val_data = torch.utils.data.DataLoader(valset, batch_size=100, shuffle=False, num_workers=4)
testset = data_providers.CIFAR100(root='data', set_name='test', download=False, transform=transform_test)
test_data = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=4)
num_output_classes = 100
custom_conv_net = ConvolutionalNetwork(num_output_classes=num_output_classes) # initialize our network object, in this case a ConvNet
conv_experiment = ExperimentBuilder(network_model=custom_conv_net, use_gpu=args.use_gpu,
experiment_name=args.experiment_name,
num_epochs=args.num_epochs,
learning_rate=args.learning_rate,
weight_decay_coefficient = args.weight_decay,
torch.manual_seed(seed=args.seed) # sets pytorch's seed
train_data = data_providers.EMNISTDataProvider(
'train', batch_size=args.batch_size,
rng=rng) # initialize our rngs using the argument set seed
val_data = data_providers.EMNISTDataProvider(
'valid', batch_size=args.batch_size,
rng=rng) # initialize our rngs using the argument set seed
test_data = data_providers.EMNISTDataProvider(
'test', batch_size=args.batch_size,
rng=rng) # initialize our rngs using the argument set seed
custom_conv_net = ConvolutionalNetwork( # initialize our network object, in this case a ConvNet
input_shape=(args.batch_size, args.image_num_channels, args.image_height,
args.image_width),
dim_reduction_type=args.dim_reduction_type,
num_output_classes=train_data.num_classes,
num_filters=args.num_filters,
num_layers=args.num_layers,
use_bias=False)
conv_experiment = ExperimentBuilder(
network_model=custom_conv_net,
experiment_name=args.experiment_name,
num_epochs=args.num_epochs,
weight_decay_coefficient=args.weight_decay_coefficient,
gpu_id=args.gpu_id,
use_gpu=args.use_gpu,
continue_from_epoch=args.continue_from_epoch,
train_data=train_data,
val_data=val_data,
test_data=test_data) # build an experiment object