def load_data(task : str):
# Define the Augmentation here only
augments = Compose([
# Convert the image to Tensor
transforms.Lambda(lambda x: torch.Tensor(x)),
# Randomly rotate the image with an angle
# between -25 degrees to 25 degrees
RandomRotate(25),
# Randomly translate the image by 11% of
# image height and width
RandomTranslate([0.11, 0.11]),
# Randomly flip the image
RandomFlip(),
# Change the order of image channels
transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
print('Loading Train Dataset of {} task...'.format(task))
# Load training dataset
train_data = MRData(task, train=True, transform=augments)
train_loader = data.DataLoader(
train_data, batch_size=1, num_workers=11, shuffle=True
)
print('Loading Validation Dataset of {} task...'.format(task))
# Load validation dataset
val_data = MRData(task, train=False)
val_loader = data.DataLoader(
val_data, batch_size=1, num_workers=11, shuffle=False
)
return train_loader, val_loader, train_data.weights, val_data.weights
def transform(x,y,crop_range,rot_range,shear_range,zoom_range,t):
if t == False: # If t is set to false the input is only cropped
crop_type = np.random.randint(0,5,1)[0] # Randomly crop image from either center or a corner.
x_new = SpecialCrop((crop_range),crop_type=crop_type)(x)
y_new = SpecialCrop((crop_range),crop_type=crop_type)(y)
else:
rot = RandomRotate(rot_range,lazy=True)(x)
shear = RandomShear(shear_range,lazy=True)(x)
zoom = RandomZoom(zoom_range,lazy=True)(x)
flip = RandomFlip(v=True,p = np.random.randint(0,2,1)[0])# Images and label is flipped with 0.5 prob.
crop_type = np.random.randint(0,5,1)[0]
x_new = SpecialCrop((crop_range),crop_type=crop_type)(x)
y_new = SpecialCrop((crop_range),crop_type=crop_type)(y)
x_new = th_affine2d(x_new,rot)
y_new = th_affine2d(y_new,rot)
x_new = th_affine2d(x_new,shear)
y_new = th_affine2d(y_new,shear)
x_new = th_affine2d(x_new,zoom)
y_new = th_affine2d(y_new,zoom)
x_new = flip(x_new)
y_new = flip(y_new)
return AddChannel()(x_new), AddChannel()(y_new) # Add channel for concatenating batch.
def load_data(task: str):
# Define the Augmentation here only
augments = Compose([
transforms.Lambda(lambda x: torch.Tensor(x)),
RandomRotate(25),
RandomTranslate([0.11, 0.11]),
RandomFlip(),
transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
print('Loading Train Dataset of {} task...'.format(task))
train_data = MRData(task, train=True, transform=augments)
train_loader = data.DataLoader(train_data,
batch_size=1,
num_workers=4,
shuffle=True)
print('Loading Validation Dataset of {} task...'.format(task))
val_data = MRData(task, train=False)
val_loader = data.DataLoader(val_data,
batch_size=1,
num_workers=4,
shuffle=False)
return train_loader, val_loader, train_data.weights, val_data.weights
def run(args):
augmentor = Compose([
transforms.Lambda(lambda x: torch.Tensor(x)),
RandomRotate(25),
RandomTranslate([0.11, 0.11]),
RandomFlip(),
transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
train_dataset = MRDataset('./data/', args.task, args.plane, transform=augmentor, train=True)
array, label, weight = train_dataset[0]
print(array.shape, label)
train_loader = torch.utils.data.DataLoader( train_dataset, batch_size=1, shuffle=True, num_workers=11, drop_last=False)
validation_dataset = MRDataset('./data/', args.task, args.plane, train=False)
validation_loader = torch.utils.data.DataLoader( validation_dataset, batch_size=1, shuffle=-True, num_workers=11, drop_last=False)
def load_data(diagnosis, use_gpu=False):
train_dirs = [
'/home/niamh/Documents/MRNET/External_data/data/vol08',
'/home/niamh/Documents/MRNET/External_data/data/vol04',
'/home/niamh/Documents/MRNET/External_data/data/vol03',
'/home/niamh/Documents/MRNET/External_data/data/vol09',
'/home/niamh/Documents/MRNET/External_data/data/vol06',
'/home/niamh/Documents/MRNET/External_data/data/vol07'
]
valid_dirs = [
'/home/niamh/Documents/MRNET/External_data/data/vol10',
'/home/niamh/Documents/MRNET/External_data/data/vol05'
]
test_dirs = [
'/home/niamh/Documents/MRNET/External_data/data/vol01',
'/home/niamh/Documents/MRNET/External_data/data/vol02'
