def main():
# parse the command line arguments
parser = NeonArgparser(__doc__)
args = parser.parse_args()
logger = logging.getLogger()
logger.setLevel(args.log_thresh)
#Set up batch iterator for training images
train = ImgMaster(repo_dir='dataTmp_optFlow_BW',
set_name='train',
inner_size=240,
subset_pct=100)
val = ImgMaster(repo_dir='dataTmp_optFlow_BW',
set_name='train',
inner_size=240,
subset_pct=100,
do_transforms=False)
test = ImgMaster(repo_dir='dataTestTmp_optFlow_BW',
set_name='train',
inner_size=240,
subset_pct=100,
do_transforms=False)
train.init_batch_provider()
val.init_batch_provider()
test.init_batch_provider()
print "Constructing network..."
#Create AlexNet architecture
model = constuct_network()
# Optimzer for model
opt = Adadelta()
# configure callbacks
valmetric = TopKMisclassification(k=5)
callbacks = Callbacks(model,
train,
eval_set=test,
metric=valmetric,
**args.callback_args)
cost = GeneralizedCost(costfunc=CrossEntropyMulti())
#flag = input("Press Enter if you want to begin training process.")
print "Training network..."
model.fit(train,
optimizer=opt,
num_epochs=args.epochs,
cost=cost,
callbacks=callbacks)
mets = model.eval(test, metric=valmetric)
print 'Validation set metrics:'
print 'LogLoss: %.2f, Accuracy: %.1f %%0 (Top-1), %.1f %% (Top-5)' % (
mets[0], (1.0 - mets[1]) * 100, (1.0 - mets[2]) * 100)
return
# parse the command line arguments
parser = NeonArgparser(__doc__)
args = parser.parse_args()
# hyperparameters
batch_size = 128
# setup backend
be = gen_backend(backend=args.backend,
rng_seed=args.rng_seed,
device_id=args.device_id,
batch_size=batch_size,
default_dtype=args.datatype)
try:
train = ImgMaster(repo_dir=args.data_dir, inner_size=224, set_name='train')
test = ImgMaster(repo_dir=args.data_dir,
inner_size=224,
set_name='validation',
do_transforms=False)
except (OSError, IOError, ValueError) as err:
print err
sys.exit(0)
train.init_batch_provider()
test.init_batch_provider()
init1 = Gaussian(scale=0.01)
init2 = Gaussian(scale=0.03)
relu = Rectlin()
# hyperparameters
args.batch_size = 64
cost_scale = 1.
VGG = 'B'
use_batch_norm = True
biases = None if use_batch_norm else Constant(0)
# setup backend
be = gen_backend(**extract_valid_args(args, gen_backend))
# initialize the data provider
img_set_options = dict(repo_dir=args.data_dir,
inner_size=224,
dtype=args.datatype,
subset_pct=100)
train = ImgMaster(set_name='train', **img_set_options)
test = ImgMaster(set_name='validation', do_transforms=False, **img_set_options)
train.init_batch_provider()
test.init_batch_provider()
init1 = GlorotUniform()
relu = Rectlin()
common_params = dict(init=init1,
activation=Rectlin(),
batch_norm=use_batch_norm,
bias=biases)
conv_params = dict(padding=1, **common_params)
# Set up the model layers, using 3x3 conv stacks with different feature map sizes
layers = []
def main():
# parse the command line arguments
parser = NeonArgparser(__doc__)
args = parser.parse_args()
logger = logging.getLogger()
logger.setLevel(args.log_thresh)
#Set up batch iterator for training images
print "Setting up data batch loaders..."
train = ImgMaster(repo_dir='dataTmp',
set_name='train',
inner_size=120,
subset_pct=100)
val = ImgMaster(repo_dir='dataTmp',
set_name='train',
inner_size=120,
subset_pct=100,
do_transforms=False)
test = ImgMaster(repo_dir='dataTestTmp',
set_name='train',
inner_size=120,
subset_pct=100,
do_transforms=False)
train.init_batch_provider()
val.init_batch_provider()
test.init_batch_provider()
print "Constructing network..."
#Create AlexNet architecture
model = constuct_network()
#model.load_weights(args.model_file)
# drop weights LR by 1/250**(1/3) at epochs (23, 45, 66), drop bias LR by 1/10 at epoch 45
weight_sched = Schedule([22, 44, 65, 90, 97], (1 / 250.)**(1 / 3.))
opt_gdm = GradientDescentMomentum(0.01,
0.9,
wdecay=0.005,
schedule=weight_sched)
opt_biases = GradientDescentMomentum(0.04,
1.0,
schedule=Schedule([130], .1))
opt = MultiOptimizer({'default': opt_gdm, 'Bias': opt_biases})
# configure callbacks
valmetric = TopKMisclassification(k=5)
callbacks = Callbacks(model,
train,
eval_set=val,
metric=valmetric,
**args.callback_args)
cost = GeneralizedCost(costfunc=CrossEntropyMulti())
#flag = input("Press Enter if you want to begin training process.")
print "Training network..."
model.fit(train,
optimizer=opt,
num_epochs=args.epochs,
cost=cost,
callbacks=callbacks)
mets = model.eval(test, metric=valmetric)
print 'Validation set metrics:'
print 'LogLoss: %.2f, Accuracy: %.1f %%0 (Top-1), %.1f %% (Top-5)' % (
mets[0], (1.0 - mets[1]) * 100, (1.0 - mets[2]) * 100)
test.exit_batch_provider()
val.exit_batch_provider()
train.exit_batch_provider()
args = parser.parse_args()
# hyperparameters
batch_size = 64
cost_scale = 1.
# setup backend
be = gen_backend(backend=args.backend,
rng_seed=args.rng_seed,
device_id=args.device_id,
batch_size=batch_size,
default_dtype=args.datatype)
train = ImgMaster(repo_dir=args.data_dir,
inner_size=224,
set_name='train',
subset_pct=1,
dtype=args.datatype)
test = ImgMaster(repo_dir=args.data_dir,
inner_size=224,
set_name='validation',
subset_pct=50,
dtype=args.datatype,
do_transforms=False)
train.init_batch_provider()
test.init_batch_provider()
init1 = GlorotUniform()
relu = Rectlin()
