def get_base_config(self, dataset):
print("Preparing training D1 for %s" %
(dataset.parent_dataset.__class__.__name__))
all_loader = DataLoader(dataset,
batch_size=self.args.batch_size,
num_workers=self.args.workers,
pin_memory=True)
# Set up the criterion
criterion = nn.NLLLoss().cuda()
# Set up the model
model_class = Global.get_ref_classifier(
dataset.name)[self.default_model]
self.add_identifier = model_class.__name__
# We must create 5 instances of this class.
from models import get_ref_model_path
all_models = []
for mid in range(5):
model = model_class()
model = DeepEnsembleWrapper(model)
model = model.to(self.args.device)
h_path = get_ref_model_path(self.args,
model_class.__name__,
dataset.name,
suffix_str='DE.%d' % mid)
best_h_path = path.join(h_path, 'model.best.pth')
if not path.isfile(best_h_path):
raise NotImplementedError(
"Please use setup_model to pretrain the networks first! Can't find %s"
% best_h_path)
else:
print(colored('Loading H1 model from %s' % best_h_path, 'red'))
model.load_state_dict(torch.load(best_h_path))
model.eval()
all_models.append(model)
master_model = DeepEnsembleMasterWrapper(all_models)
# Set up the config
config = IterativeTrainerConfig()
config.name = '%s-CLS' % (self.args.D1)
config.phases = {
'all': {
'dataset': all_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = False
config.stochastic_gradient = True
config.model = master_model
config.optim = None
config.autoencoder_target = False
config.visualize = False
config.logger = Logger()
return config
def get_ae_config(args, model, dataset, BCE_Loss):
print("Preparing training D1 for %s"%(dataset.name))
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if dataset.name in Global.mirror_augment:
print(colored("Mirror augmenting %s"%dataset.name, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds, batch_size=args.batch_size, shuffle=True, num_workers=args.workers, pin_memory=True)
valid_loader = DataLoader(valid_ds, batch_size=args.batch_size, num_workers=args.workers, pin_memory=True)
all_loader = DataLoader(dataset, batch_size=args.batch_size, num_workers=args.workers, pin_memory=True)
# Set up the model
model = model.to(args.device)
# Set up the criterion
criterion = None
if BCE_Loss:
criterion = nn.BCEWithLogitsLoss().to(args.device)
else:
criterion = nn.MSELoss().to(args.device)
model.default_sigmoid = True
# Set up the config
config = IterativeTrainerConfig()
config.name = 'autoencoder_%s_%s'%(dataset.name, model.preferred_name())
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {'dataset' : train_loader, 'backward': True},
'test': {'dataset' : valid_loader, 'backward': False},
'all': {'dataset' : all_loader, 'backward': False},
}
config.criterion = criterion
config.classification = False
config.cast_float_label = False
config.autoencoder_target = True
config.stochastic_gradient = True
config.visualize = not args.no_visualize
config.sigmoid_viz = BCE_Loss
config.model = model
config.logger = Logger()
config.optim = optim.Adam(model.parameters(), lr=1e-3)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim, patience=10, threshold=1e-3, min_lr=1e-6, factor=0.1, verbose=True)
config.max_epoch = 120
if hasattr(model, 'train_config'):
model_train_config = model.train_config()
for key, value in model_train_config.iteritems():
print('Overriding config.%s'%key)
config.__setattr__(key, value)
return config
def get_H_config(self, dataset, will_train=True):
print("Preparing training D1+D2 (H)")
print("Mixture size: %s"%colored('%d'%len(dataset), 'green'))
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if self.args.D1 in Global.mirror_augment:
print(colored("Mirror augmenting %s"%self.args.D1, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds, batch_size=self.args.batch_size, shuffle=True, num_workers=self.args.workers, pin_memory=True)
valid_loader = DataLoader(valid_ds, batch_size=self.args.batch_size, shuffle=True, num_workers=self.args.workers, pin_memory=True)
