Python 从神经网络层去除偏差

我想删除bias参数。我试图在我定义神经网络的地方加入bias=None，但没有成功

net1 = NeuralNet(
layers=[ # three layers: one hidden layer
('input', layers.InputLayer),
#('hidden', layers.DenseLayer),
('output', layers.DenseLayer),
],
# layer parameters:
input_shape=(None,2), # 2 inputs
#hidden_num_units=200, # number of units in hidden layer
output_nonlinearity=None, # output layer uses identity function
output_num_units=1, # 1 target value

# optimization method:
update=nesterov_momentum,
update_learning_rate=0.01,
update_momentum=0.9,

regression=True,  # flag to indicate we're dealing with regression problem
max_epochs=400,  # we want to train this many epochs
verbose=1,
bias = None
) 

根据（对于密集层类似），对于偏移，您有以下选项：

b = None 

至少根据千层面文档，似乎没有任何一层的“偏差”参数，而是使用“b”。我不能代表NoLearn说话，因为我不使用该软件包

# Build the network yourself
inputs = InputLayer(shape=(None, 2))
network = DenseLayer(inputs, num_units=1, nonlinearity=None, b = None)

net1 = NeuralNet(
network,
#We don't need any of these parameters since we provided them above
# layer parameters:
#input_shape=(None,2), # 2 inputs
#hidden_num_units=200, # number of units in hidden layer
#output_nonlinearity=None, # output layer uses identity function
#output_num_units=1, # 1 target value

# optimization method:
update=nesterov_momentum,
update_learning_rate=0.01,
update_momentum=0.9,

regression=True,  # flag to indicate we're dealing with regression problem
max_epochs=400,  # we want to train this many epochs
verbose=1,
bias = None
) 

编辑：

以下是一些千层面示例代码：

import lasagne
net = {}
net['input'] = lasagne.layers.InputLayer(shape=(None, 3, 224,224), input_var=None)
net['conv'] = lasagne.layers.Conv2DLayer(net['input'], num_filters=5, filter_size=3, b = None)
print net['conv'].get_params()

返回：

[W]

孤独，意味着没有偏见

对于NoLearn，我不确定，因为我不使用该软件包

# Build the network yourself
inputs = InputLayer(shape=(None, 2))
network = DenseLayer(inputs, num_units=1, nonlinearity=None, b = None)

net1 = NeuralNet(
network,
#We don't need any of these parameters since we provided them above
# layer parameters:
#input_shape=(None,2), # 2 inputs
#hidden_num_units=200, # number of units in hidden layer
#output_nonlinearity=None, # output layer uses identity function
#output_num_units=1, # 1 target value

# optimization method:
update=nesterov_momentum,
update_learning_rate=0.01,
update_momentum=0.9,

regression=True,  # flag to indicate we're dealing with regression problem
max_epochs=400,  # we want to train this many epochs
verbose=1,
bias = None
) 

---

我认为这应该行得通。网络中可能有一个kwarg要传递（我不记得了），但我认为默认情况下，如果没有给出任何参数，它是第一个参数

当使用“b=None”时，我得到了“ValueError:Unused kwarg:b”，我已经用一些烤宽面条示例代码更新了我的答案。我不使用NoLearn。我提供了一个千层面的答案，因为你的问题中包含了千层面标签。希望这对你仍然有用。我记得我在哪里看到这个。。。在源代码中：）：