在我的项目中，我必须多次使用卷积层，最后才能使用池化层。我在
找到了代码https://github.com/lisa-lab/DeepLearningTutorials/blob/master/code/convolutional_mlp.py
但是类LeNetConvPoolLayer将卷积层和池层组合在一起。当我尝试将这两个部分分成两个类ConvLayer和PoolLayer时，在计算新构建的卷积层中的参数梯度以及汇集时会出现一个名为DisconnectedInputError的错误层。
这是我的代码。谢谢你的帮助！
class ConvLayer(object):
"""Conv Layer of a convolutional network without Pooling """
def __init__(self, rng, input, filter_shape, image_shape):
"""
Allocate a LeNetConvPoolLayer with shared variable internal parameters.
:type rng: numpy.random.RandomState
:param rng: a random number generator used to initialize weights
:type input: theano.tensor.dtensor4
:param input: symbolic image tensor, of shape image_shape
:type filter_shape: tuple or list of length 4
:param filter_shape: (number of filters, num input feature maps,
filter height, filter width)
:type image_shape: tuple or list of length 4
:param image_shape: (batch size, num input feature maps,
image height, image width)
:type poolsize: tuple or list of length 2
:param poolsize: the downsampling (pooling) factor (#rows, #cols)
"""
assert image_shape[1] == filter_shape[1]
self.input = input
# there are "num input feature maps * filter height * filter width"
# inputs to each hidden unit
fan_in = numpy.prod(filter_shape[1:])
# each unit in the lower layer receives a gradient from:
# "num output feature maps * filter height * filter width" /
# pooling size
fan_out = (filter_shape[0] * numpy.prod(filter_shape[2:]))
# initialize weights with random weights
W_bound = numpy.sqrt(6. / (fan_in + fan_out))
self.W = theano.shared(
numpy.asarray(
rng.uniform(low=-W_bound, high=W_bound, size=filter_shape),
dtype=theano.config.floatX
),
borrow=True
)
# the bias is a 1D tensor -- one bias per output feature map
b_values = numpy.zeros((filter_shape[0],), dtype=theano.config.floatX)
self.b = theano.shared(value=b_values, borrow=True)
# convolve input feature maps with filters
conv_out = conv2d(
input=input,
filters=self.W,
filter_shape=filter_shape,
input_shape=image_shape
)
'''
# pool each feature map individually, using maxpooling
pooled_out = pool.pool_2d(
input=conv_out,
ds=poolsize,
ignore_border=True
)
'''
self.output = conv_out
# store parameters of this layer
self.params = [self.W, self.b]
# keep track of model input
self.input = input
class PoolLayer(object):
"""Pool Layer after a convolutional network """
def __init__(self, rng, input, filter_shape=(3, 3), poolsize=(2, 2)):
"""
Allocate a LeNetConvPoolLayer with shared variable internal parameters.
:type rng: numpy.random.RandomState
:param rng: a random number generator used to initialize weights
:type input: theano.tensor.dtensor4
:param input: symbolic image tensor, of shape image_shape
:type filter_shape: tuple or list of length 4
:param filter_shape: (number of filters, num input feature maps,
filter height, filter width)
:type image_shape: tuple or list of length 4
:param image_shape: (batch size, num input feature maps,
image height, image width)
:type poolsize: tuple or list of length 2
:param poolsize: the downsampling (pooling) factor (#rows, #cols)
"""
self.input = input
# there are "num input feature maps * filter height * filter width"
# inputs to each hidden unit
fan_in = numpy.prod(filter_shape[1:])
# each unit in the lower layer receives a gradient from:
# "num output feature maps * filter height * filter width" /
# pooling size
fan_out = (filter_shape[0] * numpy.prod(filter_shape[2:]) //
numpy.prod(poolsize))
# initialize weights with random weights
W_bound = numpy.sqrt(6. / (fan_in + fan_out))
self.W = theano.shared(
numpy.asarray(
rng.uniform(low=-W_bound, high=W_bound, size=filter_shape),
dtype=theano.config.floatX
),
borrow=True
)
# the bias is a 1D tensor -- one bias per output feature map
b_values = numpy.zeros((filter_shape[0],), dtype=theano.config.floatX)
self.b = theano.shared(value=b_values, borrow=True)
# pool each feature map individually, using maxpooling
pooled_out = pool.pool_2d(
input=input,
ds=poolsize,
ignore_border=True
)
# add the bias term. Since the bias is a vector (1D array), we first
# reshape it to a tensor of shape (1, n_filters, 1, 1). Each bias will
# thus be broadcasted across mini-batches and feature map
# width & height
self.output = T.nnet.relu(pooled_out)
# store parameters of this layer
self.params = [self.W, self.b]
# keep track of model input
self.input = input
答案 0 :(得分：0)
这是我正在使用的类的一部分。您可以修改零件以适合您的模型
class ConvLayer(object):
"""Pool Layer of a convolutional network """
def __init__(self, rng, input, image_shape, filter_shape, subsample=(1,1), poolsize=(2, 2), border_mode = 'valid'):
assert image_shape[1] == filter_shape[1]
self.input = input
fan_in = numpy.prod(filter_shape[1:])
fan_out = filter_shape[0] * numpy.prod(filter_shape[2:])
w_values, b_values = generate_weights(rng, filter_shape, fan_in, fan_out, 'relu', filter_shape[0])
self.W = theano.shared(w_values, borrow=True )
self.b = theano.shared(value=b_values, borrow=True)
# convolve input feature maps with filters
conv_out = conv2d(
input=input,
filters=self.W,
input_shape=image_shape,
filter_shape=filter_shape,
subsample=subsample,
border_mode=border_mode
)
self.rectified_conv_out = T.nnet.relu(conv_out + self.b.dimshuffle('x', 0, 'x', 'x'))
self.output = self.rectified_conv_out
class PoolLayer(object):
"""Pool Layer of a convolutional network """
def __init__(self, input, poolsize=(2, 2), stride=None, ig_border = True, mode='max', same=False ):
self.input = input
if same:
pooled_out = pool.max_pool_2d_same_size(
input=self.input,
patch_size=poolsize
)
else:
# downsample each feature map individually
pooled_out = pool.pool_2d(
input= self.input,
ws=poolsize,
ignore_border=ig_border,
stride= stride,
mode= mode
)
self.output = pooled_out