# To make the threshold learning, actually threshold learning
# the margin must be set to 0.
criterion = SVMLoss(margin=0.0).to(self.args.device)
# Set up the model
model = MCDropoutModelWrapper(self.base_model).to(self.args.device)
old_valid_loader = valid_loader
# By definition, this approach is uncacheable :(
# Set up the config
config = IterativeTrainerConfig()
base_model_name = self.base_model.__class__.__name__
if hasattr(self.base_model, 'preferred_name'):
base_model_name = self.base_model.preferred_name()
config.name = '_%s[%s](%s-%s)'%(self.__class__.__name__, base_model_name, self.args.D1, self.args.D2)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {'dataset' : train_loader, 'backward': True},
'test': {'dataset' : valid_loader, 'backward': False},
'testU': {'dataset' : old_valid_loader, 'backward': False},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = True
config.stochastic_gradient = True
config.visualize = not self.args.no_visualize
config.model = model
config.optim = optim.Adagrad(model.H.parameters(), lr=1e-1, weight_decay=0)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim, patience=10, threshold=1e-1, min_lr=1e-8, factor=0.1, verbose=True)
h_path = path.join(self.args.experiment_path, '%s' % (self.__class__.__name__),
'%d' % (self.default_model),
'%s-%s.pth' % (self.args.D1, self.args.D2))
h_parent = path.dirname(h_path)
config.logger = Logger(h_parent)
config.max_epoch = 100
return config
def get_base_config(self, dataset):
print("Preparing training D1 for %s" %
(dataset.parent_dataset.__class__.__name__))
all_loader = DataLoader(dataset,
batch_size=self.args.batch_size,
num_workers=self.args.workers,
pin_memory=True)
# Set up the model
model = Global.get_ref_pixelcnn(dataset.name)[self.default_model]().to(
self.args.device)
self.add_identifier = model.__class__.__name__
# Load the snapshot
from models import get_ref_model_path
h_path = get_ref_model_path(self.args,
model.__class__.__name__,
dataset.name,
suffix_str=model.netid)
best_h_path = path.join(h_path, 'model.best.pth')
if not path.isfile(best_h_path):
raise NotImplementedError(
"Please use setup_model to pretrain the networks first! Can't find %s"
% best_h_path)
else:
print(colored('Loading H1 model from %s' % best_h_path, 'red'))
model.load_state_dict(torch.load(best_h_path))
model.eval()
# Set up the criterion
criterion = PCNN_Loss(one_d=(model.input_channels == 1)).to(
self.args.device)
# Set up the config
config = IterativeTrainerConfig()
config.name = '%s-pcnn' % (self.args.D1)
config.phases = {
'all': {
'dataset': all_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = False
config.cast_float_label = False
config.autoencoder_target = True
config.stochastic_gradient = True
config.model = model
config.optim = None
config.visualize = False
config.logger = Logger()
return config
def get_base_config(self, dataset):
print("Preparing training D1 for %s" % (dataset.name))
# Initialize the multi-threaded loaders.
all_loader = DataLoader(dataset, batch_size=self.args.batch_size, num_workers=self.args.workers,
pin_memory=True)
# Set up the model
model = Global.get_ref_ali(dataset.name)[0]().to(self.args.device)
# Set up the criterion
criterion = None
if self.default_model == 0:
criterion = nn.BCEWithLogitsLoss().to(self.args.device)
else:
criterion = nn.MSELoss().to(self.args.device)
model.default_sigmoid = True
# Set up the config
config = IterativeTrainerConfig()
config.name = '%s-ALIAE1' % (self.args.D1)
config.phases = {
'all': {'dataset': all_loader, 'backward': False},
}
config.criterion = criterion
config.classification = False
config.cast_float_label = False
config.autoencoder_target = True
config.stochastic_gradient = True
config.visualize = not self.args.no_visualize
config.sigmoid_viz = self.default_model == 0
config.model = model
config.optim = None
h_path = path.join(self.args.experiment_path, '%s' % (self.__class__.__name__),
'%d' % (self.default_model),
'%s-%s.pth' % (self.args.D1, self.args.D2))
h_parent = path.dirname(h_path)
config.logger = Logger(h_parent)
return config
def get_base_config(self, dataset):
print("Preparing training D1 for %s" % (dataset.name))
all_loader = DataLoader(dataset,
batch_size=self.args.batch_size,
num_workers=self.args.workers,
pin_memory=True)
# Set up the criterion
criterion = nn.NLLLoss().to(self.args.device)
# Set up the model
import global_vars as Global
model = Global.get_ref_classifier(
dataset.name)[self.default_model]().to(self.args.device)
self.add_identifier = model.__class__.__name__
if hasattr(model, 'preferred_name'):
self.add_identifier = model.preferred_name()
# Set up the config
config = IterativeTrainerConfig()
config.name = '%s-CLS' % (self.args.D1)
