from model import FineTunedModel
from torchvision.models import resnet18
from model import ContrastiveModel, get_backbone
from dataset_loader import get_clf_train_test_transform
from dataset_loader import get_clf_train_test_dataloaders
if torch.cuda.is_available():
dtype = torch.cuda.FloatTensor
device = torch.device("cuda")
# torch.cuda.set_device(device_id)
print('GPU')
else:
dtype = torch.FloatTensor
device = torch.device("cpu")
backbone = get_backbone(resnet18(pretrained=False))
model = ContrastiveModel(backbone).to(device)
obj = torch.load(
"/home/octo/Desktop/clr/ckpt/0417151425/SimCLR_0417175433.pth")
model.load_state_dict(obj['state_dict'])
encoder = model.backbone
last_layers = torch.nn.Sequential(
*(list(model.projectionhead.children())[0:2]))
encoder = nn.Sequential(encoder, last_layers)
new_model = FineTunedModel(encoder, model.output_dim).to(device)
criterion = nn.CrossEntropyLoss()
from model import RetinaNet, get_backbone
from loss import RetinaNetLoss
from dataloader import FaceMask
from box import LabelEncoder
num_classes = 2
classes_name = ['face', 'mask']
batch_size = 2
label_encoder = LabelEncoder()
learning_rates = [2.5e-06, 0.000625, 0.00125, 0.0025, 0.00025, 2.5e-05]
learning_rate_boundaries = [125, 250, 500, 240000, 360000]
learning_rate_fn = tf.optimizers.schedules.PiecewiseConstantDecay(
boundaries=learning_rate_boundaries, values=learning_rates)
resnet50_backbone = get_backbone()
loss_fn = RetinaNetLoss(num_classes)
model = RetinaNet(num_classes, resnet50_backbone)
optimizer = tf.optimizers.SGD(learning_rate=learning_rate_fn, momentum=0.9)
model.compile(loss=loss_fn, optimizer=optimizer)
train_img_paths = sorted(glob('./facedataset/images/train/*.jpg'))
train_labels_paths = sorted(glob('./facedataset/labels/train/*.txt'))
val_img_paths = sorted(glob('./facedataset/images/val/*.jpg'))
val_labels_paths = sorted(glob('./facedataset/labels/val/*.txt'))
train_gen = FaceMask(train_img_paths, train_labels_paths)
train_dataset = tf.data.Dataset.from_generator(
lambda: train_gen,
output_types=(tf.float32, tf.float32, tf.int32),