num_classes) 

def in_top_k(predictions, targets, k):
    _targets = C.one_hot(targets, predictions.shape[-1])
    result = C.classification_error(predictions, _targets, topN=k)
    return 1 - C.reshape(result, shape=()) 

def emit_Embedding(self, IR_node):
        
        codes = list()
        codes.append("{}_P = cntk.one_hot({}, __weights_dict['{}']['weights'].shape[0])".format(
            IR_node.variable_name,
            self.parent_variable_name(IR_node),
            IR_node.name))
        
        codes.append("{:<15} = layers.Embedding(weights=__weights_dict['{}']['weights'])({}_P)".format(
            IR_node.variable_name,
            # IR_node.get_attr('output_dim'),
            IR_node.name,
            IR_node.variable_name))

        return codes 

def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1) 

def sparse_categorical_crossentropy(target, output, from_logits=False):
    target = C.one_hot(target, output.shape[-1])
    target = C.reshape(target, output.shape)
    return categorical_crossentropy(target, output, from_logits) 

def one_hot(indices, num_classes):
    return C.one_hot(indices, num_classes) 

def in_top_k(predictions, targets, k):
    _targets = C.one_hot(targets, predictions.shape[-1])
    result = C.classification_error(predictions, _targets, topN=k)
    return 1 - C.reshape(result, shape=()) 

def gather(reference, indices):
    # There is a bug in cntk gather op which may cause crash.
    # We have made a fix but not catched in CNTK 2.1 release.
    # Will update with gather op in next release
    if _get_cntk_version() >= 2.2:
        return C.ops.gather(reference, indices)
    else:
        num_classes = reference.shape[0]
        one_hot_matrix = C.ops.one_hot(indices, num_classes)
        return C.times(one_hot_matrix, reference, output_rank=len(reference.shape) - 1)