def main():
logger.info("Logger is set - training start")
logger.info("Torch version is: {}".format(torch.__version__))
logger.info("Torch_vision version is: {}".format(torchvision.__version__))
# set default gpu device id
torch.cuda.set_device(config.gpus[0])
# set seed
np.random.seed(config.seed)
torch.manual_seed(config.seed)
torch.cuda.manual_seed_all(config.seed)
# using deterministic
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.enabled = True
# get data with meta info
input_size, input_channels, n_classes, train_data, valid_data = utils.get_data(
config.dataset,
config.data_path,
config.cutout_length,
validation=True)
criterion = nn.CrossEntropyLoss().to(device)
use_aux = config.aux_weight > 0.
model = AugmentCNN(input_size, input_channels, config.init_channels,
n_classes, config.layers, use_aux, config.genotype)
# model size
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
model = nn.DataParallel(model, device_ids=config.gpus).to(device)
# weights optimizer
optimizer = torch.optim.SGD(model.parameters(),
config.lr,
momentum=config.momentum,
weight_decay=config.weight_decay)
# get data loader
if config.data_loader_type == 'Torch':
train_loader = torch.utils.data.DataLoader(
train_data,
batch_size=config.batch_size,
shuffle=True,
num_workers=config.workers,
pin_memory=True)
valid_loader = torch.utils.data.DataLoader(
valid_data,
batch_size=config.batch_size,
shuffle=False,
num_workers=config.workers,
pin_memory=True)
elif config.data_loader_type == 'DALI':
config.dataset = config.dataset.lower()
if config.dataset == 'cifar10':
from DataLoaders_DALI import cifar10
train_loader = cifar10.get_cifar_iter_dali(
type='train',
image_dir=config.data_path,
batch_size=config.batch_size,
num_threads=config.workers)
valid_loader = cifar10.get_cifar_iter_dali(
type='val',
image_dir=config.data_path,
batch_size=config.batch_size,
num_threads=config.workers)
else:
raise NotImplementedError
else:
raise NotImplementedError
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer, config.epochs)
best_top1 = 0.
if config.data_loader_type == 'DALI':
len_train_loader = get_train_loader_len(config.dataset.lower(),
config.batch_size,
is_train=True)
else:
len_train_loader = len(train_loader)
# training loop
for epoch in range(config.epochs):
lr_scheduler.step()
drop_prob = config.drop_path_prob * epoch / config.epochs
model.module.drop_path_prob(drop_prob)
# training
train(train_loader, model, optimizer, criterion, epoch)
# validation
cur_step = (epoch + 1) * len_train_loader
top1 = validate(valid_loader, model, criterion, epoch, cur_step)
# save
if best_top1 < top1:
best_top1 = top1
is_best = True
else:
is_best = False
utils.save_checkpoint(model, config.path, is_best)
print("")
logger.info("Final best Prec@1 = {:.4%}".format(best_top1))
def main():
logger.info("Logger is set - training start")
# set default gpu device id
torch.cuda.set_device(config.gpus[0])
# set seed
np.random.seed(config.seed)
torch.manual_seed(config.seed)
torch.cuda.manual_seed_all(config.seed)
torch.backends.cudnn.benchmark = True
# get data with meta info
input_size, input_channels, n_classes, train_data, valid_data = utils.get_data(
config.dataset, config.data_path, config.cutout_length, validation=True)
criterion = nn.CrossEntropyLoss().to(device)
use_aux = config.aux_weight > 0.
model = AugmentCNN(input_size, input_channels, config.init_channels, n_classes, config.layers,
use_aux, config.genotype)
model = nn.DataParallel(model, device_ids=config.gpus).to(device)
# model size
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
# weights optimizer
optimizer = torch.optim.SGD(model.parameters(), config.lr, momentum=config.momentum,
weight_decay=config.weight_decay)
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=config.batch_size,
shuffle=True,
num_workers=config.workers,
pin_memory=True)
valid_loader = torch.utils.data.DataLoader(valid_data,
batch_size=config.batch_size,
shuffle=False,
num_workers=config.workers,
pin_memory=True)
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, config.epochs)
best_top1 = 0.
# training loop
for epoch in range(config.epochs):
lr_scheduler.step()
drop_prob = config.drop_path_prob * epoch / config.epochs
model.module.drop_path_prob(drop_prob)
# training
train(train_loader, model, optimizer, criterion, epoch)
# validation
cur_step = (epoch+1) * len(train_loader)
top1 = validate(valid_loader, model, criterion, epoch, cur_step)
# save
if best_top1 < top1:
best_top1 = top1
is_best = True
else:
is_best = False
timebudget.report()
utils.save_checkpoint(model, config.path, is_best)
print("")
logger.info("Final best Prec@1 = {:.4%}".format(best_top1))
def evaluation(sample, name):
geno = eval(convert_sample_to_genotype(sample))
logger.info('Model sample: {}'.format(sample))
logger.info('Genotype: {}'.format(str(geno)))
# get data with meta info
input_size, input_channels, n_classes, train_data, valid_data = utils.get_data(
'cifar10',
args.data_path,
config['image_size'],
config['cutout_length'],
validation=True)
criterion = nn.CrossEntropyLoss().to(device)
use_aux = True
# change size of input image
input_size = config['image_size']
model = AugmentCNN(input_size, input_channels, config['init_channels'], 10,
config['layers'], True, geno)
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
model = nn.DataParallel(model, device_ids=[0]).to(device)
# weights optimizer
optimizer = torch.optim.SGD(model.parameters(),
config['lr'],
momentum=0.9,
weight_decay=3e-4)
# get data loader
train_loader = torch.utils.data.DataLoader(train_data, batch_size=config['batch_size'], \
shuffle=True, num_workers=4, pin_memory=True)
valid_loader = torch.utils.data.DataLoader(valid_data, batch_size=config['batch_size'], \
shuffle=True, num_workers=4, pin_memory=True)
# lr scheduler
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer, config['epochs'])
best_top1 = 0.
len_train_loader = len(train_loader)
# training loop
for epoch in range(config['epochs']):
lr_scheduler.step()
drop_prob = 0.2 * epoch / config['epochs']
model.module.drop_path_prob(drop_prob, config['fp'])
train(train_loader, model, optimizer, criterion, epoch)
cur_step = (epoch + 1) * len_train_loader
top1 = validate(valid_loader, model, criterion, epoch, cur_step)
if best_top1 < top1:
best_top1 = top1
is_best = True
else:
is_best = False
# utils.save_checkpoint(model, config.path, is_best)
logger.info("Final best Prec@1 = {:.4%}".format(best_top1))
return best_top1, geno
def main():
logger.info("Logger is set - training start")
# set default gpu device id
torch.cuda.set_device(config.gpus[0])
# set seed
np.random.seed(config.seed)
torch.manual_seed(config.seed)
torch.cuda.manual_seed_all(config.seed)
torch.backends.cudnn.benchmark = True
# get data with meta info
#input_size, input_channels, n_classes, train_data, valid_data = utils.get_data(
# config.dataset, config.data_path, config.cutout_length, validation=True)
input_size, input_channels, n_classes, train_data, test_dat, val_dat = utils.get_data(
config.dataset,
config.data_path,
cutout_length=0,
validation=True,
validation2=True)
print('input_size', input_size)
criterion = nn.CrossEntropyLoss().to(device)
use_aux = config.aux_weight > 0.
