def draw(count, memory_size, file, device='cuda'):
testtransform = transforms.Compose([transforms.ToTensor()])
testset = torchvision.datasets.MNIST(root='./data/mnist', train=False,
download=True, transform=testtransform)
testloader = torch.utils.data.DataLoader(testset, pin_memory=True, batch_size=128,
shuffle=True, num_workers=10)
base_dir = os.path.join('mnist_' + str(memory_size), "6")
model = MnistDraw(count, memory_size, output_stages=True)
optimizer = optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=0)
from datetime import datetime
current_time = datetime.now().strftime('%b%d_%H-%M-%S')
from visualise import StagesGrid
trial = Trial(model, optimizer, nn.MSELoss(reduction='sum'), ['loss'], pass_state=True, callbacks=[
callbacks.TensorBoardImages(comment=current_time, nrow=10, num_images=20, name='Prediction', write_each_epoch=True,
key=torchbearer.Y_PRED, pad_value=1),
callbacks.TensorBoardImages(comment=current_time + '_mnist', nrow=10, num_images=20, name='Target', write_each_epoch=False,
key=torchbearer.Y_TRUE, pad_value=1),
StagesGrid('mnist_stages.png', STAGES, 20)
]).load_state_dict(torch.load(os.path.join(base_dir, file)), resume=False).with_generators(train_generator=testloader, val_generator=testloader).for_train_steps(1).for_val_steps(1).to(device)
trial.run() # Evaluate doesn't work with tensorboard in torchbearer, seems to have been fixed in most recent version
def run(count, memory_size, device='cuda'):
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=10)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=10)
base_dir = os.path.join('cifar_' + str(memory_size), str(count))
model = nn.DataParallel(CifarClassifier(count, memory_size))
optimizer = optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=0.001, momentum=0.9, weight_decay=5e-4)
trial = Trial(model, optimizer, nn.NLLLoss(), [torchbearer.metrics.CategoricalAccuracy(), 'loss'], callbacks=[
callbacks.MostRecent(os.path.join(base_dir, '{epoch:02d}.pt')),
callbacks.GradientClipping(5),
callbacks.MultiStepLR(milestones=[150, 250]),
callbacks.TensorBoard(write_graph=False, comment=base_dir)
]).with_train_generator(trainloader).to(device)
trial.run(350)
trial.with_test_generator(testloader).evaluate(data_key=torchbearer.TEST_DATA)
def run(count, memory_size, iteration, device='cuda'):
traintransform = transforms.Compose(
[transforms.RandomRotation(20),
transforms.ToTensor()])
trainset = torchvision.datasets.MNIST(root='./data/mnist',
train=True,
download=True,
transform=traintransform)
trainloader = torch.utils.data.DataLoader(trainset,
pin_memory=True,
batch_size=128,
shuffle=True,
num_workers=10)
testtransform = transforms.Compose([transforms.ToTensor()])
testset = torchvision.datasets.MNIST(root='./data/mnist',
train=False,
download=True,
transform=testtransform)
testloader = torch.utils.data.DataLoader(testset,
pin_memory=True,
batch_size=128,
shuffle=True,
num_workers=10)
base_dir = os.path.join('mnist_' + str(memory_size), "4")
model = MnistDraw(count, memory_size)
optimizer = optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=1e-3)
from datetime import datetime
current_time = datetime.now().strftime('%b%d_%H-%M-%S')
trial = Trial(
model,
optimizer,
nn.MSELoss(reduction='sum'), ['loss'],
pass_state=True,
callbacks=[
tm.kl_divergence(MU, LOGVAR),
callbacks.MostRecent(
os.path.join(base_dir,
'iter_' + str(iteration) + '.{epoch:02d}.pt')),
callbacks.GradientClipping(5),
callbacks.ExponentialLR(0.99),
callbacks.TensorBoardImages(comment=current_time,
name='Prediction',
write_each_epoch=True,
key=torchbearer.Y_PRED),
callbacks.TensorBoardImages(comment=current_time + '_mnist',
name='Target',
write_each_epoch=True,
key=torchbearer.Y_TRUE)
]).with_generators(train_generator=trainloader,
val_generator=testloader).to(device)
trial.run(100)
def run(count, memory_size, file, device='cuda'):
transform_train = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.ColorJitter(0.25, 0.25, 0.25, 0.25),
transforms.ToTensor()
])
transform_test = transforms.Compose([transforms.ToTensor()])
trainset = torchvision.datasets.CIFAR10(root='./data',
train=True,
download=True,
transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset,
batch_size=128,
shuffle=True,
num_workers=10)
testset = torchvision.datasets.CIFAR10(root='./data',
train=False,
download=True,
transform=transform_test)
testloader = torch.utils.data.DataLoader(testset,
batch_size=100,
shuffle=False,
num_workers=10)
base_dir = os.path.join('cifarss_' + str(memory_size), "16")
model = CifarDraw(count, memory_size)
model.load_state_dict(torch.load(file)[torchbearer.MODEL])
