def get(self):
test_model = test()
self.write(test_model.f() + "_blog")
def main_worker(gpu, ngpus_per_node, args):
print("gpu:", gpu)
args.gpu = gpu
if args.rank == 0: #(第一台服务器只有三台GPU，需要特殊处理)
newrank = args.rank * ngpus_per_node + gpu
else:
newrank = args.rank * ngpus_per_node + gpu - 1
#初始化,使用tcp方式进行通信
print("begin init")
dist.init_process_group(init_method=args.init_method,
backend="nccl",
world_size=args.world_size,
rank=newrank)
print("end init")
#建立通信group,rank=0作为server，用broadcast模拟send和rec，需要server和每个client建立group
group = []
for i in range(1, args.world_size):
group.append(dist.new_group([0, i]))
allgroup = dist.new_group([i for i in range(args.world_size)])
if newrank == 0:
""" server"""
print("使用{}号服务器的第{}块GPU作为server".format(args.rank, gpu))
#在模型训练期间，server只负责整合参数并分发，不参与任何计算
#设置cpu
args.device = torch.device(
'cuda:{}'.format(args.gpu)
if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
net = CNNMnist().to(args.device)
w_avg = copy.deepcopy(net.state_dict())
for j in range(args.epochs):
if j == args.epochs - 1:
for i in w_avg.keys():
temp = w_avg[i].to(args.device)
w_avg[i] = average_gradients(temp, group, allgroup)
else:
for i in w_avg.keys():
temp = w_avg[i].to(args.device)
average_gradients(temp, group, allgroup)
torch.save(w_avg, 'w_wag')
net.load_state_dict(w_avg)
#加载测试数据
trans_mnist = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])
dataset_test = datasets.MNIST('data/',
train=False,
download=True,
transform=trans_mnist)
test_set = torch.utils.data.DataLoader(dataset_test,
batch_size=args.bs)
test_accuracy, test_loss = test(net, test_set, args)
print("Testing accuracy: {:.2f}".format(test_accuracy))
print("Testing loss: {:.2f}".format(test_loss))
else:
"""clents"""
print("使用{}号服务器的第{}块GPU作为第{}个client".format(args.rank, gpu, newrank))
#设置gpu
args.device = torch.device(
'cuda:{}'.format(args.gpu)
if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
print("begin train...")
net = CNNMnist().to(args.device)
print(net)
data = torch.load("data/distributed/data_of_client{}".format(newrank))
bsz = 64
train_set = torch.utils.data.DataLoader(data, batch_size=bsz)
optimizer = torch.optim.SGD(net.parameters(), lr=args.lr, momentum=0.5)
num_batches = ceil(len(train_set.dataset) / float(bsz))
start = time.time()
for epoch in range(args.epochs):
for iter in range(3):
epoch_loss = 0.0
for data, target in train_set:
data, target = data.to(args.device), target.to(args.device)
data, target = Variable(data), Variable(target)
optimizer.zero_grad()
output = net(data)
loss = F.nll_loss(output, target)
epoch_loss += loss.item()
loss.backward()
optimizer.step()
if iter == 3 - 1:
print('Rank ', dist.get_rank(), ', epoch ', epoch, ': ',
epoch_loss / num_batches)
"""federated learning"""
w_avg = copy.deepcopy(net.state_dict())
for k in w_avg.keys():
print("k:", k)
temp = average_gradients(w_avg[k].to(args.device), group,
allgroup)
w_avg[k] = temp
net.load_state_dict(w_avg)
end = time.time()
print(" training time:{}".format((end - start)))
train_accuracy, train_loss = test(net, train_set, args)
print("Training accuracy: {:.2f}".format(train_accuracy))
print("Training loss: {:.2f}".format(train_loss))
def get(self):
test_model = test()
self.write(test_model.f() + "_blog")
device = torch.device('cpu')
elif torch.cuda.is_available() and args.use_gpu:
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
else:
device = torch.device('cpu')
model.to(device)
logger.info('Running with device %s', device)
transform = torchvision.transforms.Compose(
[torchvision.transforms.ToTensor()])
if args.test:
test_dataset = XrayImageFolder(args.test_data, transform=transform)
test_dataloader = DataLoader(test_dataset, batch_size=cfg.BATCH_SIZE)
test(model, test_dataloader, device)
elif args.inference:
img = cv2.imread(args.img_path)
try:
img = transform(img).unsqueeze(0)
except TypeError:
logger.exception('Possible incorrect image path or image type')
start_time = datetime.now()
with torch.no_grad():
img = img.to(device)
output = model.inference(img)
label = output.data.argmax()
prob = output.detach()[0][label].item() * 100
def get(self):
test_model = test()
self.write(test_model.f() + "_admin")
print('run')
for i in range(opt.begin_epoch, opt.n_epochs + 1):
if not opt.no_train:
train_epoch(i, train_loader, model, criterion, optimizer, opt,
train_logger, train_batch_logger)
if not opt.no_val:
validation_loss = val_epoch(i, val_loader, model, criterion, opt,
val_logger)
if not opt.no_train and not opt.no_val:
scheduler.step(validation_loss)
if opt.test:
spatial_transform = Compose([
Scale(int(opt.sample_size / opt.scale_in_test)),
CornerCrop(opt.sample_size, opt.crop_position_in_test),
ToTensor(opt.norm_value), norm_method
])
temporal_transform = LoopPadding(opt.sample_duration)
target_transform = VideoID()
test_data = get_test_set(opt, spatial_transform, temporal_transform,
target_transform)
test_loader = torch.utils.data.DataLoader(
test_data,
batch_size=opt.batch_size,
shuffle=False,
num_workers=opt.n_threads,
pin_memory=True)
test.test(test_loader, model, opt, test_data.class_names)
