def __init__(self,
outputs,
activation=Activations,
input_shape=None,
weights=None,
bias=None,
**kwargs):
if isinstance(outputs, int) and outputs > 0:
self.outputs = outputs
else:
raise ValueError('Parameter "outputs" must be an integer and > 0')
self.weights = weights
self.bias = bias
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
super(Connected_layer, self).__init__(input_shape=input_shape)
if input_shape is not None:
self._build()
self.weights_update = None
self.bias_update = None
self.optimizer = None
def __init__(self, activation=Activations, alpha=1., beta=1., **kwargs):
'''
Shortcut layer: activation of the linear combination of the output of two layers
layer1 * alpha + layer2 * beta = output
Now working only with same shapes input
Parameters :
activation : activation function of the layer
alpha : float, default = 1., first weight of the combination
beta : float, default = 1., second weight of the combination
'''
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
self.alpha, self.beta = alpha, beta
self.output, self.delta = (None, None)
self._out_shape = None
self.ix, self.jx, self.kx = (None, None, None)
self.iy, self.jy, self.ky = (None, None, None)
def __init__(self, input_shape=None, activation=Activations, **kwargs):
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
super(Activation_layer, self).__init__(input_shape=input_shape)
def __init__(self,
outputs,
steps,
activation=Activations,
input_shape=None,
weights=None,
recurrent_weights=None,
bias=None,
return_sequence=False):
'''
Recurrent Neural Network layer. Build a Recurrent fully connected architecture.
Parameters
----------
outputs : integer, number of outputs of the layer.
steps : integer, number of timesteps of the recurrency.
activation : activation function object. activation function, applied to every hidden state
input_shape : tuple of int, default None. Used for a single layer model.
"None" is used when the layer is part of a network.
weights : numpy array, default None. numpy array of weights
of shapes (inputs, outputs). If None, the init is random.
recurrent_weights : numpy array, default None. numpy array of weights
of shapes (outputs, outputs). If None, the init is random.
bias : numpy array, default None. shape (outputs, )
If None, the init is zeros.
'''
if isinstance(outputs, int) and outputs > 0:
self.outputs = outputs
else:
raise ValueError('Parameter "outputs" must be an integer and > 0')
if isinstance(steps, int) and steps > 0:
self.steps = steps
else:
raise ValueError('Parameter "steps" must be an integer and > 0')
self.activation = _check_activation(layer=self,
activation_func=activation)
self.return_sequence = return_sequence
self.weights = weights
self.recurrent_weights = recurrent_weights
self.bias = bias
self.weights_update = None
self.recurrent_weights_update = None
self.bias_update = None
self.states = None
self.optimizer = None
if input_shape is not None:
super(SimpleRNN_layer, self).__init__(input_shape=input_shape)
self._build()
def __init__(self, filters, size, stride=None, input_shape=None,
weights=None, bias=None,
pad=False,
activation=Activations,
**kwargs):
if isinstance(filters, int) and filters > 0:
self.channels_out = filters
else:
raise ValueError('Parameter "filters" must be an integer and > 0')
self.size = size
if not hasattr(self.size, '__iter__'):
self.size = (int(self.size), int(self.size))
if self.size[0] <= 0. or self.size[1] <= 0.:
raise LayerError('Convolutional layer. Incompatible size values. They must be both > 0')
if not stride:
self.stride = size
else:
self.stride = stride
if not hasattr(self.stride, '__iter__'):
self.stride = (int(self.stride), int(self.stride))
if self.stride[0] <= 0. or self.stride[1] <= 0.:
raise LayerError('Convolutional layer. Incompatible stride values. They must be both > 0')
if len(self.size) != 2 or len(self.stride) != 2:
raise LayerError('Convolutional layer. Incompatible stride/size dimensions. They must be a 1D-2D tuple of values')
# Weights and bias
self.weights = weights
self.bias = bias
# Activation function
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
# Padding
self.pad = pad
self.pad_left, self.pad_right, self.pad_bottom, self.pad_top = (0, 0, 0, 0)
# Output, Delta and Updates
self.weights_update = None
self.bias_update = None
self.optimizer = None
if input_shape is not None:
super(Convolutional_layer, self).__init__(input_shape=input_shape)
self._build()
def __init__(self, activation=Activations, alpha=1., beta=1., **kwargs):
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
self.alpha, self.beta = alpha, beta
self.ix, self.jx, self.kx = (None, ) * 3
self.iy, self.jy, self.ky = (None, ) * 3
super(Shortcut_layer, self).__init__()
def __init__(self, activation=Activations, **kwargs):
'''
Activation layer
Parameters :
activation : activation function of the layer
'''
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
self.output, self.delta = (None, None)
self._out_shape = None
def __init__(self, input_shape=None, activation=Activations, **kwargs):
'''
Activation layer
Parameters
----------
input_shape : tuple of 4 integers: input shape of the layer.
activation : activation function of the layer.
