import argparse
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import transforms

parser = argparse.ArgumentParser(“Set parking lot occupancy detection project parameters”, add_help=False)

parser.add_argument(‘–epochs’, type=int, default=18, help=”rounds of training”)
parser.add_argument(‘–imshow’, type=bool, default=False, help=”show some training dataset”)
parser.add_argument(‘–model’, type=str, default=’mAlexNet’, help=’model name’)
parser.add_argument(‘–path’, type=str, default=”, help=’trained model path’)
parser.add_argument(‘–train_img’, type=str, default=’CNRPark-Patches-150×150/’, help=”path to training set images”)
parser.add_argument(‘–train_lab’, type=str, default=’splits/CNRParkAB/even.txt’, help=”path to training set labels”)
parser.add_argument(‘–test_img’, type=str, default=’CNRPark-Patches-150×150/’, help=”path to test set images”)
parser.add_argument(‘–test_lab’, type=str, default=’splits/CNRParkAB/odd.txt’, help=”path to test set labels”)

parser.add_argument(“–device”, default=”cuda”, help=”device used”)
args = parser.parse_args()

def train(epoch, img_path, target_path, transform, net, criterion, device):
train_dataset = Data(img_path, target_path, transform)
train_loader = DataLoader(train_dataset, batch_size=64, \
shuffle=True, num_workers=0,drop_last=False, collate_fn=collate_fn)
for ep in range(epoch):
if ep >= 12:
learning_rate = 0.0025
elif ep >= 6:
learning_rate = 0.005
else:
learning_rate = 0.01
running_loss = 0.0
print(“Epoch {}.”.format(ep+1))
for i, data in enumerate(train_loader,1):
inputs, labels = data
labels = list(map(int, labels))
labels = torch.Tensor(labels)
inputs = inputs.to(device)
labels = labels.to(device)

optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9, weight_decay=0.0005)
optimizer.zero_grad()
outputs = net(inputs)

loss = criterion(outputs, labels.long())
loss.backward()
optimizer.step()
running_loss += loss.item()
print(“Epoch {}.\tBatch {}.\tLoss = {:.3f}.”.format(ep+1, i+1, running_loss))
if i % 2000 == 1999: # 2000 mini-batches
print(‘[%d, %5d] loss: %.3f’ %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0
print(‘Finished Training.’)