#from evaluate
#model = SearchCNNController(input_channels, config.init_channels, n_classes, config.layers,
# net_crit, device_ids=config.gpus)
model = AugmentCNN(input_size, input_channels, config.init_channels,
n_classes, config.layers, use_aux, config.genotype)
model = nn.DataParallel(model, device_ids=config.gpus).to(device)
# model size
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
# weights optimizer
optimizer = torch.optim.SGD(model.parameters(),
config.lr,
momentum=config.momentum,
weight_decay=config.weight_decay)
# split data to train/validation
best_top1 = 0.
best_top_overall = -999
n_train = len(train_data)
n_val = len(val_dat)
n_test = len(test_dat)
split = n_train // 2
indices1 = list(range(n_train))
indices2 = list(range(n_val))
indices3 = list(range(n_test))
train_sampler = torch.utils.data.sampler.SubsetRandomSampler(indices1)
valid_sampler = torch.utils.data.sampler.SubsetRandomSampler(indices2)
test_sampler = torch.utils.data.sampler.SubsetRandomSampler(indices3)
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=config.batch_size,
sampler=train_sampler,
num_workers=config.workers,
pin_memory=True)
valid_loader = torch.utils.data.DataLoader(val_dat,
batch_size=config.batch_size,
sampler=valid_sampler,
num_workers=config.workers,
pin_memory=True)
test_loader = torch.utils.data.DataLoader(test_dat,
batch_size=config.batch_size,
sampler=test_sampler,
num_workers=config.workers,
pin_memory=True)
"""
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=config.batch_size,
shuffle=True,
num_workers=config.workers,
pin_memory=True)
valid_loader = torch.utils.data.DataLoader(valid_data,
batch_size=config.batch_size,
shuffle=False,
num_workers=config.workers,
pin_memory=True)
"""
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer, config.epochs)
#lambda1 = lambda epoch: 0.95 ** epoch
#lr_scheduler = torch.optim.lr_scheduler.RLambdaLR(optimizer, lr_lambda=[lambda1])
best_top1 = 0.
# training loop
for epoch in range(config.epochs):
lr_scheduler.step()
drop_prob = config.drop_path_prob * epoch / config.epochs
model.module.drop_path_prob(drop_prob)
# training
train(train_loader, model, optimizer, criterion, epoch)
# validation
cur_step = (epoch + 1) * len(train_loader)
top1 = validate(valid_loader, model, criterion, epoch, cur_step)
# save
if best_top1 < top1:
best_top1 = top1
is_best = True
else:
is_best = False
#utils.save_checkpoint(model, config.path, is_best)
utils.save_checkpoint2(model, epoch, optimizer, criterion, config.path,
is_best)
print("")
logger.info("Final best Prec@1 = {:.4%}".format(best_top1))
def evaluate(self, trial_no, trial_hyperparams):
"""Evaluates objective function
Trains the child model k times with same augmentation hyperparameters.
k is determined by the user by `opt_samples` argument.
Args:
trial_no (int): no of trial. needed for recording to notebook
trial_hyperparams (list)
Returns:
float: trial-cost = 1 - avg. rewards from samples
"""
augmented_data = augment_by_policy(self.data["X_train"],
self.data["y_train"],
*trial_hyperparams)
sample_rewards = []
#pytorch
layers = 2
init_channels = 24
use_aux = True
epochs = 30
lr = 0.01
momentum = 0.995
weight_decay = 0.995
drop_path_prob = 0.2
genotype = "Genotype(normal=[[('dil_conv_3x3', 0), ('sep_conv_5x5', 1)], [('sep_conv_3x3', 1), ('avg_pool_3x3', 0)],[('dil_conv_3x3', 1), ('dil_conv_3x3', 0)], [('sep_conv_3x3', 3), ('skip_connect', 1)]], normal_concat=range(2, 6), reduce=[[('sep_conv_3x3', 1), ('dil_conv_5x5', 0)], [('skip_connect', 0), ('sep_conv_5x5', 1)], [('sep_conv_5x5', 1),('sep_conv_5x5', 0)], [('max_pool_3x3', 1), ('sep_conv_3x3', 0)]], reduce_concat=range(2, 6))"
