batch_size=batch_size,
shuffle=True,
num_workers=num_workers)
for x in ['train', 'val']
}
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(),
lr=learning_rate,
weight_decay=weight_decay)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer,
'min',
verbose=True)
model = model.to(device)
model = train(model,
data_loader,
criterion,
optimizer,
scheduler,
num_epochs=num_epoches)
n_datapoints = len(model.train_epoch_loss)
# save it in a dictionary, recommended to export by having save_csv = True
d = {
'neuralnet':
model.name,
'lr':
learning_rate,
net = AlexNet(5)
checkpoint_path = 'cifar_10_alexnet.t7'
checkpoint = torch.load(checkpoint_path,map_location=torch.device('cpu'))
try:
net.load_state_dict(checkpoint['net'])
except:
new_check_point = OrderedDict()
for k, v in checkpoint['net'].items():
name = k[7:] # remove `module.`
# name = k[9:] # remove `module.1.`
new_check_point[name] = v
net.load_state_dict(new_check_point)
net = net.to(device)
if device == 'cuda':
net = torch.nn.DataParallel(net)
cudnn.benchmark = True
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=args.lr, momentum=0.9, weight_decay=5e-4)
#
# # Training
# def main():
# AV = [[] for _ in range(5)]
# MAV = [[] for _ in range(5)]
from alexnet import AlexNet
from utils import cifar10_loader, device
trainloader = cifar10_loader(train=True)
testloader = cifar10_loader(train=False)
writer = SummaryWriter("./logs")
epochs = 100
batch_size = 128
log_batch = 200
train_metrics = []
test_metrics = []
net = AlexNet()
net.to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
def train():
for epoch in range(epochs):
running_loss = 0.0
correct_classified = 0
total = 0
start_time = time.time()
for i, data in enumerate(trainloader):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
outputs = net(inputs)
