for g in optimizer.param_groups:
g['lr'] = new_lr
return new_lr
if __name__ == '__main__':
use_cuda = len(sys.argv) > 1 and sys.argv[1] == 'cuda'
num_epochs = 80
# get cifar 10 data
trainloader, testloader = get_dataset()
benchmark, debug = False, True
resnet = Resnet(n=2,dbg=debug)
resnet.train()
if use_cuda:
resnet = resnet.cuda()
for block in resnet.residual_blocks:
block.cuda()
current_lr = 1e-4
# optimizer = optim.SGD(resnet.parameters(), lr=current_lr, weight_decay=0.0001, momentum=0.9)
optimizer = optim.Adam(resnet.parameters(), lr=1e-4, weight_decay=0.0001)
train_accs, test_accs = [], []
gradient_norms = []
def train_model():
current_lr=1e-4
stopping_threshold, current_count = 3, 0
n_iters = 0
for e in range(num_epochs):
# modify learning rate at
for i, data in enumerate(trainloader, 0):
x, y = data
if __name__ == '__main__':
transform = transforms.Compose([transforms.RandomResizedCrop(224),transforms.ToTensor() ,transforms.Normalize((0.5 , 0.5 , 0.5) , (0.5 , 0.5 , 0.5))])
# trainset = torchvision.datasets.CIFAR10(root = './data' , train = True , download = True , transform = transform)
# trainloader = torch.utils.data.DataLoader(trainset , batch_size = 256 , shuffle = True , num_workers =2)
testset = torchvision.datasets.CIFAR10(root = './data' , train = False , download = True , transform = transform)
testloader = torch.utils.data.DataLoader(testset , batch_size = 9 , shuffle = False , num_workers = 2)
# classes = ('plane' , 'car' , 'bird' , 'cat' , 'deer' , 'dog' , 'frog' , 'horse' , 'ship' , 'truck')
os.environ['CUDA_VISIBLE_DEVICES'] = "3"
#
#
resnet = Resnet()
device_ids=[0]
resnet = resnet.cuda(device_ids[0])
net=torch.nn.DataParallel(resnet,device_ids=device_ids)
#
# read model
print('===> Try load checkpoint')
if os.path.isdir('checkpoint'):
try:
checkpoint = torch.load('./checkpoint/resnet_final.t7')
net.load_state_dict(checkpoint['state'])
start_epoch = checkpoint['epoch']
print('===> Load last checkpoint data')
except FileNotFoundError:
start_epoch = 0
print('Can\'t found resnet_final.t7')
else:
start_epoch = 0
