Python keras.engine方法代碼示例

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def get_batch(X, start=None, stop=None):
    """Like keras.engine.training.slice_X, but supports latent vectors.

    Args:
        X: Numpy array or list of Numpy arrays.
        start: integer, the start of the batch, or a list of integers, the
            indices of each sample in to use in this batch.
        stop: integer, the end of the batch (only needed if start is an
            integer).

    Returns:
        X[start:stop] if X is array-like, or [x[start:stop] for x in X]
        if X is a list. Latent vector functions will be called as appropriate.
    """

    if isinstance(X, list):
        if hasattr(start, '__len__'):
            if hasattr(start, 'shape'):
                start = start.tolist()
            return [x[start] if is_numpy_array(x)
                    else x(len(start)) for x in X]
        else:
            return [x[start:stop] if is_numpy_array(x)
                    else x(stop - start) for x in X]
    else:
        if hasattr(start, '__len__'):
            if hasattr(start, 'shape'):
                start = start.tolist()
            return (X[start] if is_numpy_array(X)
                    else X(len(start)))
        else:
            return (X[start:stop] if is_numpy_array(X)
                    else X(stop - start)) 

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def load_weights(self, filepath, by_name=False, exclude=None):
        """Modified version of the correspoding Keras function with
        the addition of multi-GPU support and the ability to exclude
        some layers from loading.
        exlude: list of layer names to excluce
        """
        import h5py
        from keras.engine import topology

        if exclude:
            by_name = True

        if h5py is None:
            raise ImportError('`load_weights` requires h5py.')
        f = h5py.File(filepath, mode='r')
        if 'layer_names' not in f.attrs and 'model_weights' in f:
            f = f['model_weights']

        # In multi-GPU training, we wrap the model. Get layers
        # of the inner model because they have the weights.
        keras_model = self.keras_model
        layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model") \
            else keras_model.layers

        # Exclude some layers
        if exclude:
            layers = filter(lambda l: l.name not in exclude, layers)

        if by_name:
            topology.load_weights_from_hdf5_group_by_name(f, layers)
        else:
            topology.load_weights_from_hdf5_group(f, layers)
        if hasattr(f, 'close'):
            f.close()

        # Update the log directory
        self.set_log_dir(filepath) 

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def load_weights(self, filepath, by_name=False, exclude=None):
        """Modified version of the correspoding Keras function with
        the addition of multi-GPU support and the ability to exclude
        some layers from loading.
        exlude: list of layer names to excluce
        """
        import h5py
        from keras.engine import topology

        if exclude:
            by_name = True

        if h5py is None:
            raise ImportError('`load_weights` requires h5py.')
        f = h5py.File(filepath, mode='r')
        if 'layer_names' not in f.attrs and 'model_weights' in f:
            f = f['model_weights']

        # In multi-GPU training, we wrap the model. Get layers
        # of the inner model because they have the weights.
        keras_model = self.keras_model
        layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
            else keras_model.layers

        # Exclude some layers
        if exclude:
            layers = filter(lambda l: l.name not in exclude, layers)

        if by_name:
            topology.load_weights_from_hdf5_group_by_name(f, layers)
        else:
            topology.load_weights_from_hdf5_group(f, layers)
        if hasattr(f, 'close'):
            f.close()

        # Update the log directory
        self.set_log_dir(filepath) 

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def load_weights(self, filepath, by_name=False, exclude=None):
        """Modified version of the correspoding Keras function with
        the addition of multi-GPU support and the ability to exclude
        some layers from loading.
        exlude: list of layer names to excluce
        """
        import h5py
        from keras.engine import saving

        if exclude:
            by_name = True

        if h5py is None:
            raise ImportError('`load_weights` requires h5py.')
        f = h5py.File(filepath, mode='r')
        if 'layer_names' not in f.attrs and 'model_weights' in f:
            f = f['model_weights']

        # In multi-GPU training, we wrap the model. Get layers
        # of the inner model because they have the weights.
        keras_model = self.keras_model
        layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
            else keras_model.layers

        # Exclude some layers
        if exclude:
            layers = filter(lambda l: l.name not in exclude, layers)

        if by_name:
            saving.load_weights_from_hdf5_group_by_name(f, layers)
        else:
            saving.load_weights_from_hdf5_group(f, layers)
        if hasattr(f, 'close'):
            f.close()

        # Update the log directory
        self.set_log_dir(filepath) 

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def load_weights(self, filepath, by_name=False, exclude=None, verbose=1):
        """Modified version of the correspoding Keras function with
        the addition of multi-GPU support and the ability to exclude
        some layers from loading.
        exlude: list of layer names to excluce
        """
        import h5py
        from keras.engine import topology
        
        if verbose==1:
            self.logger.log('loading weights form {}'.format(filepath))
        if exclude:
            by_name = True

        if h5py is None:
            raise ImportError('`load_weights` requires h5py.')
        f = h5py.File(filepath, mode='r')
        if 'layer_names' not in f.attrs and 'model_weights' in f:
            f = f['model_weights']

