def init_model_and_train(hidden_size, batch_size, train_size, n_epochs, lr, weight_decay,
betas0, betas1, seed):
# Parameters
num_hidden_layers = 1
out_channels = 1
if run_mode == "unfrozen_convolution_relu":
model = supervised_convnet.SupervisedConvNet(filter_size = 3, square_size = 3, \
hidden_size = hidden_size, out_channels = out_channels,
first_activation = "tanh", activation_func = "relu",
num_hidden_layers = num_hidden_layers, seed = seed)
results = train.trainer(model = model, batch_size = batch_size, train_size = train_size, n_epochs = n_epochs, lr = lr,
weight_decay = weight_decay,
betas0 = 1-betas0, betas1 = 1-betas1)
elif run_mode == "frozen_convolution_no_center_relu":
model = frozen.SupervisedConvNet(filter_size = 3, square_size = 3, \
hidden_size = hidden_size, out_channels = out_channels,
center = "omit", first_activation = "tanh",
activation_func = "relu", num_hidden_layers = num_hidden_layers)
results = train.trainer(model = model, batch_size = batch_size, train_size = train_size, n_epochs = n_epochs, lr = lr,
weight_decay = weight_decay,
betas0 = 1-betas0, betas1 = 1-betas1)
elif run_mode == "frozen_convolution_pretrained_relu":
model = frozen.SupervisedConvNet(filter_size = 3, square_size = 3, \
hidden_size = hidden_size, out_channels = out_channels,
center = "pre_trained", first_activation = "tanh",
activation_func = "relu", num_hidden_layers = num_hidden_layers)
results = train.trainer(model = model, batch_size = batch_size, train_size = train_size, n_epochs = n_epochs, lr = lr,
weight_decay = weight_decay,
betas0 = 1-betas0, betas1 = 1-betas1)
elif run_mode == "unfrozen_convolution_3_channels":
out_channels = 3
model = supervised_convnet.SupervisedConvNet(filter_size = 3, square_size = 3,
hidden_size = hidden_size, out_channels = out_channels,
first_activation = "tanh", activation_func = "relu",
num_hidden_layers = num_hidden_layers, seed = seed)
results = train.trainer(model = model, batch_size = batch_size, train_size = train_size, n_epochs = n_epochs, lr = lr,
weight_decay = weight_decay,
betas0 = 1-betas0, betas1 = 1-betas1)
return results
conv_params = defaultdict(list)
if run_mode == "unfrozen_convolution_relu":
"""
"""
out_channels = 1
filename = "unfrozen_convolution_relu.pl"
try:
with open(filename, "rb") as handle:
results = pickle.load(handle)
except:
results = []
results = []
for _ in range(500):
model = supervised_convnet.SupervisedConvNet(filter_size = 3, square_size = 3, \
hidden_size = hidden_size, out_channels = out_channels,
first_activation = "tanh", activation_func = "relu",
num_hidden_layers = num_hidden_layers, seed = time.time() + _)
model = model_to_cuda(model)
best_val_acc, param_dict = train.trainer(
model=model,
batch_size=100,
betas0=1 - 0.0018179320494754046,
betas1=1 - 0.001354073715524798,
lr=0.004388469485690077,
n_epochs=150,
train_size=5000,
weight_decay=0,
use_cuda=use_cuda)
results.append(best_val_acc)
conv_params["weight"].append(param_dict["conv1.weight"])
conv_params["bias"].append(param_dict["conv1.bias"])
out_channels = 1
# adjust learning rate?
adjust_learning_rate = False
# GPU?
use_cuda = True
# specify loss function
criterion = nn.BCELoss()
# tensorboard for tracking
writer = SummaryWriter(
comment="--batch size {}, training set {}, epoch {}, lr {}, \
weight decay {}, hidden_size {}, out_channels {}, num_hidden_layers {}"
.format(batch_size, train_size, n_epochs, lr, weight_decay, hidden_size,
out_channels, num_hidden_layers))
model = supervised_convnet.SupervisedConvNet(filter_size = 3, square_size = 3, \
hidden_size = hidden_size, out_channels = out_channels, num_hidden_layers = num_hidden_layers)
def trainer(model=model,
batch_size=batch_size,
train_size=train_size,
n_epochs=n_epochs,
lr=lr,
weight_decay=weight_decay,
adjust_learning_rate=adjust_learning_rate,
amsgrad=amsgrad,
betas0=betas0,
betas1=betas1,
use_cuda=use_cuda):
print("Testing out: ")
print("batch_size: ", batch_size)
hidden_size = 10
# adjust learning rate?
adjust_learning_rate = False
# specify loss function
criterion = nn.BCELoss()
# tensorboard for tracking
writer = SummaryWriter(
comment="--batch size {}, training set {}, epoch {}, lr {}, \
weight decay {}, hidden_size {}".format(
batch_size, train_size, n_epochs, lr, weight_decay, hidden_size))
# build model
model = supervised_convnet.SupervisedConvNet(filter_size=3,
square_size=3,
hidden_size=hidden_size)
# specify optimizer
optimizer = torch.optim.Adam(model.parameters(),
lr=lr,
weight_decay=weight_decay)
# prepare data loaders
train_isingdataset = supervised_convnet.IsingDataset(X_train[:train_size],
y_train[:train_size])
train_loader = torch.utils.data.DataLoader(train_isingdataset,
batch_size=batch_size,
num_workers=num_workers,
shuffle=True)