class ShallowConvNet(Net):
def __init__(self, device=torch.device('cuda:0')):
super().__init__(device)
self.conv1 = Conv(1, 6, kernel_size=5, noise_std=1e-0, act='TanH', device=self.device)
self.act1 = Activation('TanH')
self.pool1 = Pool(2, device=self.device)
self.fc1 = Linear(6*12*12, 100, noise_std=1e-0, act='TanH', device=self.device)
self.act2 = Activation('TanH')
self.fc2 = Linear(100, 10, noise_std=1e-0, act='TanH', device=self.device)
self.softmax = Activation('Softmax')
self.layers = [self.conv1, self.fc1, self.fc2]
def forward(self, input):
conv_out_1 = self.conv1.forward(input)
act_out_1 = self.act1.forward(conv_out_1)
pool_out_1 = self.pool1.forward(act_out_1)
pool_out_1 = pool_out_1.reshape(len(pool_out_1), -1)
fc_out_1 = self.fc1.forward(pool_out_1)
act_out_2 = self.act2.forward(fc_out_1)
fc_out_2 = self.fc2.forward(act_out_2)
output = self.softmax.forward(fc_out_2)
return output
class DenseNet(Net):
def __init__(self, device=torch.device('cuda:0')):
super().__init__(device)
self.fc1 = Linear(28*28, 50, noise_std=1e-0, device=self.device)
self.act1 = Activation('TanH')
self.fc2 = Linear(50, 10, noise_std=1e-0, device=self.device)
self.softmax = Activation('Softmax')
self.layers = [self.fc1, self.fc2]
def forward(self, input):
input = input.reshape(len(input), -1)
fc_out_1 = self.fc1.forward(input)
act_out_1 = self.act1.forward(fc_out_1)
fc_out_2 = self.fc2.forward(act_out_1)
output = self.softmax.forward(fc_out_2)
return output
class LeNet5(Net):
def __init__(self, device=torch.device('cuda:0')):
super().__init__(device)
self.conv1 = Conv(1, 6, kernel_size=5, noise_std=1e-0, act='ReLU', device=self.device)
self.act1 = Activation('ReLU')
self.pool1 = Pool(2, device=self.device)
self.conv2 = Conv(6, 16, kernel_size=5, noise_std=1e-0, act='ReLU', device=self.device)
self.act2 = Activation('ReLU')
self.pool2 = Pool(2, device=self.device)
self.fc1 = Linear(256, 120, noise_std=1e-0, act='ReLU', device=self.device)
self.act3 = Activation('ReLU')
self.fc2 = Linear(120, 84, noise_std=1e-0, act='ReLU', device=self.device)
self.act4 = Activation('ReLU')
self.fc3 = Linear(84, 10, noise_std=1e-0, act='ReLU', device=self.device)
self.softmax = Activation('Softmax')
self.layers = [self.conv1, self.conv2, self.fc1, self.fc2, self.fc3]
def forward(self, input):
conv_out_1 = self.conv1.forward(input)
act_out_1 = self.act1.forward(conv_out_1)
pool_out_1 = self.pool1.forward(act_out_1)
conv_out_2 = self.conv2.forward(pool_out_1)
act_out_2 = self.act2.forward(conv_out_2)
pool_out_2 = self.pool2.forward(act_out_2)
pool_out_2 = pool_out_2.reshape(len(pool_out_2), -1)
fc_out_1 = self.fc1.forward(pool_out_2)
act_out_3 = self.act3.forward(fc_out_1)
fc_out_2 = self.fc2.forward(act_out_3)
act_out_4 = self.act4.forward(fc_out_2)
fc_out_3 = self.fc3.forward(act_out_4)
output = self.softmax.forward(fc_out_3)
return output
class DenseNet_CNN(Net):
def __init__(self, device=torch.device('cuda:0')):
super().__init__(device)
# self.fc1 = Linear(28*28, 25, noise_std=1e-0, device=self.device)
self.fc1 = Conv(1, 25, kernel_size=25, noise_std=1e-0, act='TanH', device=self.device)
self.act1 = Activation('TanH')
self.fc2 = Linear(16*25, 10, noise_std=1e-0, device=self.device)
self.softmax = Activation('Softmax')
self.layers = [self.fc1, self.fc2]
def forward(self, input):
#input = input.reshape(len(input), -1)
fc_out_1 = self.fc1.forward(input)
act_out_1 = self.act1.forward(fc_out_1)
act_out_1 = act_out_1.reshape(len(act_out_1), -1)
fc_out_2 = self.fc2.forward(act_out_1)
output = self.softmax.forward(fc_out_2)
return output
activation1 = Sigmoid()
# activation2=Sigmoid()
activation2 = Activation("sigmoid")
loss_func = MSE()
#Forward Pass
# Dense -> Activation -> Dense -> Activation -> y_pred
z1 = dense.forward(x)
a1 = activation1.forward(z1)
print("Activation Value:", a1)
z2 = dense2.forward(a1)
a2 = activation2.forward(z2)
y_pred = a2
loss = loss_func.loss(y_true, y_pred)
print("Individual Loss:", loss)
total_loss = np.mean(loss)
print("Total Loss:", total_loss)
#Backward Propagation
dLdy_pred = loss_func.gradient(y_true, y_pred)
print("dLdy:", dLdy_pred)
'''
dydz=activation2.gradient(z2)
dLdz2-dLdy_pred*dydz