"""
Created on Sat Jun 29 10:06:03 2019
@author: NguyenHoangThuan
"""
from keras.preprocessing.image import *
from prepare_data import *
from loss_and_metrics import *
from model import VGG
from keras.models import *
from keras.callbacks import *
import config as cf
train_x,train_y,val_x,val_y = create_data()
model = VGG(shape=(64, 256, 1))
model.summary()
model.compile(loss = custom_loss,
optimizer='adam',
metrics=[char_acc,image_acc])
datagen = ImageDataGenerator(width_shift_range=0.14,
height_shift_range=0.08,
fill_mode='constant',
zoom_range = 0.1,
rotation_range = 10,
#rescale =1./255
)
mcp_save = ModelCheckpoint(cf.CKP_PATH, save_best_only=True, monitor='val_loss', mode='min',verbose=1)
if __name__ == "__main__":
# hyper param
init_lr = 0.0001
weight_decay = 0.0005
Epochs = 1000
train_dir = r"C:\Users\13249\Desktop\20200115-20200205\Calcification\Data\INBreast\Sample\train"
valid_dir = r"C:\Users\13249\Desktop\20200115-20200205\Calcification\Data\INBreast\Sample\valid"
# data_loader
train_loader = get_data_loader(train_dir, data_augment=True)
valid_loader = get_data_loader(train_dir, data_augment=False, batch_size=128)
# model
net = VGG(1).cuda()
# define loss function (criterion) and optimizer
loss_func = FocalLoss().cuda()
opt = optim.Adam(net.parameters(), init_lr, weight_decay=weight_decay)
lr_decay = torch.optim.lr_scheduler.StepLR(opt, step_size=5, gamma=0.5)
# train
writer = SummaryWriter()
for epoch in range(0, Epochs + 1):
net.train()
losses = []
for i, (images, target) in enumerate(train_loader):
images = images.cuda()
target = target.cuda()
window_size=args.window_size,
window_stride=args.window_stride,
window_type=args.window_type,
normalize=args.normalize)
test_loader = torch.utils.data.DataLoader(test_dataset,
batch_size=args.test_batch_size,
shuffle=None,
num_workers=20,
pin_memory=args.cuda,
sampler=None)
# build model
if args.arc == 'LeNet':
model = LeNet()
elif args.arc.startswith('VGG'):
model = VGG(args.arc)
else:
model = LeNet()
if args.cuda:
print('Using CUDA with {0} GPUs'.format(torch.cuda.device_count()))
model = torch.nn.DataParallel(model, device_ids=[0]).cuda()
# define optimizer
if args.optimizer.lower() == 'adam':
optimizer = optim.Adam(model.parameters(), lr=args.lr)
elif args.optimizer.lower() == 'sgd':
optimizer = optim.SGD(model.parameters(),
lr=args.lr,
momentum=args.momentum)
else:
