# lr = 0.005
# 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/'
epochs = 100
lr = 0.005 # Learning rate
batchsize = 128
net = Deep_Emotion() ## CREATING THE MODEL BY CALLING DEEPMOTION.PY
net.to(device) ## MOVING IT TO GPU / CPU
print("Model archticture: ", net)
traincsv_file = 'data' + '/' + 'train.csv'
validationcsv_file = 'data' + '/' + 'val.csv'
train_img_dir = 'data' + '/' + 'train/'
validation_img_dir = '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,
generate_dataset.split_test()
generate_dataset.save_images()
generate_dataset.save_images('finaltest')
generate_dataset.save_images('val')
if args.hyperparams:
epochs = args.epochs
lr = args.learning_rate
batchsize = args.batch_size
else:
epochs = 100
lr = 0.005
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,
from deep_emotion import Deep_Emotion
from generate_data import Generate_data
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
mapping = {
0: 'Angry',
1: 'Disgust',
2: 'Fear',
3: 'Happy',
4: 'Sad',
5: 'Surprise',
6: 'Neutral'
}
net = Deep_Emotion() # In pytorch we have to first load the model
file_name = 'deep_emotion-100-128-0.005.pt'
net.load_state_dict(torch.load(file_name))
net.to(device)
path = "haarcascade_frontalface_default.xml"
font_scale = 1.5
font = cv2.FONT_HERSHEY_PLAIN
# SET THE RECTANGLE BACKGROUND TO WHITE
rectangle_bgr = (255, 255, 255)
# MAKE A BLACK IMAGE
img = np.zeros((500, 500))
# SET SOME TEXT
'-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)
outputs = net(data)
pred = F.softmax(outputs, dim=1)
classs = torch.argmax(pred, 1)
wrong = torch.where(classs != labels,
torch.save(net.state_dict(),'deep_emotion-{}-{}-{}.pt'.format(epochs,batchsize,lr))
print("===================================Training Finished===================================")
generate_dataset = Generate_data("data//")
generate_dataset.split_test()
generate_dataset.save_images()
generate_dataset.save_images('finaltest')
generate_dataset.save_images('val')
epochs = 100
lr = 0.005
batchsize = 128
net = Deep_Emotion()
net.to(device)
print("Model archticture: ", net)
traincsv_file = 'data'+'/'+'train.csv' #remove
validationcsv_file = 'data'+'/'+'val.csv'
train_img_dir = 'data'+'/'+'train/'
validation_img_dir = '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()
optmizer= optim.Adam(net.parameters(),lr= lr)
generate_dataset.split_test()
generate_dataset.save_images()
generate_dataset.save_images('finaltest')
generate_dataset.save_images('val')
if args.hyperparams:
epochs = args.epochs
lr = args.learning_rate
batchsize = args.batch_size
else:
epochs = 100
lr = 0.0001
batchsize = 16
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/'
transformation2 = tfs.Compose(
[tfs.ToTensor(), tfs.Normalize((0.5, ), (0.5, ))])
train_dataset = Plain_Dataset(csv_file=traincsv_file,
img_dir=train_img_dir,
datatype='train',
transform=train_tf)
validation_dataset = Plain_Dataset(csv_file=validationcsv_file,
img_dir=validation_img_dir,
epochs = 100
lr = 0.005
batchsize = 128
if args.channel50:
num_channel = 50
else:
num_channel = 10
if args.stn:
stn = args.stn
else:
stn = True
if args.train:
net = Deep_Emotion(num_channel, stn)
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/'
if args.regularizer:
regularizer = args.regularizer
else:
regularizer = False
transformation = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, ), (0.5, ))])