model = SelfTaught(count, 512, memory_size, model.memory)
for param in model.memory.parameters():
param.requires_grad = False
model.memory.decay.requires_grad = True
model.memory.learn.requires_grad = True
model.memory.learn2.requires_grad = True
optimizer = optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=1e-3)
trial = Trial(model,
optimizer,
nn.NLLLoss(), ['acc', 'loss'],
pass_state=True,
callbacks=[
callbacks.MultiStepLR([25, 40, 45]),
callbacks.MostRecent(
os.path.join(base_dir, '{epoch:02d}.pt')),
callbacks.GradientClipping(5)
]).with_generators(
train_generator=trainloader,
val_generator=testloader).for_val_steps(5).to(device)
trial.run(50)
def train(self, model, **kwargs) -> (float, float):
# Get transfer model and put it in training mode
net = model.net
net.train()
# Create optimiser
optimiser = optim.Adam(net.parameters(), lr=1e-4)
# Check for cuda
device = "cuda:0" if torch.cuda.is_available() else "cpu"
print("Training using", device)
# Setup loss function
if self.class_weight_method != ClassWeightMethod.Unweighted:
distribution = class_distribution("data/processed/train")
if self.class_weight_method == ClassWeightMethod.SumBased:
inv_distribution = [
1 - x / np.sum(distribution) for x in distribution
]
inv_distribution = torch.from_numpy(
np.array(inv_distribution)).float()
elif self.class_weight_method == ClassWeightMethod.MaxBased:
inv_distribution = [
np.max(distribution) / x for x in distribution
]
inv_distribution = torch.from_numpy(
np.array(inv_distribution)).float()
else:
raise IndexError("Unknown class weight method " +
str(self.class_weight_method))
loss_function = self.loss(inv_distribution.to(device))
else:
loss_function = self.loss()
# Setup trial
trial = Trial(net,
optimiser,
loss_function,
metrics=["loss", "accuracy"]).to(device)
trial.with_generators(
self.image_datasets.train_loader,
test_generator=self.image_datasets.validation_loader,
)
# Actually run the training
trial.run(epochs=self.num_epochs)
# Evaluate and show results
time.sleep(0.1) # Ensure training has finished
net.eval()
results = trial.evaluate(data_key=torchbearer.TEST_DATA)
acc = float(results["test_acc"])
loss = float(results["test_loss"])
return acc, loss
def run(count, memory_size, device='cuda'):
traintransform = transforms.Compose([
transforms.RandomRotation(20),
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])
trainset = torchvision.datasets.MNIST(root='./data/mnist',
train=True,
download=True,
transform=traintransform)
trainloader = torch.utils.data.DataLoader(trainset,
pin_memory=True,
batch_size=128,
shuffle=True,
num_workers=10)
testtransform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))])
testset = torchvision.datasets.MNIST(root='./data/mnist',
train=False,
download=True,
transform=testtransform)
testloader = torch.utils.data.DataLoader(testset,
pin_memory=True,
batch_size=128,
shuffle=False,
num_workers=10)
base_dir = os.path.join('mnist_' + str(memory_size), str(count))
model = MnistClassifier(count, memory_size)
optimizer = optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=0.001)
trial = Trial(
model,
optimizer,
nn.NLLLoss(), ['acc', 'loss'],
callbacks=[
callbacks.MostRecent(os.path.join(base_dir, '{epoch:02d}.pt')),
callbacks.GradientClipping(5),
callbacks.MultiStepLR(milestones=[50, 100, 150, 190, 195]),
callbacks.ExponentialLR(0.99),
callbacks.TensorBoard(write_graph=False, comment=base_dir)
]).with_train_generator(trainloader).to(device)
trial.run(200)
trial.with_test_generator(testloader).evaluate(
data_key=torchbearer.TEST_DATA)
def draw(file, device='cuda'):
transform_test = transforms.Compose([transforms.ToTensor()])
testset = torchvision.datasets.CIFAR10(root='./data',
train=False,
download=True,
transform=transform_test)
testloader = torch.utils.data.DataLoader(testset,
batch_size=100,
shuffle=False,
num_workers=10)
base_dir = 'cifar_vae'
model = CifarVAE()
optimizer = optim.SGD(filter(lambda p: p.requires_grad,
model.parameters()),
lr=0)
from datetime import datetime
current_time = datetime.now().strftime('%b%d_%H-%M-%S')
trial = Trial(
model,
optimizer,
nn.MSELoss(reduction='sum'), ['acc', 'loss'],
pass_state=True,
callbacks=[
callbacks.TensorBoardImages(comment=current_time,
name='Prediction',
write_each_epoch=True,
key=torchbearer.Y_PRED,
pad_value=1,
nrow=16),
callbacks.TensorBoardImages(comment=current_time + '_cifar_vae',
name='Target',
write_each_epoch=False,
key=torchbearer.Y_TRUE,
pad_value=1,
nrow=16)
]).load_state_dict(
torch.load(os.path.join(base_dir, file)),
resume=False).with_generators(
train_generator=testloader,
val_generator=testloader).for_train_steps(1).to(device)
trial.run(
) # Evaluate doesn't work with tensorboard in torchbearer, seems to have been fixed in most recent version
def train_model(
model: nn.Module,
train_loader: DataLoader,
val_loader: DataLoader = None,
output_path: str = None,
):
# Define the loss function and the optimiser
loss_function = nn.MSELoss()
optimiser = optim.Adam(model.parameters())
device = "cuda:0" if torch.cuda.is_available() else "cpu"
trial = Trial(model, optimiser, loss_function, metrics=["loss"]).to(device)
trial.with_generators(train_loader, val_generator=val_loader)
trial.run(epochs=100)
if output_path:
torch.save(model.state_dict(), output_path)
return trial
def train_model(train, valid, test, classes, batch, num_epochs):
# model = CNN(3, classes)
model = models.resnet18()
train_loader = DataLoader(train, batch_size=batch)
val_loader = DataLoader(valid, batch_size=batch)
test_loader = DataLoader(test, batch_size=batch)
# define the loss function and the optimiser
loss_function = nn.CrossEntropyLoss() # equation 8 in original paper
optimiser = optim.Adam(model.parameters())
trial = Trial(model, optimiser, loss_function, metrics=['loss', 'accuracy'], verbose=1).to(device)
trial.with_generators(train_loader, val_generator=val_loader, test_generator=test_loader)
trial.run(epochs=num_epochs)
results_test = trial.evaluate(data_key=torchbearer.TEST_DATA)
results_val = trial.evaluate(data_key=torchbearer.VALIDATION_DATA)
print(results_test)
return results_test, results_val
def run(train_batch_size,
val_batch_size,
epochs,
lr,
log_interval,
input_size=10,
hidden_size=100,
out_size=4):
dataset = FuzzBuzzDataset(input_size)
splitter = DatasetValidationSplitter(len(dataset), 0.1)
train_set = splitter.get_train_dataset(dataset)
val_set = splitter.get_val_dataset(dataset)
train_loader = DataLoader(train_set,
pin_memory=True,
batch_size=train_batch_size,
shuffle=True,
num_workers=2)
val_loader = DataLoader(val_set,
pin_memory=True,
batch_size=val_batch_size,
shuffle=False,
num_workers=2)
model = FuzzBuzzModel(input_size, hidden_size, out_size)
device = 'cpu'
if torch.cuda.is_available():
device = 'cuda'
optimizer = optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=lr)
loss = nn.CrossEntropyLoss()
trial = Trial(model, optimizer, criterion=loss,
metrics=['acc', 'loss']).to(device)
trial = trial.with_generators(train_generator=train_loader,
val_generator=val_loader)
trial.run(epochs=epochs)
trial.evaluate(data_key=VALIDATION_DATA)
def run(count, glimpse_size, memory_size, iteration, device='cuda'):
base_dir = os.path.join('celeba_' + str(memory_size), str(glimpse_size))
if not os.path.exists(base_dir):
os.makedirs(base_dir)
transform_train = transforms.Compose([
transforms.ToTensor()
])
dataset = torchvision.datasets.ImageFolder(root='./cropped_celeba/', transform=transform_train)
splitter = DatasetValidationSplitter(len(dataset), 0.05)
trainset = splitter.get_train_dataset(dataset)
# Save the ids
torch.save((splitter.train_ids, splitter.valid_ids), os.path.join(base_dir, 'split.dat'))
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=10)
model = CelebDraw(count, glimpse_size, memory_size)
optimizer = optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), lr=1e-4)
from datetime import datetime
current_time = datetime.now().strftime('%b%d_%H-%M-%S')
call_a = callbacks.TensorBoardImages(comment=current_time, name='Prediction', write_each_epoch=True, key=torchbearer.Y_PRED)
call_a.on_step_training = call_a.on_step_validation # Hack to make this log training samples
call_b = callbacks.TensorBoardImages(comment=current_time + '_celeba', name='Target', write_each_epoch=True,
key=torchbearer.Y_TRUE)
call_b.on_step_training = call_b.on_step_validation # Hack to make this log training samples
trial = Trial(model, optimizer, nn.MSELoss(reduction='sum'), ['acc', 'loss'], pass_state=True, callbacks=[
joint_kl_divergence(MU, LOGVAR),
callbacks.MostRecent(os.path.join(base_dir, 'iter_' + str(iteration) + '.{epoch:02d}.pt')),
callbacks.GradientClipping(5),
call_a,
call_b
]).with_generators(train_generator=trainloader).to(device)
trial.run(100)
def draw(count, glimpse_size, memory_size, file, device='cuda'):
base_dir = os.path.join('celeba_' + str(memory_size), str(glimpse_size))
transform = transforms.Compose([
transforms.ToTensor()
])
dataset = torchvision.datasets.ImageFolder(root='./cropped_celeba/', transform=transform)
splitter = DatasetValidationSplitter(len(dataset), 0.05)
# load the ids
splitter.train_ids, splitter.valid_ids = torch.load(os.path.join(base_dir, 'split.dat'))
testset = splitter.get_val_dataset(dataset)
testloader = torch.utils.data.DataLoader(testset, batch_size=128, shuffle=True, num_workers=10)
model = CelebDraw(count, glimpse_size, memory_size, output_stages=True)
optimizer = optim.SGD(filter(lambda p: p.requires_grad, model.parameters()), lr=0)
from datetime import datetime
current_time = datetime.now().strftime('%b%d_%H-%M-%S')
from visualise import StagesGrid
trial = Trial(model, optimizer, nn.MSELoss(reduction='sum'), ['loss'], pass_state=True, callbacks=[
callbacks.TensorBoardImages(comment=current_time, nrow=10, num_images=20, name='Prediction', write_each_epoch=True,
key=torchbearer.Y_PRED, pad_value=1),
callbacks.TensorBoardImages(comment=current_time + '_celeb', nrow=10, num_images=20, name='Target', write_each_epoch=False,
key=torchbearer.Y_TRUE, pad_value=1),
callbacks.TensorBoardImages(comment=current_time + '_celeb_mask', nrow=10, num_images=20, name='Masked Target', write_each_epoch=False,
key=MASKED_TARGET, pad_value=1),
StagesGrid('celeb_stages.png', STAGES, 20)
]).load_state_dict(torch.load(os.path.join(base_dir, file)), resume=False).with_generators(train_generator=testloader, val_generator=testloader).for_train_steps(1).for_val_steps(1).to(device)
trial.run() # Evaluate doesn't work with tensorboard in torchbearer, seems to have been fixed in most recent version
def train(self):
scheduler = torch_scheduler.StepLR(self.num_epochs_decay,
gamma=self.decay_factor)
loss_plot_plan = os.path.join(
self.result_path, 'live_loss_plot%s-%d-%.4f-%d-%.4f.png' %
(self.model_type, self.num_epochs, self.lr, self.num_epochs_decay,
self.augmentation_prob))
callbacks = [scheduler]
# imaging.FromState(torchbearer.X).on_val().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_TRUE).on_val().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_PRED).on_val().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.X).on_test().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_TRUE).on_test().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_PRED).on_test().cache(16).make_grid().to_pyplot(),
# TensorBoard(write_batch_metrics=True),
trial = Trial(
self.unet,
self.optimizer,
self.criterion,
metrics=['loss', 'binary_acc'],
# binary_acc for debugging certain things
callbacks=callbacks).to(self.device)
trial.with_generators(train_generator=self.train_loader,
val_generator=self.valid_loader,
test_generator=self.test_loader)
start = time.time()
history = trial.run(epochs=self.num_epochs, verbose=2)
stop = time.time()
train_time = stop - start
state = self.unet.state_dict()
unet_path = os.path.join(
self.model_path,
'%s-%d-%.4f-%d-%.4f_Index_BCE_Dropout_STAREIndex.pkl' % (
self.model_type,
self.num_epochs,
self.lr,
self.num_epochs_decay,
self.augmentation_prob,
))
torch.save(state, unet_path)
print(history)
### Testing
results = trial.evaluate(data_key=torchbearer.TEST_DATA)
print("Test result:")
print(results)
return history, results
def run(hidden_size: int, file_prefix: str, epochs: int = 20):
# Flatten 28*28 images to a 784 vector for each image
transform = transforms.Compose([
transforms.ToTensor(), # convert to tensor
transforms.Lambda(lambda x: x.view(-1)), # flatten into vector
])
trainset = MNIST(".", train=True, download=True, transform=transform)
testset = MNIST(".", train=False, download=True, transform=transform)
data_size = torch.numel(trainset[0][0])
# Create data loaders
trainloader = DataLoader(trainset,
batch_size=128,
shuffle=True,
drop_last=False)
testloader = DataLoader(testset,
batch_size=128,
shuffle=True,
drop_last=False)
model = SingleHiddenLayerMLP(data_size, hidden_size, 10)
loss_function = nn.CrossEntropyLoss()
optimiser = optim.Adam(model.parameters())
device = "cuda" if torch.cuda.is_available() else "cpu"
cm = (PyCM().on_train().with_handler(
to_pandas_seaborn(normalize=True, title="Confusion Matrix: {epoch}")))
callbacks = [cm]
trial = Trial(
model,
optimiser,
loss_function,
metrics=["loss", "accuracy"],
callbacks=callbacks,
)
trial.to(device)
trial.with_generators(trainloader, val_generator=testloader, val_steps=1)
history = trial.run(epochs=epochs)
return history
if state[torchbearer.BATCH] % 10 == 0:
w = state[torchbearer.MODEL].w[0].detach().to('cpu').numpy()
b = state[torchbearer.MODEL].b[0].detach().to('cpu').numpy()
z = (w.dot(xy) + b).reshape(x.shape)
z[np.where(z > 1.)] = 4
z[np.where((z > 0.) & (z <= 1.))] = 3
z[np.where((z > -1.) & (z <= 0.))] = 2
z[np.where(z <= -1.)] = 1
if CONTOUR in state:
for coll in state[CONTOUR].collections:
coll.remove()