        # In multi-GPU training, we wrap the model. Get layers
        # of the inner model because they have the weights.
        keras_model = self.keras_model
        layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
            else keras_model.layers

        # Exclude some layers
        if exclude:
            layers = filter(lambda l: l.name not in exclude, layers)

        if by_name:
            topology.load_weights_from_hdf5_group_by_name(f, layers)
        else:
            topology.load_weights_from_hdf5_group(f, layers)
        if hasattr(f, 'close'):
            f.close() 

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def load_weights(self, filepath, by_name=False, exclude=None):
        """Modified version of the corresponding Keras function with
        the addition of multi-GPU support and the ability to exclude
        some layers from loading.
        exclude: list of layer names to exclude
        """
        import h5py
        # Conditional import to support versions of Keras before 2.2
        # TODO: remove in about 6 months (end of 2018)
        try:
            from keras.engine import saving
        except ImportError:
            # Keras before 2.2 used the 'topology' namespace.
            from keras.engine import topology as saving

        if exclude:
            by_name = True

        if h5py is None:
            raise ImportError('`load_weights` requires h5py.')
        f = h5py.File(filepath, mode='r')
        if 'layer_names' not in f.attrs and 'model_weights' in f:
            f = f['model_weights']

        # In multi-GPU training, we wrap the model. Get layers
        # of the inner model because they have the weights.
        keras_model = self.keras_model
        layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
            else keras_model.layers

        # Exclude some layers
        if exclude:
            layers = filter(lambda l: l.name not in exclude, layers)

        if by_name:
            saving.load_weights_from_hdf5_group_by_name(f, layers)
        else:
            saving.load_weights_from_hdf5_group(f, layers)
        if hasattr(f, 'close'):
            f.close()

        # Update the log directory
        self.set_log_dir(filepath) 

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def load_weights(self, filepath, by_name=False, exclude=None):
        """Modified version of the corresponding Keras function with
        the addition of multi-GPU support and the ability to exclude
        some layers from loading.
        exclude: list of layer names to exclude
        """
        import h5py
        # Conditional import to support versions of Keras before 2.2
        # TODO: remove in about 6 months (end of 2018)
        try:
            from keras.engine import saving
        except ImportError:
            # Keras before 2.2 used the 'topology' namespace.
            from keras.engine import topology as saving

        if exclude:
            by_name = True

        if h5py is None:
            raise ImportError('`load_weights` requires h5py.')
        f = h5py.File(filepath, mode='r')
        if 'layer_names' not in f.attrs and 'model_weights' in f:
            f = f['model_weights']

        # In multi-GPU training, we wrap the model. Get layers
        # of the inner model because they have the weights.
        keras_model = self.keras_model
        layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
            else keras_model.layers

        # Exclude some layers
        if exclude:
            layers = filter(lambda l: l.name not in exclude, layers)

        if by_name:
            saving.load_weights_from_hdf5_group_by_name(f, layers)
        else:
            saving.load_weights_from_hdf5_group(f, layers)
        if hasattr(f, 'close'):
            f.close()

        # Update the log directory
        if self.mode == 'training':
            self.set_log_dir(filepath) 

# 需要導入模塊: import keras [as 別名]
# 或者: from keras import engine [as 別名]
def load_weights(self, filepath, by_name=False, exclude=None):
        """Modified version of the correspoding Keras function with
        the addition of multi-GPU support and the ability to exclude
        some layers from loading.
        exlude: list of layer names to excluce
        """
        import h5py
        # Keras 2.2 use saving
        try:
            from keras.engine import saving
        except ImportError:
            # Keras before 2.2 used the 'topology' namespace.
            from keras.engine import topology as saving

        if exclude:
            by_name = True

        if h5py is None:
            raise ImportError('`load_weights` requires h5py.')
        f = h5py.File(filepath, mode='r')
        if 'layer_names' not in f.attrs and 'model_weights' in f:
            f = f['model_weights']

        # In multi-GPU training, we wrap the model. Get layers
        # of the inner model because they have the weights.
        keras_model = self.keras_model
        layers = keras_model.inner_model.layers if hasattr(keras_model, "inner_model")\
            else keras_model.layers

        # Exclude some layers
        if exclude:
            layers = filter(lambda l: l.name not in exclude, layers)

        if by_name:
            saving.load_weights_from_hdf5_group_by_name(f, layers)
        else:
            saving.load_weights_from_hdf5_group(f, layers)
        if hasattr(f, 'close'):
            f.close()

        # Update the log directory
        self.set_log_dir(filepath)