parser.add_argument('-t',
'--test_acc',
type=bool,
help='Only show test accuarcy')
parser.add_argument(
'-c',
'--cam',
type=bool,
help='Test the model in real time with webcam connect via usb')
args = parser.parse_args()
transformation = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, ), (0.5, ))])
dataset = Plain_Dataset(csv_file=args.data + '/finaltest.csv',
img_dir=args.data + '/' + 'finaltest/',
datatype='finaltest',
transform=transformation)
test_loader = DataLoader(dataset, batch_size=64, num_workers=0)
net = Deep_Emotion()
print("Deep Emotion:-", net)
net.load_state_dict(torch.load(args.model))
net.to(device)
net.eval()
#Model Evaluation on test data
classes = ('Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral')
total = []
if args.test_acc:
with torch.no_grad():
for data, labels in test_loader:
data, labels = data.to(device), labels.to(device)
batchsize = 128
if args.train:
net = Deep_Emotion()
net.to(device)
print("Model archticture: ", net)
traincsv_file = args.data + '/' + 'train.csv'
validationcsv_file = args.data + '/' + 'val.csv'
train_img_dir = args.data + '/' + 'train/'
validation_img_dir = args.data + '/' + 'val/'
transformation = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, ), (0.5, ))])
train_dataset = Plain_Dataset(csv_file=traincsv_file,
img_dir=train_img_dir,
datatype='train',
transform=transformation)
validation_dataset = Plain_Dataset(csv_file=validationcsv_file,
img_dir=validation_img_dir,
datatype='val',
transform=transformation)
train_loader = DataLoader(train_dataset,
batch_size=batchsize,
shuffle=True,
num_workers=0)
val_loader = DataLoader(validation_dataset,
batch_size=batchsize,
shuffle=True,
num_workers=0)
criterion = nn.CrossEntropyLoss()
type=bool,
help='if you do not want to use stn, type False')
parser.add_argument('--jaffe',
action='store_true',
help='set if you are using the jaffe dataset')
args = parser.parse_args()
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
transformation = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5), (0.5))])
dataset = Plain_Dataset(csv_file=args.file,
img_dir=args.data,
datatype='finaltest',
transform=transformation)
if args.channel50:
num_channel = 50
else:
num_channel = 10
if args.stn:
stn = args.stn
else:
stn = True
net = Deep_Emotion(num_channel, stn)
net.load_state_dict(torch.load(args.model))
net.to(device)