def main():
torch.manual_seed(6717449005)
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
train_loader, test_loader = mnist_data()
model = Lenet_300_100().to(device)
optimizer = optim.Adam(model.parameters())
criterion = my_loss(model, len(train_loader.dataset))
train(model, device, train_loader, criterion, optimizer, n_epochs=400)
model.set_flag('train', False)
test(model, device, train_loader, criterion)
model.set_flag('train', True)
evaluate(model, device, train_loader, criterion, 10)
criterion = my_loss(model, len(test_loader.dataset))
model.set_flag('train', False)
print('Mean')
test(model, device, test_loader, criterion)
model.set_flag('train', True)
print('Stochastic')
evaluate(model, device, test_loader, criterion, 10)
save(model)
def test_pl_model():
mnist = mnist_data()
cnn = CNN(num_channels=mnist.dims[0],
num_classes=mnist.num_classes) # Architecture
BaseLitModel(datamodule=mnist, backbone=cnn, lr=1e-3,
flood_height=0) # Lightning model
cnn = CNN(num_channels=mnist.dims[0],
num_classes=mnist.num_classes,
maxpool=False)
BaseLitModel(datamodule=mnist, backbone=cnn, lr=1e-3, flood_height=0)
def main():
torch.manual_seed(6717449005)
criterion = nn.CrossEntropyLoss()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
train_loader, test_loader = mnist_data()
model = Lenet_300_100().to(device)
optimizer = optim.Adam(model.parameters())
train(model, device, train_loader, criterion, optimizer)
test(model, device, test_loader, criterion)
save(model)
from torch import nn, optim
from torch.autograd.variable import Variable
from torchvision import transforms, datasets
from utils import Logger, mnist_data, images_to_vectors, vectors_to_images, noise
from discriminator import DiscriminatorNet
from generator import GeneratorNet
from trainers import train_discriminator, train_generator
# Hack for MNIST fetch error
from six.moves import urllib
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
urllib.request.install_opener(opener)
# Load data
data = mnist_data()
# Create loader with data, so that we can iterate over it
data_loader = torch.utils.data.DataLoader(data, batch_size=100, shuffle=True)
# Num batches
num_batches = len(data_loader)
use_cuda = torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
discriminator = DiscriminatorNet().to(device)
generator = GeneratorNet().to(device)
# Optimizers
d_optimizer = optim.Adam(discriminator.parameters(), lr=0.0002)
g_optimizer = optim.Adam(generator.parameters(), lr=0.0002)
def test_mnist_data():
mnist_data()
def test_ImagePredictionLogger():
mnist = mnist_data() # datamodule
return ImagePredictionLogger(mnist.val_dataloader())
def test_knnMonitorLogger():
mnist = mnist_data() # datamodule
test_transforms = ComposeMany([A.Normalize(mean=(0.0,), std=(1,)), ToTensorV2()])
memory_dataloader = mnist.train_dataloader(transforms=test_transforms)
test_dataloader = mnist.test_dataloader(transforms=test_transforms)
return knnMonitorLogger(memory_dataloader, test_dataloader, knn_k=1, knn_t=1)