def get_data(manifest, manifest_root, batch_size, subset_pct, rng_seed):
'''
Loads training and validation set using aeon loader
args(object): Contains function arguments
manifest(list): Manifest files for traning and validaions
manifest_root(string): Root directory of manifest file
batch_size(int): Mini batch size
subset_pct(float): Subset percentage of the data (0-100)
rng_seed(int): Seed for random number generator
'''
assert 'train' in manifest[1], "Missing train manifest"
assert 'test' in manifest[0], "Missing validation manifest"
train_set = make_train_loader(manifest[1], manifest_root, batch_size,
subset_pct, rng_seed)
valid_set = make_validation_loader(manifest[0], manifest_root, batch_size,
subset_pct)
return train_set, valid_set
help='save visualization data from deconvolution')
parser.add_argument('--subset_pct',
type=float,
default=100,
help='subset of training dataset to use (percentage)')
args = parser.parse_args()
model, cost = create_network()
rseed = 0 if args.rng_seed is None else args.rng_seed
# setup data provider
assert 'train' in args.manifest, "Missing train manifest"
assert 'val' in args.manifest, "Missing validation manifest"
train = make_alexnet_train_loader(args.manifest['train'], args.manifest_root,
model.be, args.subset_pct, rseed)
valid = make_validation_loader(args.manifest['val'], args.manifest_root,
model.be, args.subset_pct)
sched_weight = Schedule([10], change=0.1)
opt = GradientDescentMomentum(0.01, 0.9, wdecay=0.0005, schedule=sched_weight)
# configure callbacks
valmetric = TopKMisclassification(k=5)
callbacks = Callbacks(model,
eval_set=valid,
metric=valmetric,
**args.callback_args)
if args.deconv:
callbacks.add_deconv_callback(train, valid)
model.fit(train,
parser = NeonArgparser(__doc__, default_config_files=config_files)
parser.add_argument('--depth', type=int, default=2,
help='depth of each stage (network depth will be 9n+2)')
parser.add_argument('--subset_pct', type=float, default=100,
help='subset of training dataset to use (percentage)')
args = parser.parse_args()
random_seed = args.rng_seed if args.rng_seed else 0
# Check that the proper manifest sets have been supplied
assert 'train' in args.manifest, "Missing train manifest"
assert 'val' in args.manifest, "Missing validation manifest"
model, cost = create_network(args.depth)
# setup data provider
train = make_train_loader(args.manifest['train'], args.manifest_root, model.be, args.subset_pct,
random_seed)
test = make_validation_loader(args.manifest['val'], args.manifest_root, model.be, args.subset_pct)
# tune batch norm parameters on subset of train set with no augmentations
tune_set = make_tuning_loader(args.manifest['train'], args.manifest_root, model.be)
# configure callbacks
callbacks = Callbacks(model, eval_set=test, metric=Misclassification(), **args.callback_args)
callbacks.add_callback(BatchNormTuneCallback(tune_set), insert_pos=0)
# begin training
opt = GradientDescentMomentum(0.1, 0.9, wdecay=0.0001, schedule=Schedule([82, 124], 0.1))
model.fit(train, optimizer=opt, num_epochs=args.epochs, cost=cost, callbacks=callbacks)
train_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'train.cfg')
config_files = [train_config] if os.path.exists(train_config) else []
parser = NeonArgparser(__doc__, default_config_files=config_files)
parser.add_argument('--subset_pct', type=float, default=100,
help='subset of training dataset to use (percentage)')
args = parser.parse_args()
model, cost = create_network_lrn()
rseed = 0 if args.rng_seed is None else args.rng_seed
# setup data provider
assert 'train' in args.manifest, "Missing train manifest"
assert 'val' in args.manifest, "Missing validation manifest"
train = make_alexnet_train_loader(args.manifest['train'], args.manifest_root,
model.be, args.subset_pct, rseed, dtype=args.datatype)
valid = make_validation_loader(args.manifest['val'], args.manifest_root,
model.be, args.subset_pct, dtype=args.datatype)
weight_sched = Schedule(20, 0.1)
opt_gdm = GradientDescentMomentum(0.01, 0.9, wdecay=0.0005, schedule=weight_sched,
stochastic_round=args.rounding)
opt_biases = GradientDescentMomentum(0.02, 0.9, schedule=weight_sched,
stochastic_round=args.rounding)
opt = MultiOptimizer({'default': opt_gdm, 'Bias': opt_biases})
# configure callbacks
valmetric = TopKMisclassification(k=5)
callbacks = Callbacks(model, eval_set=valid, metric=valmetric, **args.callback_args)
model.fit(train, optimizer=opt, num_epochs=args.epochs, cost=cost, callbacks=callbacks)