model = AugmentCNN(self.input_size, self.input_channels, init_channels,
self.n_classes, layers, use_aux, genotype)
model = nn.DataParallel(model, device_ids='0').to(device)
# model size
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
# weights optimizer
optimizer = torch.optim.SGD(model.parameters(),
lr,
momentum=momentum,
weight_decay=weight_decay)
a = 2 / 0
"""
for sample_no in range(1, self.opt_samples + 1):
self.child_model.load_pre_augment_weights()
# TRAIN
history = self.child_model.fit(self.data, augmented_data)
#
reward = self.calculate_reward(history)
sample_rewards.append(reward)
self.notebook.record(
trial_no, trial_hyperparams, sample_no, reward, history
)
"""
best_top1 = -9999
for epoch in range(epochs):
lr_scheduler.step()
drop_prob = drop_path_prob * epoch / epochs
model.module.drop_path_prob(drop_prob)
# training
train(train_loader, model, optimizer, criterion, epoch)
# validation
cur_step = (epoch + 1) * len(train_loader)
top1 = validate(valid_loader, model, criterion, epoch, cur_step)
# save
if best_top1 < top1:
best_top1 = top1
is_best = True
else:
is_best = False
print('best_top1:', best_top1)
#sample_rewards.append(reward)
#self.notebook.record(
# trial_no, trial_hyperparams, sample_no, reward, history
#)
#trial_cost = 1 - np.mean(sample_rewards)
#self.notebook.save()
log_and_print(
f"{str(trial_no)}, {str(trial_cost)}, {str(trial_hyperparams)}",
self.logging,
)
#return trial_cost
return best_top1
def worker(gpu, ngpus_per_node, config_in):
# init
config = copy.deepcopy(config_in)
jobid = os.environ["SLURM_JOBID"]
procid = int(os.environ["SLURM_PROCID"])
config.gpu = gpu
if config.gpu is not None:
writer_name = "tb.{}-{:d}-{:d}".format(jobid, procid, gpu)
logger_name = "{}.{}-{:d}-{:d}.aug.log".format(config.name, jobid,
procid, gpu)
ploter_name = "{}-{:d}-{:d}".format(jobid, procid, gpu)
ck_name = "{}-{:d}-{:d}".format(jobid, procid, gpu)
else:
writer_name = "tb.{}-{:d}-all".format(jobid, procid)
logger_name = "{}.{}-{:d}-all.aug.log".format(config.name, jobid,
procid)
ploter_name = "{}-{:d}-all".format(jobid, procid)
ck_name = "{}-{:d}-all".format(jobid, procid)
writer = SummaryWriter(log_dir=os.path.join(config.path, writer_name))
writer.add_text('config', config.as_markdown(), 0)
logger = utils.get_logger(os.path.join(config.path, logger_name))
config.print_params(logger.info)
# get cuda device
device = torch.device('cuda', gpu)
# begin
logger.info("Logger is set - training start")
if config.dist_url == "env://" and config.rank == -1:
config.rank = int(os.environ["RANK"])
if config.mp_dist:
# For multiprocessing distributed training, rank needs to be the
# global rank among all the processes
config.rank = config.rank * ngpus_per_node + gpu
# print('back:{}, dist_url:{}, world_size:{}, rank:{}'.format(config.dist_backend, config.dist_url, config.world_size, config.rank))
dist.init_process_group(backend=config.dist_backend,
init_method=config.dist_url,
world_size=config.world_size,
rank=config.rank)
# get data with meta info
input_size, input_channels, n_classes, train_data, valid_data = utils.get_data(
config.dataset,
config.data_path,
config.cutout_length,
validation=True)
# build model
criterion = nn.CrossEntropyLoss().to(device)
use_aux = config.aux_weight > 0.