'''
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
super(Activation_layer, self).__init__(input_shape=input_shape)
def __init__(self, outputs, activation=Activations, input_shape=None, weights=None, bias=None, **kwargs):
'''
Connected layer
Parameters
----------
outputs : integer, number of outputs of the layers
activation : activation function of the layer
input_shape : tuple, default None. Shape of the input in the format (batch, w, h, c),
None is used when the layer is part of a Network model.
weights : array of shape (w * h * c, outputs), default is None. Weights of the dense layer.
If None, weights init is random.
bias : array of shape (outputs, ), default None. Bias of the connected layer.
If None, bias init is random
'''
if isinstance(outputs, int) and outputs > 0:
self.outputs = outputs
else :
raise ValueError('Parameter "outputs" must be an integer and > 0')
self.weights = weights
self.bias = bias
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
super(Connected_layer, self).__init__(input_shape=input_shape)
if input_shape is not None:
self._build()
self.weights_update = None
self.bias_update = None
self.optimizer = None
def __init__(self,
input_shape,
filters,
size,
stride=None,
weights=None,
bias=None,
pad=False,
activation=Activations,
**kwargs):
'''
Convolution Layer: the output is the convolution of of the input batch
with a group of kernel of shape size = (kx,ky) with step stride.
Parameters:
input_shape : tuple, shape of the input batch of image (batch, w, h, channels_in)
filters : int, Number of filters to be slided over the input, and also
the number of channels of the output
size : tuple of int, size of the kernel of shape (kx, ky)
stride : tuple of int, step of the kernel of shape (st1, st2)
weights : filters array, with shape (kx, ky, channels_in, channels_out)
pad : boolean, if False the image is cutted along the last raws and columns, if True
the input is padded following keras SAME padding
activation : activation function of the layer
'''
self.batch, self.w, self.h, self.c = input_shape
self.channels_out = filters
self.size = size
if not hasattr(self.size, '__iter__'):
self.size = (int(self.size), int(self.size))
if not stride:
self.stride = size
else:
self.stride = stride
if not hasattr(self.stride, '__iter__'):
self.stride = (int(self.stride), int(self.stride))
assert len(self.size) == 2 and len(self.stride) == 2
self.pad = pad
self.pad_left, self.pad_right, self.pad_bottom, self.pad_top = (0, 0,
0, 0)
activation = _check_activation(self, activation)
# Activation function
self.activation = activation.activate
self.gradient = activation.gradient
self.delta, self.output = (None, None)
# Weights and bias
if weights is None:
scale = np.sqrt(2 / (self.size[0] * self.size[1] * self.c))
self.weights = np.random.normal(loc=scale,
scale=1.,
size=(self.size[0], self.size[1],
self.c, self.channels_out))
else:
self.weights = weights
if bias is None:
self.bias = np.zeros(shape=(self.channels_out, ), dtype=float)
else:
self.bias = bias
# Updates
self.weights_update = None
self.bias_update = None
self.optimizer = None
def __init__(self,
filters,
size,
stride=None,
input_shape=None,
weights=None,
bias=None,
pad=False,
activation=Activations,
**kwargs):
'''
Convolution Layer: the output is the convolution of the input images
with a group of kernel of shape size = (kx,ky) with step stride.
Parameters
----------
filters : integer. Number of filters to be slided over the input, and also
the number of channels of the output (channels_out)
size : tuple of int, size of the kernel of shape (kx, ky).
stride : tuple of int, default None. Step of the kernel, with shape (st1, st2).
If None, stride is assigned size values.
input_shape : tuple, default None. Shape of the input in the format (batch, w, h, c),
None is used when the layer is part of a Network model.
weights : numpy array, default None. filters of the convolutionanl layer,
with shape (kx, ky, channels_in, filters). If None, random weights are initialized
bias : numpy array, default None. Bias of the convolutional layer.
