def CAE_AE_TRAIN(shapes, task_samples, iterations):
global stage
global student_model
global vae_optimizer
student_model = models.CAE() #.to(device)
vae_optimizer = optim.Adam(student_model.parameters(),
lr=0.0001) #, amsgrad=True)
student_model.train()
print("len of takssample is", len(task_samples))
accuracies = np.zeros((iterations, len(task_samples)))
for i in range(0, len(task_samples) - len(Skill_Mu)):
Skill_Mu.append([])
for batch_idx in range(1, iterations):
randPerm = np.random.permutation(len(task_samples))
#randPerm,nReps = helper_functions.biased_permutation(stage+1,nBiased,trainBias,len(task_samples),minReps)
print(randPerm, nReps)
for s in randPerm:
skill = s
vae_optimizer.zero_grad()
data = Variable(torch.FloatTensor(
task_samples[skill])) #.to(device)
hidden_representation, recons_x = student_model(data)
W = student_model.state_dict()['fc2.weight']
loss, con_mse, con_loss, closs_mul_lam = helper_functions.Contractive_loss_function(
W, data.view(-1, 61326), recons_x, hidden_representation, lam)
Skill_Mu[skill] = hidden_representation
loss.backward()
vae_optimizer.step()
print('Train Iteration: {},tLoss: {:.6f},picked skill {}'.format(
batch_idx, loss.data[0], skill))
if batch_idx % 1 == 0:
values = 0
for i in range(0, len(task_samples)):
mu1 = Skill_Mu[i][0]
task_sample = student_model.decoder(mu1).cpu()
sample = task_sample.data.numpy().reshape(61326)
#print('MSE IS',i,mean_squared_error(task_sample.data.numpy(),Variable(torch.FloatTensor(task_samples[i])).data.numpy()))
#mse=mean_squared_error(task_sample.data.numpy(),Variable(torch.FloatTensor(task_samples[i])).data.numpy())
final_weights = helper_functions.unFlattenNetwork(
sample, shapes)
loadWeights_cifar(final_weights, net)
if i >= 6:
load_individual_class([i], [0, 1, 2, 3])
else:
load_individual_class([i], [6, 7, 8, 9])
Avg_Accuracy = test()
accuracies[batch_idx, i] = Avg_Accuracy
if round(Avg_Accuracy + 0.5) >= int(Actual_Accuracy[i]):
values = values + 1
if values == len(task_samples):
print("########## \n Batch id is", batch_idx, "\n#########")
threshold_batchid.append(batch_idx)
break
stage = stage + 1
return accuracies
model.conv1.weight.data = torch.from_numpy(weights_to_load[0]).cuda()
model.conv1.bias.data = torch.from_numpy(weights_to_load[1]).cuda()
model.conv2.weight.data = torch.from_numpy(weights_to_load[2]).cuda()
model.conv2.bias.data = torch.from_numpy(weights_to_load[3]).cuda()
model.fc1.weight.data = torch.from_numpy(weights_to_load[4]).cuda()
model.fc1.bias.data = torch.from_numpy(weights_to_load[5]).cuda()
model.fc2.weight.data = torch.from_numpy(weights_to_load[6]).cuda()
model.fc2.bias.data = torch.from_numpy(weights_to_load[7]).cuda()
return model
print("device is ", device)
#model = models.Net().to(device)
#model_reset= models.Net().to(device)
#optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
student_model = models.CAE().to(
device) #nn.DataParallel(models.CAE().to(device))
teacher_model = models.CAE().to(
device) #nn.DataParallel(models.CAE().to(device))
vae_optimizer = optim.Adam(student_model.parameters(), lr=0.0001)
lam = 0.001
Actual_Accuracy = []
threshold_batchid = []
Actual_task_net_weights = []
# win = vis.line(
# X=np.array([0]),
# Y=np.array([0]),
# win="test",
# name='Line1',
# )
#####################################################################################################################
# For Viewing the test/train images-just for confirmation
Flat_input,net_shapes=helper_functions.flattenNetwork(model.cpu())
final_skill_sample.append(Flat_input)
if len(task_samples)==0:
accuracies = CAE_AE_TRAIN(net_shapes,task_samples+final_skill_sample,100)
else:
accuracies = CAE_AE_TRAIN(net_shapes,task_samples+final_skill_sample,300)
return accuracies
######################################################################################################
# GLOBAL VARIABLES
######################################################################################################
#net=models.Net().to(device)
net_reset=models.Net().to(device)
Actual_Accuracy=[]
criterion = nn.CrossEntropyLoss()
student_model=models.CAE()#.to(device)
teacher_model=models.CAE().to(device)
vae_optimizer = optim.Adam(student_model.parameters(), lr = 0.0001)#, amsgrad=True)
lam = 0.001
Actual_Accuracy=[]
threshold_batchid=[]
#biased training variables
nSamples = 10
nBiased = min(nSamples,10)
trainBias = 0.5
minReps = 1
nReps = 30
stage=0
addRepsTotal = nReps*minReps
#####################################################################################################################
# CAE TRAIN AND CIFAR TEST #