state[CONTOUR] = plt.contourf(x, y, z, cmap=plt.cm.jet, alpha=0.5)
else:
state[CONTOUR] = plt.contourf(x, y, z, cmap=plt.cm.jet, alpha=0.5)
plt.tight_layout()
plt.show()
mypause(0.001)
svm = LinearSVM()
model = Trial(svm, optim.SGD(svm.parameters(), 0.1), hinge_loss, ['loss'],
callbacks=[scatter, draw_margin, ExponentialLR(0.999, step_on_batch=True), L2WeightDecay(0.01, params=[svm.w])]).to('cuda')
model.with_train_data(X, Y, batch_size=32)
model.run(epochs=50, verbose=1)
plt.ioff()
plt.show()
A.RGBShift(r_shift_limit=15, g_shift_limit=15, b_shift_limit=15,
p=0.5),
A.RandomBrightnessContrast(p=0.5),
A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
ToTensorV2(),
])
# load dataset
trainset = CourseworkDataset(tfms, 'train', path2phow_features)
trainloader = DataLoader(trainset, batch_size=256, shuffle=True)
valset = CourseworkDataset(tfms, 'test', path2phow_features)
valloader = DataLoader(valset, batch_size=256, shuffle=True)
testset = CourseworkDataset(tfms, 'predict', path2phow_features)
testloader = DataLoader(testset, batch_size=256, shuffle=True)
# define model and loss
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = ClassifierNet().to(device)
optimizer = optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=0.001)
loss = nn.CrossEntropyLoss()
# begin to train
trial = Trial(model, optimizer, loss, metrics=['acc', 'loss']).to(device)
trial.with_loader(custom_loader)
trial.with_generators(train_generator=trainloader,
val_generator=valloader,
test_generator=testloader)
history = trial.run(epochs=50, verbose=1)
def run(iteration, device='cuda:1'):
transform_train = transforms.Compose([
transforms.RandomHorizontalFlip(),
transforms.ColorJitter(0.25, 0.25, 0.25, 0.25),
transforms.ToTensor()
])
transform_test = transforms.Compose([transforms.ToTensor()])
trainset = torchvision.datasets.CIFAR10(root='./data',
train=True,
download=True,
transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset,
batch_size=128,
shuffle=True,
num_workers=10)
testset = torchvision.datasets.CIFAR10(root='./data',
train=False,
download=True,
transform=transform_test)
testloader = torch.utils.data.DataLoader(testset,
batch_size=100,
shuffle=False,
num_workers=10)
base_dir = 'cifar_vae'
model = CifarVAE()
optimizer = optim.Adam(filter(lambda p: p.requires_grad,
model.parameters()),
lr=5e-4)
from datetime import datetime
current_time = datetime.now().strftime('%b%d_%H-%M-%S')
trial = Trial(
model,
optimizer,
nn.MSELoss(reduction='sum'), ['acc', 'loss'],
pass_state=True,
callbacks=[
tm.kl_divergence(MU, LOGVAR, beta=2),
callbacks.MultiStepLR([50, 90]),
callbacks.MostRecent(
os.path.join(base_dir,
'iter_' + str(iteration) + '.{epoch:02d}.pt')),
callbacks.GradientClipping(5),
callbacks.TensorBoardImages(comment=current_time,
name='Prediction',
write_each_epoch=True,
key=torchbearer.Y_PRED),
callbacks.TensorBoardImages(comment=current_time + '_cifar_vae',
name='Target',
write_each_epoch=False,
key=torchbearer.Y_TRUE),
]).with_generators(
train_generator=trainloader,
val_generator=testloader).for_val_steps(5).to(device)
trial.run(100)
comparison = torch.cat([
data[:num_images],
recon_batch.view(128, 1, 28, 28)[:num_images]
])
save_image(comparison.cpu(),
str(folder) + 'reconstruction_' +
str(state[torchbearer.EPOCH]) + '.png',
nrow=num_images)
return saver
model = VAE()
optimizer = optim.Adam(filter(lambda p: p.requires_grad, model.parameters()),
lr=0.001)
loss = binary_cross_entropy
from torchbearer import Trial
torchbearer_trial = Trial(
model,
optimizer,
loss,
metrics=['acc', 'loss'],
callbacks=[add_kld_loss_callback,
save_reconstruction_callback()],
pass_state=True).to('cuda')
torchbearer_trial.with_generators(train_generator=traingen,
val_generator=valgen)
torchbearer_trial.run(epochs=10)
# test_set = CIFAR10('./data', train=False, download=True, transform=transforms.Compose([transform_test]))
test_gen = torch.utils.data.DataLoader(test_set,
pin_memory=True,
batch_size=128,
shuffle=False,
num_workers=4)
optimizer = optim.SGD(net.parameters(),
lr=0.1,
momentum=0.9,
weight_decay=1e-4)
from torchbearer.callbacks import MultiStepLR, TensorBoard
from torchbearer import Trial
from datetime import datetime
current_time = datetime.now().strftime('%b%d_%H-%M-%S')
trial = Trial(net,
optimizer,
nn.CrossEntropyLoss(),
metrics=['acc', 'loss'],
callbacks=[
UnpackState(),
TensorBoard(write_graph=False, comment=current_time),
MultiStepLR([100, 150])
])
trial.with_generators(train_generator=train_gen,
val_generator=test_gen).to('cuda')
trial.run(200, verbose=1)
def train(self):
"""Train encoder, generator and discriminator."""