config.phases = {
'all': {
'dataset': all_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = False
config.stochastic_gradient = True
config.model = model
config.optim = None
config.autoencoder_target = False
config.visualize = False
config.logger = Logger()
return config
def get_classifier_config(args, model, dataset, mid=0):
print("Preparing training D1 for %s" % (dataset.name))
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if dataset.name in Global.mirror_augment:
print(colored("Mirror augmenting %s" % dataset.name, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds,
batch_size=args.batch_size / 2,
shuffle=True,
num_workers=args.workers,
pin_memory=True)
valid_loader = DataLoader(valid_ds,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True)
all_loader = DataLoader(dataset,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True)
import methods.deep_ensemble as DE
# Set up the model
model = DE.DeepEnsembleWrapper(model).to(args.device)
# Set up the criterion
criterion = DE.DeepEnsembleLoss(ensemble_network=model).to(args.device)
# Set up the config
config = IterativeTrainerConfig()
base_model_name = model.__class__.__name__
if hasattr(model, 'preferred_name'):
base_model_name = model.preferred_name()
config.name = 'DeepEnsemble_%s_%s(%d)' % (dataset.name, base_model_name,
mid)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'all': {
'dataset': all_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.stochastic_gradient = True
config.visualize = not args.no_visualize
config.model = model
config.logger = Logger()
config.optim = optim.Adam(model.parameters(), lr=1e-3)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=10,
threshold=1e-2,
min_lr=1e-6,
factor=0.1,
verbose=True)
config.max_epoch = 120
if hasattr(model.model, 'train_config'):
model_train_config = model.model.train_config()
for key, value in model_train_config.iteritems():
print('Overriding config.%s' % key)
config.__setattr__(key, value)
return config
def get_H_config(self, dataset, will_train=True):
print("Preparing training D1+D2 (H)")
print("Mixture size: %s" % colored('%d' % len(dataset), 'green'))
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if self.args.D1 in Global.mirror_augment:
print(colored("Mirror augmenting %s" % self.args.D1, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
valid_loader = DataLoader(valid_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
# To make the threshold learning, actually threshold learning
# the margin must be set to 0.
criterion = SVMLoss(margin=0.0).to(self.args.device)
# Set up the model
model = DeepEnsembleModelWrapper(self.base_model).to(self.args.device)
old_valid_loader = valid_loader
if will_train:
# cache the subnetwork for faster optimization.
from methods import get_cached
from torch.utils.data.dataset import TensorDataset
trainX, trainY = get_cached(model, train_loader, self.args.device)
validX, validY = get_cached(model, valid_loader, self.args.device)
new_train_ds = TensorDataset(trainX, trainY)
new_valid_ds = TensorDataset(validX, validY)
# Initialize the new multi-threaded loaders.
train_loader = DataLoader(new_train_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
valid_loader = DataLoader(new_valid_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
# Set model to direct evaluation (for cached data)
model.set_eval_direct(True)
# Set up the config
config = IterativeTrainerConfig()
base_model_name = self.base_model.preferred_name()
config.name = '_%s[%s](%s->%s)' % (self.__class__.__name__,
base_model_name, self.args.D1,
self.args.D2)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'testU': {
'dataset': old_valid_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = True
config.stochastic_gradient = True
config.visualize = not self.args.no_visualize
config.model = model
config.optim = optim.Adagrad(model.H.parameters(),
lr=1e-1,
weight_decay=0)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=10,
threshold=1e-1,
min_lr=1e-8,
factor=0.1,
verbose=True)
config.logger = Logger()
config.max_epoch = 100
return config
def get_H_config(self,
train_ds,
valid_ds,
will_train=True,
epsilon=0.0012,
temperature=1000):
print("Preparing training D1+D2 (H)")
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
valid_loader = DataLoader(valid_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
# Set up the criterion
# To make the threshold learning, actually threshold learning
# the margin must be set to 0.
criterion = SVMLoss(margin=0.0).to(self.args.device)
# Set up the model
model = ODINModelWrapper(self.base_model,
epsilon=epsilon,
temperature=temperature).to(self.args.device)
old_valid_loader = valid_loader
if will_train:
