DNN2_net=MLP(DNN2_arch)
DNN2_net.cuda()
if pt_file!='none':
print('LOADING MODEL.')
checkpoint_load = torch.load(pt_file)
CNN_net.load_state_dict(checkpoint_load['CNN_model_par'])
DNN1_net.load_state_dict(checkpoint_load['DNN1_model_par'])
DNN2_net.load_state_dict(checkpoint_load['DNN2_model_par'])
optimizer_CNN = optim.RMSprop(CNN_net.parameters(), lr=lr,alpha=0.95, eps=1e-8)
optimizer_DNN1 = optim.RMSprop(DNN1_net.parameters(), lr=lr,alpha=0.95, eps=1e-8)
optimizer_DNN2 = optim.RMSprop(DNN2_net.parameters(), lr=lr,alpha=0.95, eps=1e-8)
# print("----------------------")
# print(DNN2_net(DNN1_net(CNN_net(3200))))
#for epoch in range(N_epochs):
test_flag=0
CNN_net.train()
DNN1_net.train()
DNN2_net.train()
loss_sum=0
err_sum=0
'fc_use_laynorm': class_use_laynorm,
'fc_use_laynorm_inp': class_use_laynorm_inp,
'fc_use_batchnorm_inp': class_use_batchnorm_inp,
'fc_act': class_act,
}
DNN2_net = MLP(DNN2_arch)
DNN2_net.cuda()
if pt_file != 'none':
checkpoint_load = torch.load(pt_file)
CNN_net.load_state_dict(checkpoint_load['CNN_model_par'])
DNN1_net.load_state_dict(checkpoint_load['DNN1_model_par'])
DNN2_net.load_state_dict(checkpoint_load['DNN2_model_par'])
optimizer_CNN = optim.RMSprop(CNN_net.parameters(),
lr=lr,
alpha=0.95,
eps=1e-8)
optimizer_DNN1 = optim.RMSprop(DNN1_net.parameters(),
lr=lr,
alpha=0.95,
eps=1e-8)
optimizer_DNN2 = optim.RMSprop(DNN2_net.parameters(),
lr=lr,
alpha=0.95,
eps=1e-8)
for epoch in range(N_epochs):
test_flag = 0