# D_LOSS = state_key('d_loss')
#
# def dice_loss(prediction, target):
# """Calculating the dice loss
# Args:
# prediction = predicted image
# target = Targeted image
# Output:
# dice_loss"""
#
# smooth = 1.0
# # print(prediction.shape)
# # print(target.shape)
# # TODO: Used reshape() instead of view because of batch size > 1
# i_flat = prediction.reshape(-1)
# t_flat = target.reshape(-1)
#
# intersection = (i_flat * t_flat).sum()
#
# return 1 - ((2. * intersection + smooth) / (i_flat.sum() + t_flat.sum() + smooth))
#
# def calc_loss(prediction, target, bce_weight=0.5):
# """Calculating the loss and metrics
# Args:
# prediction = predicted image
# target = Targeted image
# metrics = Metrics printed
# bce_weight = 0.5 (default)
# Output:
# loss : dice loss of the epoch """
# bce = F.binary_cross_entropy_with_logits(prediction, target)
# prediction = F.sigmoid(prediction)
# dice = dice_loss(prediction, target)
#
# loss = bce * bce_weight + dice * (1 - bce_weight)
# state[D_LOSS] = loss
#
# return loss
#
# stopping = EarlyStopping(monitor='val_acc', patience=5, mode='max')
scheduler = torch_scheduler.StepLR(self.num_epochs_decay, gamma=0.1)
loss_plot_plan = os.path.join(self.result_path,
'live_loss_plot%s-%d-%.4f-%d-%.4f.png' % (self.model_type,
self.num_epochs,
self.lr,
self.num_epochs_decay,
self.augmentation_prob))
callbacks = [scheduler]
# imaging.FromState(torchbearer.X).on_val().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_TRUE).on_val().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_PRED).on_val().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.X).on_test().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_TRUE).on_test().cache(16).make_grid().to_pyplot(),
# imaging.FromState(torchbearer.Y_PRED).on_test().cache(16).make_grid().to_pyplot(),
# TensorBoard(write_batch_metrics=True),
try:
trial = Trial(self.unet, self.optimizer, self.criterion, metrics=['loss', 'binary_acc'],
# binary_acc for debugging certain things
callbacks=callbacks).to(self.device)
trial.with_generators(train_generator=self.train_loader,
val_generator=self.valid_loader,
test_generator=self.test_loader)
start = time.time()
history = trial.run(epochs=self.num_epochs, verbose=2)
stop = time.time()
train_time = stop - start
state = self.unet.state_dict()
unet_path = os.path.join(self.model_path,
'%s-%d-%.4f-%d-%.4f_Index_BCE_Dropout_STAREIndex.pkl' % (self.model_type,
self.num_epochs,
self.lr,
self.num_epochs_decay,
self.augmentation_prob,))
torch.save(state, unet_path)
print(history)
### Testing
results = trial.evaluate(data_key=torchbearer.TEST_DATA)
print("Test result:")
print(results)
except (RuntimeError, OSError):
state = self.unet.state_dict()
unet_path = os.path.join(self.model_path,
'%s-%d-%.4f-%d-%.4f_Index_BCE_Dropout_STAREIndex.pkl' % (self.model_type,
self.num_epochs,
self.lr,
self.num_epochs_decay,
self.augmentation_prob,))
torch.save(state, unet_path[:-4] + 'interrupted' + '.pkl')
optimizer = torch.optim.SGD(model.parameters(),
0.1,
momentum=0.9,
weight_decay=1e-4)
# optimiser = optim.RMSprop(model.parameters(), alpha=0.9, lr=0.0001, weight_decay=1e-6)
loss_function = nn.CrossEntropyLoss()
# device = "cuda:0" if torch.cuda.is_available() else "cpu"
trial = Trial(model,
optimizer,
loss_function,
metrics=['loss', 'acc', 'top_5_acc'],
callbacks=[
callbacks.TensorBoard(write_graph=False,
comment=f'resnet50_{n_bn}_{rep}'),
callbacks.MultiStepLR([30, 60]),
callbacks.MostRecent(dir + model_file + '_{epoch:02d}.pt')
]).to('cuda')
trial.with_generators(trainloader, test_generator=testloader)
pattern = re.compile(model_file + '_\d+.pt')
for filepath in os.listdir(dir):
if pattern.match(filepath):
trial.load_state_dict(torch.load(dir + filepath))
trial.run(epochs=90)
trial.evaluate(data_key=torchbearer.TEST_DATA)
torch.save(model.module.state_dict(), dir + model_file + '.pt')
for key, value in regime.items():
if key <= epoch:
lr = value
else:
break
print("set lr to : ", lr)
return lr
scheduler = LambdaLR(lr_lambda=[lr_func])