model = AugmentCNN(input_size, input_channels, config.init_channels,
n_classes, config.layers, use_aux, config.genotype)
if config.gpu is not None:
torch.cuda.set_device(config.gpu)
# model = model.to(device)
model.cuda(config.gpu)
# When using a single GPU per process and per DistributedDataParallel, we need to divide
# the batch size ourselves based on the total number of GPUs we have
config.batch_size = int(config.batch_size / ngpus_per_node)
config.workers = int(
(config.workers + ngpus_per_node - 1) / ngpus_per_node)
# model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[config.rank])
model = torch.nn.parallel.DistributedDataParallel(
model, device_ids=[config.gpu])
# model = torch.nn.parallel.DistributedDataParallel(model, device_ids=None, output_device=None)
else:
model.cuda()
# DistributedDataParallel will divide and allocate batch_size to all
# available GPUs if device_ids are not set
model = torch.nn.parallel.DistributedDataParallel(model)
# model size
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
# weights optimizer
optimizer = torch.optim.SGD(model.parameters(),
config.lr,
momentum=config.momentum,
weight_decay=config.weight_decay)
# load data
train_sampler = data.distributed.DistributedSampler(
train_data, num_replicas=config.world_size, rank=config.rank)
valid_sampler = data.distributed.DistributedSampler(
valid_data, num_replicas=config.world_size, rank=config.rank)
train_loader = data.DataLoader(train_data,
batch_size=config.batch_size,
sampler=train_sampler,
shuffle=False,
num_workers=config.workers,
pin_memory=True)
valid_loader = data.DataLoader(valid_data,
batch_size=config.batch_size,
sampler=valid_sampler,
shuffle=False,
num_workers=config.workers,
pin_memory=True)
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer, config.epochs)
# setting the privacy protecting procedure
if config.dist_privacy:
logger.info("PRIVACY ENGINE OFF")
best_top1 = 0.
# training loop
for epoch in range(config.epochs):
# lr_scheduler.step()
drop_prob = config.drop_path_prob * epoch / config.epochs
model.module.drop_path_prob(drop_prob)
# training
train(logger, writer, device, config, train_loader, model, optimizer,
criterion, epoch)
lr_scheduler.step()
# validation
cur_step = (epoch + 1) * len(train_loader)
top1 = validate(logger, writer, device, config, valid_loader, model,
criterion, epoch, cur_step)
# save
if best_top1 < top1:
best_top1 = top1
is_best = True
else:
is_best = False
utils.save_checkpoint(model, config.path, ck_name, 'aug', is_best)
print("")
logger.info("Final best Prec@1 = {:.4%}".format(best_top1))
def main():
logger.info("Logger is set - training start")
# set default gpu device id
torch.cuda.set_device(config.gpus[0])
# set seed
np.random.seed(config.seed)
torch.manual_seed(config.seed)
torch.cuda.manual_seed_all(config.seed)
torch.backends.cudnn.benchmark = True
# get data with meta info
input_size, input_channels, n_classes, train_data, valid_data = utils.get_data(
config.dataset,
config.data_path,
config.cutout_length,
validation=True,
autoaugment=config.autoaugment)
if config.label_smooth != 0:
criterion = utils.CrossEntropyLabelSmooth(
10, config.label_smooth).to(device)
else:
criterion = nn.CrossEntropyLoss().to(device)
use_aux = config.aux_weight > 0.
if config.dataset in utils.LARGE_DATASETS:
model = AugmentCNNImageNet(input_size, input_channels,
config.init_channels, n_classes,
config.layers, use_aux, config.genotype)
else:
model = AugmentCNN(input_size,
input_channels,
config.init_channels,
n_classes,
config.layers,
use_aux,
config.genotype,
SSC=config.SSC)
model = nn.DataParallel(model, device_ids=config.gpus).to(device)
# model size
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
# weights optimizer
if config.p != 1:
optimizer = torch.optim.SGD(model.parameters(),
1.,
momentum=config.momentum,
weight_decay=config.weight_decay)
else:
optimizer = torch.optim.SGD(model.parameters(),
config.lr,
momentum=config.momentum,
weight_decay=config.weight_decay)
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=config.batch_size,
shuffle=True,
num_workers=config.workers,
pin_memory=True)
valid_loader = torch.utils.data.DataLoader(valid_data,
batch_size=config.batch_size,
shuffle=False,
num_workers=config.workers,
pin_memory=True)
if config.p == 1:
lr_scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(
optimizer, config.epochs)
else:
lr_cpa = utils.cosine_power_annealing_lr(nepochs=config.epochs,
min_lr=config.lr_min,
max_lr=config.lr,
p=config.p)
lr_scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, [lr_cpa])
best_top1 = 0.