If None, bias init is random with shape (filters, )
pad : boolean, default False. If False the image is cutted along the last raws and columns, if True
the input is padded following keras SAME padding
activation : activation function of the layer
'''
if isinstance(filters, int) and filters > 0:
self.channels_out = filters
else:
raise ValueError('Parameter "filters" must be an integer and > 0')
self.size = size
if not hasattr(self.size, '__iter__'):
self.size = (int(self.size), int(self.size))
if self.size[0] <= 0. or self.size[1] <= 0.:
raise LayerError(
'Convolutional layer. Incompatible size values. They must be both > 0'
)
if not stride:
self.stride = size
else:
self.stride = stride
if not hasattr(self.stride, '__iter__'):
self.stride = (int(self.stride), int(self.stride))
if self.stride[0] <= 0. or self.stride[1] <= 0.:
raise LayerError(
'Convolutional layer. Incompatible stride values. They must be both > 0'
)
if len(self.size) != 2 or len(self.stride) != 2:
raise LayerError(
'Convolutional layer. Incompatible stride/size dimensions. They must be a 1D-2D tuple of values'
)
# Weights and bias
self.weights = weights
self.bias = bias
# Activation function
activation = _check_activation(self, activation)
self.activation = activation.activate
self.gradient = activation.gradient
# Padding
self.pad = pad
self.pad_left, self.pad_right, self.pad_bottom, self.pad_top = (0, 0,
0, 0)
# Output, Delta and Updates
self.weights_update = None
self.bias_update = None
self.optimizer = None
if input_shape is not None:
super(Convolutional_layer, self).__init__(input_shape=input_shape)
self._build()
def __init__(self, outputs, steps, activation=Activations, input_shape=None, weights=None, bias=None, **kwargs):
'''
RNN layer
Parameters
----------
outputs : integer, number of outputs of the layers
steps : integer, number of mini-batch/steps to perform.
activation : activation function of the layer
input_shape : tuple, default None. Shape of the input in the format (batch, w, h, c),
None is used when the layer is part of a Network model.
weights : array of shape (w * h * c, outputs), default is None. Weights of the dense layer.
If None, weights init is random.
bias : array of shape (outputs, ), default None. Bias of the connected layer.
If None, bias init is random
'''
if isinstance(outputs, int) and outputs > 0:
self.outputs = outputs
else :
raise ValueError('Parameter "outputs" must be an integer and > 0')
if isinstance(steps, int) and steps > 0:
self.steps = steps
else :
raise ValueError('Parameter "steps" must be an integer and > 0')
if weights is None:
weights = (None, None, None)
else:
if np.shape(weights)[0] != 3:
raise ValueError('Wrong number of init "weights". There are 3 connected layers into the RNN cell.')
if bias is None:
bias = (None, None, None)
else:
if np.shape(bias)[0] != 3:
raise ValueError('Wrong number of init "biases". There are 3 connected layers into the RNN cell.')
self.activation = _check_activation(self, activation)
# if input shape is passed, init of weights, else done in __call__
if input_shape is not None:
b, w, h, c = input_shape
if b < self.steps:
class_name = self.__class__.__name__
prev_name = layer.__class__.__name__
raise LayerError('Incorrect steps found. Layer {} cannot be connected to the previous {} layer.'.format(class_name, prev_name))
self.batch = b // self.steps
self.input_shape = (self.batch, w, h, c)
indices = np.arange(0, b)
self.batches = np.lib.stride_tricks.as_strided(indices, shape=(self.steps, self.batch), strides=(self.batch * 8, 8)).copy()
self.input_layer = Connected_layer(self.outputs, self.activation, input_shape=(self.batches[-1][-1] + 1, w, h, c), weights=weights[0], bias=bias[0])
self.self_layer = Connected_layer(self.outputs, self.activation, weights=weights[1], bias=bias[1])(self.input_layer)
self.output_layer = Connected_layer(self.outputs, self.activation, weights=weights[2], bias=bias[2])(self.self_layer)
self.state = np.zeros(shape=(self.batch, w, h, self.outputs), dtype=float)
else:
self.batch = None
self.input_shape = None
self.batches = None
self.input_layer = None
self.self_layer = None
self.output_layer = None
self.state = None
self.prev_state = None
self.output, self.delta = (None, None)
