def __init__(self, num_epochs, var, f_lr_mult=5.0, enable_cuda=False):
AbstractMethod.__init__(self)
self.g = None
self.f = None
self.dev_f_collection = None
g_models = [
MLPModel(input_dim=9, layer_widths=[20, 3],
activation=nn.LeakyReLU, var=var).double(),
]
f_models = [
MLPModel(input_dim=9, layer_widths=[20],
activation=nn.LeakyReLU, var=var).double(),
]
if torch.cuda.is_available() and enable_cuda:
for i, g in enumerate(g_models):
g_models[i] = g.cuda()
for i, f in enumerate(f_models):
f_models[i] = f.cuda()
g_learning_rates = [0.0005, 0.0002, 0.001]
game_objectives = [
OptimalMomentObjective(),
]
# g_learning_rates = [0.0005]
# game_objectives = [OptimalMomentObjective(lambda_1=0.5)]
learning_setups = []
for g_lr in g_learning_rates:
for game_objective in game_objectives:
learning_setup = {
"g_optimizer_factory": OptimizerFactory(
# OAdam, lr=float(g_lr), betas=(0.5, 0.9), weight_decay=1e-1),
OAdam, lr=float(g_lr), betas=(0.5, 0.9)),
"f_optimizer_factory": OptimizerFactory(
# OAdam, lr=float(g_lr), betas=(0.5, 0.9), weight_decay=1e-1),
OAdam, lr=f_lr_mult*float(g_lr), betas=(0.5, 0.9)),
"game_objective": game_objective
}
learning_setups.append(learning_setup)
default_g_opt_factory = OptimizerFactory(
Adam, lr=0.001, betas=(0.5, 0.9))
default_f_opt_factory = OptimizerFactory(
Adam, lr=0.005, betas=(0.5, 0.9))
g_simple_model_eval = SGDSimpleModelEval()
f_simple_model_eval = SGDSimpleModelEval()
learning_eval = FHistoryLearningEvalSGDNoStop(
num_epochs=num_epochs, eval_freq=20, print_freq=100, batch_size=1024)
self.model_selection = FHistoryModelSelectionV3(
g_model_list=g_models,
f_model_list=f_models,
learning_args_list=learning_setups,
default_g_optimizer_factory=default_g_opt_factory,
default_f_optimizer_factory=default_f_opt_factory,
g_simple_model_eval=g_simple_model_eval,
f_simple_model_eval=f_simple_model_eval,
learning_eval=learning_eval,
psi_eval_max_no_progress=20, psi_eval_burn_in=50)
self.default_g_opt_factory = default_g_opt_factory
def __init__(self, enable_cuda=False):
AbstractMethod.__init__(self)
self.g = None
self.f = None
self.dev_f_collection = None
g_models = [
MLPModel(input_dim=1, layer_widths=[200, 200],
activation=nn.LeakyReLU).double(),
]
f_models = [
DefaultCNN(cuda=enable_cuda),
#OtherCNN(cuda=enable_cuda),
#OtherCNNV2(cuda=enable_cuda),
#OtherCNNV3(cuda=enable_cuda),
]
if enable_cuda:
for g in g_models:
g.cuda()
g_learning_rates = [0.00010, 0.000050, 0.000020]
# g_learning_rates = [0.00001]
game_objective = OptimalMomentObjective()
# g_learning_rates = [0.0005]
# game_objectives = [OptimalMomentObjective(lambda_1=0.5)]
learning_setups = []
for g_lr in g_learning_rates:
learning_setup = {
"g_optimizer_factory": OptimizerFactory(
OAdam, lr=g_lr, betas=(0.5, 0.9)),
"f_optimizer_factory": OptimizerFactory(
OAdam, lr=5.0*g_lr, betas=(0.5, 0.9)),
"game_objective": game_objective
}
learning_setups.append(learning_setup)
default_g_opt_factory = OptimizerFactory(
Adam, lr=0.001, betas=(0.5, 0.9))
default_f_opt_factory = OptimizerFactory(
Adam, lr=0.0001, betas=(0.5, 0.9))
g_simple_model_eval = GradientDecentSimpleModelEval(
max_num_iter=4000, max_no_progress=10, eval_freq=100)
f_simple_model_eval = SGDSimpleModelEval(
max_num_epoch=50, max_no_progress=10, batch_size=512, eval_freq=1)
learning_eval = FHistoryLearningEvalSGDNoStop(
num_epochs=60, eval_freq=1, batch_size=1024)
self.model_selection = FHistoryModelSelectionV3(
g_model_list=g_models,
f_model_list=f_models,
learning_args_list=learning_setups,
default_g_optimizer_factory=default_g_opt_factory,
default_f_optimizer_factory=default_f_opt_factory,
g_simple_model_eval=g_simple_model_eval,
f_simple_model_eval=f_simple_model_eval,
learning_eval=learning_eval,
psi_eval_max_no_progress=10, psi_eval_burn_in=30,
)
self.default_g_opt_factory = default_g_opt_factory
def __init__(self, enable_cuda=False):
AbstractMethod.__init__(self)
self.g = None
self.f = None
self.dev_f_collection = None
g_models = [
DefaultCNN(cuda=enable_cuda),
]
f_models = [
DefaultCNN(cuda=enable_cuda),
# LeakySoftmaxCNN(input_c=1, input_h=28, input_w=28,
# channel_sizes=[10, 20], kernel_sizes=[3, 3],
# extra_padding=[0, 1], cuda=enable_cuda),
]
g_learning_rates = [5e-6, 2e-6, 1e-6]
# g_learning_rates = [0.00001]
game_objective = OptimalMomentObjective()
# g_learning_rates = [0.0005]
# game_objectives = [OptimalMomentObjective(lambda_1=0.5)]
learning_setups = []
for g_lr in g_learning_rates:
learning_setup = {
"g_optimizer_factory": OptimizerFactory(
OAdam, lr=g_lr, betas=(0.5, 0.9)),
"f_optimizer_factory": OptimizerFactory(
OAdam, lr=5.0*g_lr, betas=(0.5, 0.9)),
"game_objective": game_objective
}
learning_setups.append(learning_setup)
default_g_opt_factory = OptimizerFactory(
Adam, lr=0.0001, betas=(0.5, 0.9))
default_f_opt_factory = OptimizerFactory(
Adam, lr=0.0001, betas=(0.5, 0.9))
g_simple_model_eval = SGDSimpleModelEval(
max_num_epoch=50, max_no_progress=10, batch_size=1024, eval_freq=1)
f_simple_model_eval = SGDSimpleModelEval(
max_num_epoch=50, max_no_progress=10, batch_size=1024, eval_freq=1)
learning_eval = FHistoryLearningEvalSGDNoStop(
num_epochs=60, eval_freq=1, batch_size=1024)
self.model_selection = FHistoryModelSelectionV3(
g_model_list=g_models,
f_model_list=f_models,
learning_args_list=learning_setups,
default_g_optimizer_factory=default_g_opt_factory,
default_f_optimizer_factory=default_f_opt_factory,
g_simple_model_eval=g_simple_model_eval,
f_simple_model_eval=f_simple_model_eval,
learning_eval=learning_eval,
psi_eval_burn_in=30, psi_eval_max_no_progress=10,
)
self.default_g_opt_factory = default_g_opt_factory