# cache the subnetwork for faster optimization.
from methods import get_cached
from torch.utils.data.dataset import TensorDataset
trainX, trainY = get_cached(model, train_loader, self.args.device)
validX, validY = get_cached(model, valid_loader, self.args.device)
new_train_ds = TensorDataset(trainX, trainY)
x_center = trainX[trainY == 0].mean()
y_center = trainX[trainY == 1].mean()
init_value = (x_center + y_center) / 2
if model.H.threshold.device.type == "cpu":
model.H.threshold.data = init_value.view((1, ))
else:
model.H.threshold.data = init_value.cuda().view((1, ))
#model.H.threshold.fill_(init_value)
print("Initializing threshold to %.2f" % (init_value.item()))
new_valid_ds = TensorDataset(validX, validY)
# Initialize the new multi-threaded loaders.
train_loader = DataLoader(new_train_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
valid_loader = DataLoader(new_valid_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
# Set model to direct evaluation (for cached data)
model.set_eval_direct(True)
# Set up the config
config = IterativeTrainerConfig()
base_model_name = self.base_model.__class__.__name__
if hasattr(self.base_model, 'preferred_name'):
base_model_name = self.base_model.preferred_name()
config.name = '_%s[%s](%s-%s)' % (self.__class__.__name__,
base_model_name, self.args.D1,
self.args.D2)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'testU': {
'dataset': old_valid_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = True
config.stochastic_gradient = True
config.visualize = not self.args.no_visualize
config.model = model
config.optim = optim.Adagrad(model.H.parameters(),
lr=1e-2,
weight_decay=0)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=5,
threshold=1e-1,
min_lr=1e-8,
factor=0.1,
verbose=True)
h_path = path.join(self.args.experiment_path,
'%s' % (self.__class__.__name__),
'%d' % (self.default_model),
'%s-%s.pth' % (self.args.D1, self.args.D2))
h_parent = path.dirname(h_path)
config.logger = Logger(h_parent)
config.max_epoch = 30
return config
def get_H_config(self,
train_ds,
valid_ds,
will_train=True,
epsilon=0.0012):
print("Preparing training D1+D2 (H)")
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
valid_loader = DataLoader(valid_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
# Set up the criterion
criterion = nn.BCEWithLogitsLoss().cuda()
# Set up the model
model = MahaODModelWrapper(self.base_model,
epsilon=epsilon,
num_class=2,
num_layers=1).to(self.args.device)
old_valid_loader = valid_loader
if will_train:
# cache the subnetwork for faster optimization.
from methods import get_cached
from torch.utils.data.dataset import TensorDataset
trainX, trainY = get_cached(model, train_loader, self.args.device)
validX, validY = get_cached(model, valid_loader, self.args.device)
new_train_ds = TensorDataset(trainX, trainY)
new_valid_ds = TensorDataset(validX, validY)
# Initialize the new multi-threaded loaders.
train_loader = DataLoader(new_train_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
valid_loader = DataLoader(new_valid_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
# Set model to direct evaluation (for cached data)
model.set_eval_direct(True)
# Set up the config
config = IterativeTrainerConfig()
base_model_name = self.base_model.__class__.__name__
if hasattr(self.base_model, 'preferred_name'):
base_model_name = self.base_model.preferred_name()
config.name = '_%s[%s](%s-%s)' % (self.__class__.__name__,
base_model_name, self.args.D1,
self.args.D2)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'testU': {
'dataset': old_valid_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = True
config.stochastic_gradient = True
config.visualize = not self.args.no_visualize
config.model = model
config.optim = optim.Adam(model.H.parameters(), lr=1e-1)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=5,
threshold=1e-1,
min_lr=1e-6,
factor=0.1,
verbose=True)
h_path = path.join(self.args.experiment_path,
'%s' % (self.__class__.__name__),
'%d' % (self.default_model),
'%s-%s.pth' % (self.args.D1, self.args.D2))
h_parent = path.dirname(h_path)
config.logger = Logger(h_parent)
config.max_epoch = 100
return config
def get_pcnn_config(args, model, home_path, dataset):
print("Preparing training D1 for %s" % (dataset.name))
sample_im, _ = dataset[0]
obs = sample_im.size()
obs = [int(d) for d in obs]
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if dataset.name in Global.mirror_augment:
print(colored("Mirror augmenting %s" % dataset.name, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
pin_memory=True)
valid_loader = DataLoader(valid_ds,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True)
all_loader = DataLoader(dataset,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True)
# Set up the model
model = model.to(args.device)
# Set up the criterion
criterion = pcnn_utils.PCNN_Loss(one_d=(model.input_channels == 1))
# Set up the config
config = IterativeTrainerConfig()
config.name = 'PCNN_%s_%s' % (dataset.name, model.preferred_name())
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'all': {
'dataset': all_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = False
config.cast_float_label = False
config.autoencoder_target = True
config.stochastic_gradient = True
config.visualize = not args.no_visualize
config.model = model
config.logger = Logger(home_path)
config.sampler = lambda x: sample(x.model, 32, obs)
config.optim = optim.Adam(model.parameters(), lr=1e-3)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=10,
threshold=1e-2,
min_lr=1e-5,
factor=0.1,
verbose=True)
config.max_epoch = 60
if hasattr(model, 'train_config'):
model_train_config = model.train_config()
for key, value in model_train_config.items():
print('Overriding config.%s' % key)
config.__setattr__(key, value)
return config
def get_H_config(self, dataset, will_train=True):
print("Preparing training D1+D2 (H)")
print("Mixture size: %s" % colored('%d' % len(dataset), 'green'))
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if self.args.D1 in Global.mirror_augment:
print(colored("Mirror augmenting %s" % self.args.D1, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
valid_loader = DataLoader(valid_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True)
