def get_hidden_values(self, input):
""" Computes the values of the hidden layer.
Arguments:
input: the data to feed through the input layer to the
hidden layer.
Returns:
The encoded (lower dimensional) feature vector for a given
asin in the form of a 1 hot encoding vector.
"""
if type(input) == T.TensorVariable:
sparse_input = basic.csc_from_dense(input)
else:
sparse_input = input
lin_output = basic.dot(sparse_input, self.W)
if self.activation is None and self.b is None:
return lin_output
elif self.activation is None:
return lin_output + self.b
elif self.b is None:
return self.activation(lin_output)
else:
return self.activation(lin_output + self.b)
def reconstruct_input(samples, labels, c, count):
# feed through the network and write out
samples = basic.csc_from_dense(samples.toarray())
h = da.get_hidden_values(samples)
z = h.eval() #da.get_reconstructed_input(h).eval()
# write out to file
dataDict = dict()
with open(get_reconstruction_output_path(dataset), "a+") as handle:
idx = count - MINI_BATCH_SIZE + 1
for sample in z:
dataDict[idx] = dict()
dataDict[idx]["x"] = sample.tolist()
dataDict[idx]["y"] = sample.tolist()
idx = idx + 1
handle.write(json.dumps(dataDict)+"\n")
return c
def get_hidden_values(self, input):
#if type(input) != basic.SparseVariable:
if type(input) == T.TensorVariable:
sparse_input = basic.csc_from_dense(input)
else:
sparse_input = input
#x_is_sparse_variable = basic._is_sparse_variable(input)
#w_is_sparse_variable = basic._is_sparse_variable(self.W)
#if not x_is_sparse_variable and not w_is_sparse_variable:
# fn = T.dot
#else:
# fn = basic.dot
lin_output = basic.dot(sparse_input, self.W)
if self.activation is None and self.b is None:
return lin_output
elif self.activation is None:
return lin_output + self.b
elif self.b is None:
return self.activation(lin_output)
else:
return self.activation(lin_output + self.b)