@on_step_training
def clip(serial):
alexnetBin.clamp()
trial = Trial(alexnetBin,
optimizer,
criterion=loss,
metrics=['acc', 'loss'],
callbacks=[clip, scheduler]).to('cuda')
trial = trial.with_generators(train_generator=train_set,
val_generator=valid_set,
test_generator=test_set)
trial.run(epochs=EPOCH_NB)
trial.evaluate(data_key=TEST_DATA)
alexnetBin.train()
testloader = DataLoader(testset, batch_size=128, shuffle=True) valloader = DataLoader(valset, batch_size=128, shuffle=True) # build the model model = SimpleCNN() # define the loss function and the optimiser loss_function = nn.CrossEntropyLoss() live_loss_plot = LiveLossPlot(draw_once=True) optimiser = optim.Adam(model.parameters(), lr=0.001) scheduler = StepLR(step_size=10, gamma=0.5) device = "cuda:0" if torch.cuda.is_available() else "cpu" trial = Trial(model, optimiser, loss_function, callbacks=[scheduler, live_loss_plot], metrics=['loss', 'accuracy']).to(device) trial.with_generators(trainloader, val_generator=valloader, test_generator=testloader) history = trial.run(verbose=1, epochs=30)# results = trial.evaluate(data_key=torchbearer.TEST_DATA) print(results) # build the model model = SimpleCNN() # define the loss function and the optimiser loss_function = nn.CrossEntropyLoss() live_loss_plot = LiveLossPlot(draw_once=True) optimiser = optim.Adam(model.parameters(), lr=0.001) scheduler = StepLR(step_size=10, gamma=0.5) device = "cuda:0" if torch.cuda.is_available() else "cpu" trial = Trial(model, optimiser, loss_function, callbacks=[scheduler, live_loss_plot], metrics=['loss', 'accuracy']).to(device)
super().__init__('roc_auc_score',
lambda y_pred, y_true: sklearn.metrics.roc_auc_score(y_true.cpu().numpy(), y_pred.detach().sigmoid().cpu().numpy()),
running=False)
metrics_append = [RocAucScore()]
if args.dataset == 'imagenet_a':
from datasets.imagenet_a import indices_in_1k
@on_forward_validation
def map_preds(state):
state[torchbearer.PREDICTION] = state[torchbearer.PREDICTION][:, indices_in_1k]
cb.append(map_preds)
print('==> Training model..')
acc = 'acc'
if args.dataset in ['toxic', 'toxic_bert', 'imdb', 'yelp_2']:
acc = 'binary_acc'
trial = Trial(net, optimizer, criterion, metrics=[acc, 'loss', 'lr'] + metrics_append, callbacks=cb)
trial.with_generators(train_generator=trainloader, val_generator=valloader, train_steps=args.train_steps, test_generator=testloader).to(args.device)
if args.reload:
state = torch.load(args.model_file)
trial.load_state_dict(state, resume=args.dataset != 'imagenet_a')
trial.replay()
if trainloader is not None:
trial.run(args.epoch, verbose=args.verbose)
trial.evaluate(data_key=torchbearer.TEST_DATA)
model = torch.load('fashionMNIST_VAE_20epochs.pytorchweights')
model_parameters = filter(lambda p: p.requires_grad, model.parameters())
print(sum([np.prod(p.size()) for p in model_parameters]))
optimizer = optim.Adam(
filter(lambda p: p.requires_grad, model.parameters()), lr=5e-4)
trial = Trial(model, optimizer, nn.MSELoss(reduction='sum'), metrics=['acc', 'loss'], callbacks=[
beta_kl(MU, LOGVAR),
callbacks.ConsolePrinter(),
plot_progress()
], verbose=1).with_generators(train_generator=traingen, test_generator=testgen)
history = trial.run(10)
trial.evaluate(verbose=0, data_key=torchbearer.TEST_DATA)
torch.save(model, 'fashionMNIST_VAE_30epochs.pytorchweights')
# torch.save(model, 'fashionMNIST_VAE_10epochs.pytorchweights')
print(history)
train_loss_list = []
val_loss_list = []
for item in history:
train_loss_list.append(item['running_loss'])
val_loss_list.append(item['test_loss'])
fig1 = plt.figure('1')
ax1 = fig1.gca()
ax1.plot(train_loss_list, color='blue', alpha=0.7)
ax1.plot(val_loss_list, color='red', alpha=0.7)
plt.imshow(out.detach().numpy()[0, 0, :, :])
plt.show()
out = F.relu(out)
out = self.conv2(out)
out = F.relu(out)
out = self.gmp1(out)
out = out.view(out.shape[0], -1)
out = self.fc1(out)
out = F.relu(out)
out = self.fc2(out)
return out
model = BetterCNN()
loss_function = nn.L1Loss()
optimiser = optim.Adam(model.parameters())