# Set up the criterion
# margin must be non-zero.
criterion = SVMLoss(margin=1.0).cuda()
# Set up the model
model = OTModelWrapper(self.base_model, self.mav,
self.weib_models).to(self.args.device)
old_valid_loader = valid_loader
if will_train:
# cache the subnetwork for faster optimization.
from methods import get_cached
from torch.utils.data.dataset import TensorDataset
trainX, trainY = get_cached(model, train_loader, self.args.device)
validX, validY = get_cached(model, valid_loader, self.args.device)
trainX_notnan = trainX[torch.logical_not(
torch.isnan(trainX)[:, 0]).nonzero().squeeze(1)]
trainY_notnan = trainY[torch.logical_not(
torch.isnan(trainX)[:, 0]).nonzero().squeeze(1)]
validX_notnan = validX[torch.logical_not(
torch.isnan(validX)[:, 0]).nonzero().squeeze(1)]
validY_notnan = validY[torch.logical_not(
torch.isnan(validX)[:, 0]).nonzero().squeeze(1)]
new_train_ds = TensorDataset(trainX_notnan, trainY_notnan)
new_valid_ds = TensorDataset(validX_notnan, validY_notnan)
# Initialize the new multi-threaded loaders.
train_loader = DataLoader(new_train_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
valid_loader = DataLoader(new_valid_ds,
batch_size=2048,
shuffle=True,
num_workers=0,
pin_memory=False)
# Set model to direct evaluation (for cached data)
model.set_eval_direct(True)
# Set up the config
config = IterativeTrainerConfig()
base_model_name = self.base_model.__class__.__name__
if hasattr(self.base_model, 'preferred_name'):
base_model_name = self.base_model.preferred_name()
config.name = '_%s[%s](%s->%s)' % (self.__class__.__name__,
base_model_name, self.args.D1,
self.args.D2)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'testU': {
'dataset': old_valid_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = True
config.stochastic_gradient = True
config.visualize = not self.args.no_visualize
config.model = model
config.optim = optim.SGD(model.H.parameters(),
lr=1e-2,
weight_decay=0.0) #1.0/len(train_ds))
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=10,
threshold=1e-1,
min_lr=1e-8,
factor=0.1,
verbose=True)
h_path = path.join(self.args.experiment_path,
'%s' % (self.__class__.__name__),
'%d' % (self.default_model),
'%s-%s.pth' % (self.args.D1, self.args.D2))
h_parent = path.dirname(h_path)
config.logger = Logger(h_parent)
config.max_epoch = 100
return config
def get_classifier_config(args, model, dataset, balanced=False):
print("Preparing training D1 for %s" % (dataset.name))
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if dataset.name in Global.mirror_augment:
print(colored("Mirror augmenting %s" % dataset.name, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
if balanced:
y_train = []
for x, y in train_ds:
y_train.append(y.numpy())
y_train = np.array(y_train)
class_sample_count = np.array(
[len(np.where(y_train == t)[0]) for t in np.unique(y_train)])
print(class_sample_count)
weight = 1. / class_sample_count
samples_weight = np.array([weight[t] for t in y_train])
samples_weight = torch.from_numpy(samples_weight)
sampler = WeightedRandomSampler(
samples_weight.type('torch.DoubleTensor'), len(samples_weight))
train_loader = DataLoader(train_ds,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True,
sampler=sampler)
y_val = []
for x, y in valid_ds:
y_val.append(y.numpy())
y_val = np.array(y_val)
class_sample_count = np.array(
[len(np.where(y_val == t)[0]) for t in np.unique(y_val)])
print(class_sample_count)
weight = 1. / class_sample_count
samples_weight = np.array([weight[t] for t in y_val])
samples_weight = torch.from_numpy(samples_weight)
sampler = WeightedRandomSampler(
samples_weight.type('torch.DoubleTensor'), len(samples_weight))
valid_loader = DataLoader(valid_ds,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True,
