def forward_propagation(self, x):
"""
Runs a forward propagation of the model for a batch of examples, activating
all layers besides the top one.
The function should return the linear input to the top layer, i.e.,
non-normalized scores, with higher scores corresponding to greater
probability of an image belonging a particular class.
Inputs:
x: batch with shape [batch_size, 1, 28, 28]
Output:
A Tensor with shape [batch_size, 10] containing predicted scores (logits)
"""
# normalize data to improve performance
x = x / 127.5 - 1.0
# flatten the input image data to a 2d matrix in the shape [N, d]
x = nn.reshape(x, [x.shape[0], -1], inplace=True)
# define the structure of the network to get the logits result from x
#######################################################################
"*** YOUR CODE HERE ***"
logits = None
hidden1=nn.matmul(x,self.param['w1'])+self.param['b1']
z1=nn.relu(hidden1)
hidden2=nn.matmul(z1,self.param['w2'])+self.param['b2']
#z2=nn.ReLU(hidden2)
logits=hidden2
#######################################################################
return logits
def forward_propagation(self, x):
"""
Runs a forward propagation of the model for a batch of examples, activating
all layers besides the top one.
The function should return the linear input to the top layer, i.e.,
non-normalized scores, with higher scores corresponding to greater
probability of an image belonging a particular class.
Inputs:
x: batch with shape [batch_size, 1, 28, 28]
Output:
A Tensor with shape [batch_size, 10] containing predicted scores (logits)
"""
# normalize data to improve performance
x = x / 127.5 - 1.0
# flatten the input image data to a 2d matrix in the shape [N, d]
x = nn.reshape(x, [x.shape[0], -1], inplace=True)
# define the structure of the network to get the logits result from x
#######################################################################
"*** YOUR CODE HERE ***"
y1 = nn.matmul(x, self.param["w"]) + self.param["b"]
y1 = nn.relu(y1)
y2 = nn.matmul(y1, self.param["w1"]) + self.param["b1"]
y2 = nn.relu(y2)
'''
y3 = nn.matmul(y2_out, self.param["w2"]) + self.param["b2"]
y3_out = nn.relu(y3)
y4 = nn.matmul(y3_out, self.param["w3"]) + self.param["b3"]
y4_out = nn.relu(y4)
'''
logits = nn.matmul(y2, self.param["w2"]) + self.param["b2"]
#logits = nn.sigmoid(logits)
#######################################################################
return logits