device = "cuda:0" if torch.cuda.is_available() else "cpu"
trial = Trial(model, optimiser, loss_function,
metrics=['loss', 'accuracy']).to(device)
trial.with_generators(train_dl, valid_dl, test_generator=test_dl)
history = trial.run(epochs=1)
results = trial.evaluate(data_key=tb.TEST_DATA)
print(results)
loss_list = []
for item in history:
loss_list.append(item['loss'])
fig1 = plt.figure('1')
ax1 = fig1.gca()
ax1.plot(loss_list)
plt.show()
if key <= epoch:
lr = value
else:
break
print("set lr to : ", lr)
return lr
scheduler = LambdaLR(lr_lambda=[lr_func])
@on_step_training
def clip(serial):
alexnetBin.clip()
trial = Trial(alexnetBin,
optimizer,
criterion=loss,
metrics=['acc', 'loss'],
callbacks=[clip, scheduler]).to('cpu')
trial = trial.with_generators(train_generator=train_set,
val_generator=valid_set,
test_generator=test_set)
trial.run(epochs=150)
trial.evaluate(data_key=TEST_DATA)
alexnetBin.train()
torch.save(alexnetBin.state_dict(),
open("./models/cifar10/alexnetBin.pth", "wb"))
# state_dict.pop('fc1.weight')
# state_dict.pop('fc1.bias')
state_dict.pop('fc2.weight')
state_dict.pop('fc2.bias')
# state_dict['fc3'] = None
model.load_state_dict(state_dict, strict=False)
to_deactivate = ['conv1a', 'conv1b', 'conv1c', 'conv2a', 'conv2b', 'conv2c', 'conv3a', 'conv3b', 'conv3c']
for l in to_deactivate:
deactivate_layer(model, l)
'''
loss_function = nn.CrossEntropyLoss()
optimiser = optim.Adam(model.parameters())
device = "cuda:0" if torch.cuda.is_available() else "cpu"
trial = Trial(model, optimiser, loss_function, metrics=['loss',
'accuracy']).to(device)
trial.with_generators(train_loader, test_generator=validation_loader)
trial.run(epochs=10)
results = trial.evaluate(data_key=torchbearer.TEST_DATA)
print(results)
model_name = 'resnet_model_3b'
weights_path = './weights/{}/'.format(model_name)
if not os.path.exists(weights_path):
os.makedirs(weights_path)
w_filepath = './weights/{}/train_{}.weights'.format(model_name, p)
torch.save(model.state_dict(), w_filepath)
for d_vvs in ventral_depths:
for t in range(n_trials):
model_file = f'./models/{cmode}/model_{n_bn}_{d_vvs}_{t}.pt'
log_file = f'./logs/{cmode}/model_{n_bn}_{d_vvs}_{t}.csv'
pathlib.Path(model_file).parents[0].mkdir(parents=True,
exist_ok=True)
pathlib.Path(log_file).parents[0].mkdir(parents=True,
exist_ok=True)
model = BaselineModel(n_bn, d_vvs, nch)
optimiser = optim.RMSprop(model.parameters(),
alpha=0.9,
lr=0.0001,
weight_decay=1e-6)
loss_function = nn.CrossEntropyLoss()
device = "cuda:0" if torch.cuda.is_available() else "cpu"
trial = Trial(
model,
optimiser,
loss_function,
metrics=['loss', 'accuracy'],
callbacks=[
torchbearer.callbacks.csv_logger.CSVLogger(log_file)
]).to(device)
trial.with_generators(trainloader, val_generator=testloader)
trial.run(epochs=20)
torch.save(model.state_dict(), model_file)
# ######### Data
print('==> Preparing data..')
classes, cifar = 10, datasets.CIFAR10
normalize = transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))
transform_base = [transforms.ToTensor(), normalize]
transform = [transforms.RandomCrop(32, padding=4), transforms.RandomHorizontalFlip()] + transform_base
transform_train = transforms.Compose(transform)
transform_test = transforms.Compose(transform_base)
trainset = cifar(root='./data', train=True, download=True, transform=transform_train)
valset = cifar(root='./data', train=False, download=True, transform=transform_test)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=8)
valloader = torch.utils.data.DataLoader(valset, batch_size=128, shuffle=True, num_workers=8)
######### Model
print('==> Building model..')
net = models.resnet18(False)
optimizer = optim.SGD(net.parameters(), lr=0.1, momentum=0.9, weight_decay=1e-4)
fmix = FMix()
criterion = fmix.loss()
######### Trial
print('==> Starting training..')
trial = Trial(net, optimizer, criterion, metrics=['acc', 'loss'], callbacks=[fmix])
trial.with_generators(train_generator=trainloader, val_generator=valloader).to('cuda')
trial.run(100, verbose=2)
