def main():
args = parse_args()
bot_config, web_config, db_config = load_config(args.config_path)
web_app = init_web_app(web_config)
globibot = Globibot(bot_config, db_config, web_app, args.plugin_path)
run_async(web_app.run(), globibot.boot())
def main():
args = parse_args()
bot_config, web_config, db_config = load_config(args.config_path)
web_app = init_web_app(web_config)
globibot = Globibot(
bot_config,
db_config,
web_app,
args.plugin_path
)
run_async(
web_app.run(),
globibot.boot()
)
clients = [
Client(copy.deepcopy(extractor), self.trainloader[i], server,
self.args, self.cls_num_list[i], epoch)
for i in range(len(self.trainloader))
]
client_w = None
for client in clients:
print(f"| Global Round: {epoch} | client index: {index} |")
client.train(client_w)
client_w = client.get_weight()
index += 1
return client_w, server.get_weight()
if __name__ == "__main__":
args = parse_args()
data_name = 'cifar10' if not args.cifar100 else 'cifar100'
num_classes = 10 if not args.cifar100 else 100
TAG = 'multi-mixsl-mixsum' + str(
args.mix_num) + '-' + data_name + '-' + args.name
print(f'{TAG}: training start....')
setup_seed(args.seed, True if args.gpu > -1 else False)
logs = []
if args.cifar100:
train_dataset, test_dataset = get_cifar100(args.balanced)
else:
train_dataset, test_dataset = get_cifar10(args.balanced)
user_groups = random_avg_strategy(train_dataset, args.num_users)
cls_num_per_clients = count_class_num_per_client(train_dataset,
user_groups, 100)
logs_file = TAG
])
z_all = torch.from_numpy(np.array(z_all))
model.n_query = n_query
scores = model.set_forward(z_all, is_feature=True)
pred = scores.data.cpu().numpy().argmax(axis=1)
y = np.repeat(range(n_way), n_query)
acc = np.mean(pred == y) * 100
return acc
# --- main ---
if __name__ == '__main__':
# parse argument
params = parse_args('test')
print('Testing! {} shots on {} dataset with {} epochs of {}({})'.format(
params.n_shot, params.dataset, params.save_epoch, params.name,
params.method))
remove_featurefile = True
print('\nStage 1: saving features')
# dataset
print(' build dataset')
image_size = 224
split = params.split
loadfile = os.path.join(params.data_dir, params.dataset, split + '.json')
datamgr = SimpleDataManager(image_size, batch_size=64)
data_loader = datamgr.get_data_loader(loadfile, aug=False)
print(' build feature encoder')
print('GG!! best accuracy {:f}'.format(max_acc))
if ((epoch + 1) % params.save_freq==0) or (epoch == stop_epoch - 1):
outfile = os.path.join(params.checkpoint_dir, '{:d}.tar'.format(epoch + 1))
model.save(outfile, epoch)
return
# --- main function ---
if __name__=='__main__':
# set numpy random seed
np.random.seed(10)
# parse argument
params = parse_args('train')
print('--- LFTNet training: {} ---\n'.format(params.name))
print(params)
# outputs and tensorboard dir
params.tf_dir = './logs/%s'%(params.name)
params.checkpoint_dir = '%s/checkpoints/%s'%(params.save_dir, params.name)
ensurepath(params.tf_dir)
ensurepath(params.checkpoint_dir)
# dataloader
print('\n--- prepare dataloader ---')
print(' train with multiple seen domains (unseen domain: {})'.format(params.testset))
datasets = ['miniImagenet', 'cars', 'places', 'cub', 'plantae']
datasets.remove(params.testset)
val_file = os.path.join(params.data_dir, 'miniImagenet', 'val.json')