def data():
from init import init_uv
from utils.datasets import load_dataset
from utils.params import Params
X, C, labels = load_dataset('mnist_10k')
return (
X,
*init_uv(
X, C,
Params({
'method': 'random'
})
),
labels
)
def target(self, index):
from init import init_uv
from iterations import run
X, C, labels = load_dataset(self.dataset)
U, V = init_uv(X, C, Params(dict(**self.init_params, **self.mutual)))
initial = {name: (U.copy(), V.copy()) for name in self.params}
result = {}
for name, param in self.params.items():
p = Params({
**param,
**self.mutual, 'initial': initial[name],
'init': 'preset',
'C': C
})
dest = os.path.join(self.root_directory, name + '.h5.' +
str(index)) if self.root_directory else ''
print('running', name)
logger = Logger(dest)
start_time = time()
result = run(X, labels, p, logger)
end_time = time()
time_elasped = end_time - start_time
result = (*result, time_elasped)
print(name, result[2:])
logger.log_final(*result)
logger.close()
return result
model_name = ''.join([str(timestamp), '_', NETWORK, '_', DATASET])
session_logdir = os.path.join(LOGDIR, model_name)
train_logdir = os.path.join(session_logdir, 'train')
test_logdir = os.path.join(session_logdir, 'test')
session_modeldir = os.path.join(MODELDIR, model_name)
# Create folder
if not os.path.exists(session_modeldir):
os.makedirs(session_modeldir)
if not os.path.exists(train_logdir):
os.makedirs(train_logdir)
if not os.path.exists(test_logdir):
os.makedirs(test_logdir)
# dataset preparation using tensorflow dataset iterators
x_train, y_train, x_test, y_test, num_classes = datasets.load_dataset(DATASET)
print(x_train)
print(y_train)
print(x_train.shape[0])
print(x_train.shape[1:])
#sys.exit()
# select batch size
batch_size = tf.placeholder(tf.int64)
data_features, data_labels = tf.placeholder(
tf.float32,
(None, ) + x_train.shape[1:]), tf.placeholder(tf.int32,
(None, ) + y_train.shape[1:])
args = parse_args()
######################################################################################################### Seeding
# Seeding can be annoying in pytorch at the moment. Based on my experience, the below means of seeding
# allows for deterministic experimentation.
torch.manual_seed(args.seed)
np.random.seed(args.seed) # set seed
random.seed(args.seed)
device = 'cuda' if torch.cuda.is_available() else 'cpu'
args.device = device
if device == 'cuda':
torch.cuda.manual_seed_all(args.seed)
torch.backends.cudnn.deterministic = True
######################################################################################################### Data
trainloader, testloader, in_shape = load_dataset(args)
n_train_batches = len(trainloader)
n_train_images = len(trainloader.dataset)
n_test_batches = len(testloader)
n_test_images = len(testloader.dataset)
print("Data loaded successfully ")
print("Training --> {} images and {} batches".format(n_train_images,
n_train_batches))
print("Testing --> {} images and {} batches".format(n_test_images,
n_test_batches))
######################################################################################################### Admin
saved_models_filepath, logs_filepath, images_filepath = build_experiment_folder(
if __name__ == "__main__":
parse = argparse.ArgumentParser()
parse.add_argument("--train-csv-path", type=str, default="data/train.csv", help="Training csv path for label file")
parse.add_argument("--valid-csv-path", type=str, default="data/valid.csv", help="Validation csv path for label file")
parse.add_argument("--test-csv-path", type=str, default="data/test.csv", help="Testing csv path for label file")
parse.add_argument("--batch-size", type=int, default=64, help="Batch size of images")
parse.add_argument("--lr", type=float, default=0.005, help="Learning rate")
parse.add_argument("--momentum", type=float, default=0.9, help="Momentum")
parse.add_argument("--gamma", type=float, default=0.8, metavar="M",
help="Learning rate step gamma (default: 0.7)")
opt = parse.parse_args()
train_loader, valid_loader, test_loader = load_dataset(train_csv_path=opt.train_csv_path,
valid_csv_path=opt.valid_csv_path,
test_csv_path=opt.test_csv_path,
bs=opt.batch_size, workers=2, transform=True)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Initialize model
model = Net()
model.to(device)
# Define hyperparameter, optimizer, loss, scheduler
optimizer = optim.SGD(model.parameters(), lr=opt.lr, momentum=opt.momentum)
loss_fn = nn.CrossEntropyLoss()
# scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=opt.gamma)
train(model, device, train_loader, valid_loader, loss_fn, optimizer, epoch=50)