I am doing classification challenge, i want to ensemble different CNN models to improve the accuracy of the classification. i have see the similar question https://discuss.pytorch.org/t/custom-ensemble-approach/52024 but i stil feel confuse.
this is one of the answer：
class MyModelA(nn.Module):
def __init__(self):
super(MyModelA, self).__init__()
self.fc1 = nn.Linear(10, 2)
def forward(self, x):
x = self.fc1(x)
return x
class MyModelB(nn.Module):
def __init__(self):
super(MyModelB, self).__init__()
self.fc1 = nn.Linear(20, 2)
def forward(self, x):
x = self.fc1(x)
return x
class MyEnsemble(nn.Module):
def __init__(self, modelA, modelB):
super(MyEnsemble, self).__init__()
self.modelA = modelA
self.modelB = modelB
self.classifier = nn.Linear(4, 2)
def forward(self, x1, x2):
x1 = self.modelA(x1)
x2 = self.modelB(x2)
x = torch.cat((x1, x2), dim=1)
x = self.classifier(F.relu(x))
return x
# Create models and load state_dicts
modelA = MyModelA()
modelB = MyModelB()
# Load state dicts
modelA.load_state_dict(torch.load(PATH))
modelB.load_state_dict(torch.load(PATH))
model = MyEnsemble(modelA, modelB)
x1, x2 = torch.randn(1, 10), torch.randn(1, 20)
output = model(x1, x2)
another answer：https://discuss.pytorch.org/t/how-to-train-an-ensemble-of-two-cnns-and-a-classifier/3026/8
one of is to use the torch.cat() . but another to use the “+”, which answer is more suitable for my classification.
this is part of my code.
if opt.model == 'VGG19':
net = VGG('VGG19')
elif opt.model == 'Resnet18':
net = ResNet18()
if opt.resume:
# Load checkpoint.
print('==> Resuming from checkpoint..')
assert os.path.isdir(path), 'Error: no checkpoint directory found!'
checkpoint = torch.load(os.path.join(path,'PrivateTest_model.t7'))
net.load_state_dict(checkpoint['net'])
best_PublicTest_acc = checkpoint['best_PublicTest_acc']
best_PrivateTest_acc = checkpoint['best_PrivateTest_acc']
best_PrivateTest_acc_epoch = checkpoint['best_PublicTest_acc_epoch']
best_PrivateTest_acc_epoch = checkpoint['best_PrivateTest_acc_epoch']
start_epoch = checkpoint['best_PrivateTest_acc_epoch'] + 1
else:
print('==> Building model..')
if use_cuda:
net.cuda()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=opt.lr, momentum=0.9, weight_decay=5e-4)
# Training
def train(epoch):
print('\nEpoch: %d' % epoch)
global Train_acc
net.train()
train_loss = 0
correct = 0
total = 0
if epoch > learning_rate_decay_start and learning_rate_decay_start >= 0:
frac = (epoch - learning_rate_decay_start) // learning_rate_decay_every
decay_factor = learning_rate_decay_rate ** frac
current_lr = opt.lr * decay_factor
utils.set_lr(optimizer, current_lr) # set the decayed rate
else:
current_lr = opt.lr
print('learning_rate: %s' % str(current_lr))
for batch_idx, (inputs, targets) in enumerate(trainloader):
if use_cuda:
inputs, targets = inputs.cuda(), targets.cuda()
optimizer.zero_grad()
inputs, targets = Variable(inputs), Variable(targets)
outputs = net(inputs)
loss = criterion(outputs, targets)
loss.backward()
utils.clip_gradient(optimizer, 0.1)
optimizer.step()
train_loss += loss.data[0]
_, predicted = torch.max(outputs.data, 1)
total += targets.size(0)
correct += predicted.eq(targets.data).cpu().sum()
utils.progress_bar(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
% (train_loss/(batch_idx+1), 100.*correct/total, correct, total))
Train_acc = 100.*correct/total
Please help me， thanks so much