Please help me out! Thanks for your time.
# Initialize and load Dataset
face_data = FaceAnnoDataset(root_dir=path, img_dir ='image', anno_dir='label', txtfile='image.txt', transform=transforms.Compose([
Rescale((224,224)),
ToTensor()])
)
model = DetectionNet()
train_loader = DataLoader(face_data, batch_size=50, shuffle=False, pin_memory=True,
num_workers=10, collate_fn=collate_fn)
optimizer = optim.SGD(model.parameters(), lr=0.001)
step_lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=25, gamma=0.95)
train(model=model, train_loader=train_loader, criterion=loss_fn, optimizer=optimizer, scheduler=step_lr_scheduler,
num_epochs=60)
---Epochs: 1/60---loss:1381.1974 time per epoch: 71.1s
---Epochs: 2/60---loss:748.1144 time per epoch: 70.4s
---Epochs: 3/60---loss:714.3693 time per epoch: 70.6s
---Epochs: 4/60---loss:415.6876 time per epoch: 70.8s
---Epochs: 5/60---loss:296.9739 time per epoch: 71.2s
---Epochs: 6/60---loss:247.1272 time per epoch: 70.8s
---Epochs: 7/60---loss:239.9819 time per epoch: 71.3s
---Epochs: 8/60---loss:253.4962 time per epoch: 72.2s
---Epochs: 9/60---loss:253.9536 time per epoch: 71.4s
---Epochs: 10/60---loss:266.9828 time per epoch: 71.1s
---Epochs: 11/60---loss:231.9026 time per epoch: 72.1s
---Epochs: 12/60---loss:234.4481 time per epoch: 71.1s
---Epochs: 13/60---loss:242.5606 time per epoch: 71.3s
---Epochs: 14/60---loss:220.9487 time per epoch: 71.4s
---Epochs: 15/60---loss:228.3398 time per epoch: 71.7s
---Epochs: 16/60---loss:216.9143 time per epoch: 72.1s
---Epochs: 17/60---loss:224.2294 time per epoch: 72.0s
---Epochs: 18/60---loss:223.6916 time per epoch: 71.8s
---Epochs: 19/60---loss:225.8125 time per epoch: 71.8s
---Epochs: 20/60---loss:221.8919 time per epoch: 72.3s
---Epochs: 21/60---loss:228.5138 time per epoch: 71.9s
---Epochs: 22/60---loss:228.7554 time per epoch: 72.4s
---Epochs: 23/60---loss:213.6178 time per epoch: 72.5s
---Epochs: 24/60---loss:215.1711 time per epoch: 72.4s
---Epochs: 25/60---loss:218.0184 time per epoch: 72.5s
---Epochs: 26/60---loss:215.1418 time per epoch: 71.9s
---Epochs: 27/60---loss:218.2050 time per epoch: 72.4s
---Epochs: 28/60---loss:215.3260 time per epoch: 72.2s
---Epochs: 29/60---loss:211.5364 time per epoch: 72.1s
---Epochs: 30/60---loss:215.0333 time per epoch: 73.2s
---Epochs: 31/60---loss:213.9194 time per epoch: 73.2s
---Epochs: 32/60---loss:217.5076 time per epoch: 72.4s
---Epochs: 33/60---loss:213.3889 time per epoch: 72.5s
---Epochs: 34/60---loss:216.6434 time per epoch: 72.3s
---Epochs: 35/60---loss:212.9640 time per epoch: 71.8s
---Epochs: 36/60---loss:212.9351 time per epoch: 72.6s
---Epochs: 37/60---loss:215.7963 time per epoch: 71.6s
---Epochs: 38/60---loss:209.7389 time per epoch: 72.1s
---Epochs: 39/60---loss:212.4336 time per epoch: 71.9s
---Epochs: 40/60---loss:209.1561 time per epoch: 73.0s
---Epochs: 41/60---loss:209.4057 time per epoch: 73.2s
---Epochs: 42/60---loss:209.8560 time per epoch: 73.2s
---Epochs: 43/60---loss:209.1799 time per epoch: 72.7s
---Epochs: 44/60---loss:208.5630 time per epoch: 72.6s
---Epochs: 45/60---loss:207.7853 time per epoch: 73.0s
---Epochs: 46/60---loss:212.6032 time per epoch: 73.3s
---Epochs: 47/60---loss:209.7255 time per epoch: 72.1s
---Epochs: 48/60---loss:208.5065 time per epoch: 72.9s
---Epochs: 49/60---loss:213.0023 time per epoch: 72.2s
---Epochs: 50/60---loss:212.4016 time per epoch: 71.9s
---Epochs: 51/60---loss:211.8147 time per epoch: 72.6s
---Epochs: 52/60---loss:208.5325 time per epoch: 71.9s
---Epochs: 53/60---loss:214.9977 time per epoch: 72.1s
---Epochs: 54/60---loss:211.7724 time per epoch: 71.9s
---Epochs: 55/60---loss:214.1940 time per epoch: 72.1s
---Epochs: 56/60---loss:210.2245 time per epoch: 72.3s
---Epochs: 57/60---loss:214.8525 time per epoch: 74.2s
---Epochs: 58/60---loss:212.2930 time per epoch: 72.2s
---Epochs: 59/60---loss:209.7719 time per epoch: 72.3s
---Epochs: 60/60---loss:212.6878 time per epoch: 72.3s