def end_to_end():
s=1
input_shape = (128,128,3)
# set up training data
train_trans = TrainDataAugmentation(s, input_shape)
train_aug = train_trans.augment()
train_data = datasets.ImageFolder('unlabelled', transform=SimCLRDataTransform(train_aug))
# set up tuning data
tune_trans = TuneDataAugmentation(s, input_shape)
tune_aug = tune_trans.augment()
tune_data = datasets.ImageFolder('labelled', transform=TuneDataTransform(tune_aug))
# # set up val data
# val_data = tv.datasets.CIFAR10(
# root='Data', train=False, download=True,
# transform=TuneDataTransform(tune_aug)
# )
val_data = None
# create the base model
model = ResNetSimCLR(in_channels=3, n_classes=10, mlp_layers=2)
simclr = SimCLR(model)
print(f'Our model has {simclr.trainer.num_params:,} parameters')
results = simclr.full_model_maker(
train_data, tune_data, val_data, n_cycles=1, train_epochs=5, tune_epochs=2,
train_path='chkpt/train.tar', tune_path='chkpt/tune.tar'
)
return results
def validateCIFAR(modelpath):
s = 1
input_shape = (128,128,3)
# get transform pipeline
transform = TuneDataAugmentation(s, input_shape)
augment = transform.augment()
# load data
testdata = tv.datasets.CIFAR10(root='TestData',
train=False,download=False,transform=SimCLRDataTransform(augment))
simclr = Validate()
testloader = simclr.load_data(testdata)
accuracy = simclr.validate_labels(modelpath,testloader)
return accuracy
def trainCIFAR():
s = 1
input_shape = (128,128,3)
temperature = .5
# get transform pipeline
transform = TrainDataAugmentation(s, input_shape)
augment = transform.augment()
# load data
trainset = datasets.ImageFolder('unlabelled', transform=SimCLRDataTransform(augment))
simclr = Train()
data = simclr.load_data(trainset)
model,losses = simclr.train(data, temperature,n_epochs=1,ckpt_path='face_recognition.tar')
return model, losses
def finish_the_job():
s = 1
input_shape = (128, 128, 3)
# set up training data
train_trans = TrainDataAugmentation(s, input_shape)
train_aug = train_trans.augment()
train_data = tv.datasets.ImageFolder(
root='Data/unlabeled', transform=SimCLRDataTransform(train_aug))
# set up tuning and validation data
tune_trans = TuneDataAugmentation(s, input_shape)
tune_aug = tune_trans.augment()
tune_val_data = tv.datasets.ImageFolder(
root='Data/supervised', transform=TuneDataTransform(tune_aug))
tune_data, val_data = random_split(tune_val_data, [7112, 16595])
saved = torch.load('chkpt/race_train.tar70')
trained_model = model = ResNetSimCLR(in_channels=3,
n_classes=5,
mlp_layers=2,
blocks_layers=[3, 4, 6, 3])
trained_model.load_state_dict(saved['model_state_dict'])
simclr = SimCLR(trained_model)
model = simclr.trainer.return_model()
simclr.make_tuner(model)
tune_epochs = 50
tune_path = 'chkpt/race_tune.tar'
model, tune_losses = simclr.tune(tune_data, tune_epochs, tune_path)
simclr.make_validator(simclr.tuner.model)
acc, actual, predicted = simclr.validate(val_data)
results = (model, tune_losses, acc, actual, predicted)
return results
def trainCIFAR():
s = 1
input_shape = (96,96,3)
temperature = .5
# get transform pipeline
transform = TrainDataAugmentation(s, input_shape)
augment = transform.augment()
# load data
trainset = tv.datasets.CIFAR10(
root='Data', train=True, download=False,
transform=SimCLRDataTransform(augment)
)
simclr = Train()
data = simclr.load_data(trainset)
model,losses = simclr.train(data, temperature,n_epochs=1,ckpt_path='CIFAR10.tar')
return model, losses
def train_race_fr():
s = 1
input_shape = (128, 128, 3)
# set up training data
train_trans = TrainDataAugmentation(s, input_shape)
train_aug = train_trans.augment()
train_data = tv.datasets.ImageFolder(
root='Data/unlabeled', transform=SimCLRDataTransform(train_aug))
# set up tuning and validation data
tune_trans = TuneDataAugmentation(s, input_shape)
tune_aug = tune_trans.augment()
tune_val_data = tv.datasets.ImageFolder(
root='Data/supervised', transform=TuneDataTransform(tune_aug))
tune_data, val_data = random_split(tune_val_data, [7112, 16595])
# create the base model
model = ResNetSimCLR(in_channels=3,
n_classes=5,
mlp_layers=2,
blocks_layers=[3, 4, 6, 3])
simclr = SimCLR(model)
print(f'Our model has {simclr.trainer.num_params:,} parameters')
results = simclr.full_model_maker(train_data,
tune_data,
val_data,
n_cycles=1,
train_epochs=71,
tune_epochs=31,
train_path='chkpt/race_train.tar',
tune_path='chkpt/race_tune.tar')
return results