'--model',
type=str,
default='model.pt',
metavar='M',
help="the model file to be evaluated. (default: model.pt)")
parser.add_argument(
'--outfile',
type=str,
default='visualize_stn.png',
metavar='O',
help=
"visualize the STN transformation on some input batch (default: visualize_stn.png)"
)
args = parser.parse_args()
# Load model checkpoint
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
checkpoint = torch.load(args.model, map_location=device)
# Neural Network and Loss Function
model = TrafficSignNet().to(device)
model.load_state_dict(checkpoint)
model.eval()
criterion = nn.CrossEntropyLoss()
# Data Initialization and Loading
test_loader = get_test_loader(args.data, device)
evaluate(model, criterion, test_loader)
visualize_stn(test_loader, args.outfile)
parser.add_argument('--num-workers', type=int, default=0, metavar='W',
help='How many subprocesses to use for data loading (default: 0)')
parser.add_argument('--epochs', type=int, default=100, metavar='N',
help='Number of epochs to train (default: 100)')
parser.add_argument('--patience', type=int, default=10, metavar='P',
help='Number of epochs with no improvement after which training will be stopped (default: 10)')
parser.add_argument('--lr', type=float, default=0.0001, metavar='LR',
help='Learning rate (default: 0.0001)')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='Random seed (default: 1)')
parser.add_argument('--checkpoint', type=str, default='model.pt', metavar='M',
help='checkpoint file name (default: model.pt)')
args = parser.parse_args()
torch.manual_seed(args.seed)
# Data Initialization and Loading
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
preprocess(args.data)
train_loader, valid_loader = get_train_loaders(
args.data, device, args.batch_size, args.num_workers, args.class_count)
# Neural Network and Optimizer
model = TrafficSignNet().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
# Training and Validation
fit(args.epochs, model, criterion, optimizer,
train_loader, valid_loader, args.patience, args.checkpoint)
)
parser.add_argument(
'--model',
type=str,
default='model.pt',
metavar='M',
help="the model file to be evaluated. (default: model.pt)")
args = parser.parse_args()
# Load model checkpoint
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
checkpoint = torch.load(args.model, map_location=device)
# Neural Network and Loss Function
model = TrafficSignNet().to(device)
model.load_state_dict(checkpoint)
model_children = list(model.children())
# load the data that are needed to be visualized
test_loader = get_test_loader(args.data, device)
# As instructed in the Programming assignment, Selecting 10 images from at least 5 different classes
images = []
images_classes = []
dict = {}
for x, y in test_loader:
if (len(images) < 10):
dict[y] = dict[y] + 1 if (y in dict) else 1
if (dict[y] <= 2):