sampler=sampler)
else:
train_loader = DataLoader(train_ds,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
pin_memory=True)
valid_loader = DataLoader(valid_ds,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True)
all_loader = DataLoader(dataset,
batch_size=args.batch_size,
num_workers=args.workers,
pin_memory=True)
# Set up the criterion
criterion = nn.NLLLoss().to(args.device)
# Set up the model
model = model.to(args.device)
# Set up the config
config = IterativeTrainerConfig()
config.name = 'classifier_%s_%s' % (dataset.name, model.__class__.__name__)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'all': {
'dataset': all_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.stochastic_gradient = True
config.visualize = not args.no_visualize
config.model = model
home_path = Models.get_ref_model_path(args,
config.model.__class__.__name__,
dataset.name,
model_setup=True,
suffix_str='base0')
config.logger = Logger(home_path)
config.optim = optim.Adam(model.parameters(), lr=1e-3)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=10,
threshold=1e-2,
min_lr=1e-6,
factor=0.1,
verbose=True)
config.max_epoch = 120
if hasattr(model, 'train_config'):
model_train_config = model.train_config()
for key, value in model_train_config.items():
print('Overriding config.%s' % key)
config.__setattr__(key, value)
return config
def get_H_config(self, dataset, will_train=True):
print("Preparing training D1+D2 (H)")
print("Mixture size: %s" % colored('%d' % len(dataset), 'green'))
import global_vars as Global
# 80%, 20% for local train+test
train_ds, valid_ds = dataset.split_dataset(0.8)
if self.args.D1 in Global.mirror_augment:
print(colored("Mirror augmenting %s" % self.args.D1, 'green'))
new_train_ds = train_ds + MirroredDataset(train_ds)
train_ds = new_train_ds
# Initialize the multi-threaded loaders.
train_loader = DataLoader(train_ds,
batch_size=self.args.batch_size,
shuffle=True,
num_workers=self.args.workers,
pin_memory=True,
drop_last=True)
valid_loader = DataLoader(valid_ds,
batch_size=self.args.batch_size,
num_workers=self.args.workers,
pin_memory=True)
all_loader = DataLoader(dataset,
batch_size=self.args.batch_size,
num_workers=self.args.workers,
pin_memory=True)
# Set up the criterion
criterion = nn.BCEWithLogitsLoss().cuda()
# Set up the model
model = Global.get_ref_classifier(
self.args.D1)[self.default_model]().to(self.args.device)
self.add_identifier = model.__class__.__name__
if hasattr(model, 'preferred_name'):
self.add_identifier = model.preferred_name()
model = BinaryModelWrapper(model).to(self.args.device)
# Set up the config
config = IterativeTrainerConfig()
base_model_name = model.__class__.__name__
if hasattr(model, 'preferred_name'):
base_model_name = model.preferred_name()
config.name = '_%s[%s](%s->%s)' % (self.__class__.__name__,
base_model_name, self.args.D1,
self.args.D2)
config.train_loader = train_loader
config.valid_loader = valid_loader
config.phases = {
'train': {
'dataset': train_loader,
'backward': True
},
'test': {
'dataset': valid_loader,
'backward': False
},
'testU': {
'dataset': all_loader,
'backward': False
},
}
config.criterion = criterion
config.classification = True
config.cast_float_label = True
config.stochastic_gradient = True
config.visualize = not self.args.no_visualize
config.model = model
config.logger = Logger()
config.optim = optim.Adam(model.parameters(), lr=1e-3)
config.scheduler = optim.lr_scheduler.ReduceLROnPlateau(config.optim,
patience=5,
threshold=1e-2,
min_lr=1e-6,
factor=0.1,
verbose=True)
config.max_epoch = 30
if hasattr(model, 'train_config'):
model_train_config = model.train_config()
for key, value in model_train_config.iteritems():
print('Overriding config.%s' % key)
config.__setattr__(key, value)
return config