# training loop
for epoch in range(config.epochs):
lr_scheduler.step()
drop_prob = config.drop_path_prob * epoch / config.epochs
model.module.drop_path_prob(drop_prob)
# training
train(train_loader, model, optimizer, criterion, epoch)
# validation
cur_step = (epoch + 1) * len(train_loader)
top1 = validate(valid_loader, model, criterion, epoch, cur_step)
# save
if best_top1 < top1:
best_top1 = top1
is_best = True
else:
is_best = False
utils.save_checkpoint(model, config.path, is_best)
print("")
logger.info("Final best Prec@1 = {:.4%} for job {}".format(
best_top1, config.name))
def main():
logger.info("Logger is set - training start")
fileRoot = r'/home/hlu/Data/VIPL'
saveRoot = r'/home/hlu/Data/VIPL_STMap' + str(config.fold_num) + str(config.fold_index)
n_classes = 1
input_channels = 3
input_size = np.array([64, 300])
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
toTensor = transforms.ToTensor()
resize = transforms.Resize(size=(64, 300))
# set default gpu device id
torch.cuda.set_device(config.gpus[0])
# set seed
np.random.seed(config.seed)
torch.manual_seed(config.seed)
torch.cuda.manual_seed_all(config.seed)
# net acc
torch.backends.cudnn.benchmark = True
# get data with meta info
if config.reData == 1:
test_index, train_index = MyDataset.CrossValidation(fileRoot, fold_num=config.fold_num,
fold_index=config.fold_index)
Train_Indexa = MyDataset.getIndex(fileRoot, train_index, saveRoot + '_Train', 'STMap_YUV_Align_CSI_POS.png', 15, 300)
Test_Indexa = MyDataset.getIndex(fileRoot, test_index, saveRoot + '_Test', 'STMap_YUV_Align_CSI_POS.png', 15, 300)
train_data = MyDataset.Data_STMap(root_dir=(saveRoot + '_Train'), frames_num=300,
transform=transforms.Compose([resize, toTensor, normalize]))
valid_data = MyDataset.Data_STMap(root_dir=(saveRoot + '_Test'), frames_num=300,
transform=transforms.Compose([resize, toTensor, normalize]))
train_loader = torch.utils.data.DataLoader(train_data,
batch_size=config.batch_size,
shuffle=True,
num_workers=config.workers,
pin_memory=True)
valid_loader = torch.utils.data.DataLoader(valid_data,
batch_size=config.batch_size,
shuffle=False,
num_workers=config.workers,
pin_memory=True)
# loss
criterion = nn.L1Loss().to(device)
# net
Model_name = config.name + 'fn' + str(config.fold_num) + 'fi' + str(config.fold_index)
use_aux = config.aux_weight > 0.
if config.reTrain == 1:
model = torch.load(os.path.join(config.path, Model_name + 'best.pth.tar'), map_location=device)
print('load ' + Model_name + ' right')
model = nn.DataParallel(model, device_ids=config.gpus).to(device)
else:
model = AugmentCNN(input_size, input_channels, config.init_channels, n_classes, config.layers,
use_aux, config.genotype)
model._init_weight()
model = nn.DataParallel(model, device_ids=config.gpus).to(device)
# model size
mb_params = utils.param_size(model)
logger.info("Model size = {:.3f} MB".format(mb_params))
# weights optimizer
optimizer = torch.optim.Adam(model.parameters(), config.lr)
best_losses = 10
# training loop
for epoch in range(config.epochs):
# training
train(train_loader, model, optimizer, criterion, epoch)
# validation
cur_step = (epoch+1) * len(train_loader)
best_losses = validate(valid_loader, model, criterion, epoch, cur_step, best_losses)
logger.info("Final best Losses@1 = {:.4%}".format(best_losses))