]
augmentor = Compose([
transforms.Lambda(lambda x: torch.Tensor(x)),
RandomRotate(25),
RandomTranslate([0.11, 0.11]),
RandomFlip(),
# transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
train_dataset = Dataset(train_dirs, diagnosis, augmentor, use_gpu)
valid_dataset = Dataset(valid_dirs, diagnosis, None, use_gpu)
test_dataset = Dataset(test_dirs, diagnosis, None, use_gpu)
train_loader = data.DataLoader(train_dataset,
batch_size=1,
num_workers=8,
shuffle=True)
valid_loader = data.DataLoader(valid_dataset,
batch_size=1,
num_workers=8,
shuffle=False)
test_loader = data.DataLoader(test_dataset,
batch_size=1,
num_workers=8,
shuffle=False)
return train_loader, valid_loader, test_loader
def run(args):
indexes = list(range(0, 1130))
random.seed(26)
random.shuffle(indexes)
for fold in range(0, 8):
if fold == 0:
train_ind = indexes[0:141] + indexes[282:]
valid_ind = indexes[141:282]
elif fold == 1:
train_ind = indexes[0:282] + indexes[423:]
valid_ind = indexes[282:423]
elif fold == 2:
train_ind = indexes[0:564] + indexes[705:]
valid_ind = indexes[564:705]
elif fold == 3:
train_ind = indexes[:705] + indexes[846:]
valid_ind = indexes[705:846]
elif fold == 4:
train_ind = indexes[:846] + indexes[987:]
valid_ind = indexes[846:987]
elif fold == 5:
train_ind = indexes[:987]
valid_ind = indexes[987:]
elif fold == 6:
train_ind = indexes[141:]
valid_ind = indexes[0:141]
elif fold == 7:
train_ind = indexes[0:423] + indexes[568:]
valid_ind = indexes[423:568]
log_root_folder = "./logs/{0}/{1}/".format(args.task, args.plane)
if args.flush_history == 1:
objects = os.listdir(log_root_folder)
for f in objects:
if os.path.isdir(log_root_folder + f):
shutil.rmtree(log_root_folder + f)
now = datetime.now()
logdir = log_root_folder + now.strftime("%Y%m%d-%H%M%S") + "/"
os.makedirs(logdir)
writer = SummaryWriter(logdir)
augmentor = Compose([
transforms.Lambda(lambda x: torch.Tensor(x)),
RandomRotate(25),
RandomTranslate([0.11, 0.11]),
RandomFlip(),
# transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
mrnet = model.MRNet()
if torch.cuda.is_available():
mrnet = mrnet.cuda()
optimizer = optim.Adam(mrnet.parameters(),
lr=args.lr,
weight_decay=0.1)
if args.lr_scheduler == "plateau":
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
optimizer, patience=2, factor=.3, threshold=1e-4, verbose=True)
elif args.lr_scheduler == "step":
scheduler = torch.optim.lr_scheduler.StepLR(optimizer,
step_size=3,
gamma=args.gamma)
best_val_loss = float('inf')
best_val_auc = float(0)
num_epochs = args.epochs
iteration_change_loss = 0
patience = args.patience
log_every = args.log_every
t_start_training = time.time()
train_dataset = MRDataset(train_ind,
'/content/data/',
args.task,
args.plane,
valid=False,
transform=augmentor)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=1,
shuffle=True,
num_workers=11,
drop_last=False)
validation_dataset = MRDataset(valid_ind,
'/content/data/',
args.task,
args.plane,
valid=False,
transform=None)
validation_loader = torch.utils.data.DataLoader(validation_dataset,
batch_size=1,
shuffle=- True,
num_workers=11,
drop_last=False)
valid_dataset = MRDataset([0],
'/content/data/',
args.task,
args.plane,
valid=True,
transform=None)
valid_loader = torch.utils.data.DataLoader(valid_dataset,
batch_size=1,
shuffle=- True,
num_workers=11,
drop_last=False)
for epoch in range(num_epochs):
current_lr = get_lr(optimizer)
t_start = time.time()
train_loss, train_auc = train_model(mrnet, train_loader, epoch,
num_epochs, optimizer, writer,
current_lr, log_every)
val_loss, val_auc, test_auc = evaluate_model(
mrnet, validation_loader, valid_loader, epoch, num_epochs,
writer, current_lr)
if args.lr_scheduler == 'plateau':
scheduler.step(val_loss)
elif args.lr_scheduler == 'step':
scheduler.step()
t_end = time.time()
delta = t_end - t_start
print(
"fold : {0} | train loss : {1} | train auc {2} | val loss {3} | val auc {4} | elapsed time {5} s"
.format(fold, train_loss, train_auc, val_loss, val_auc, delta))
iteration_change_loss += 1
print('-' * 30)
if val_auc > best_val_auc:
best_val_auc = val_auc
if bool(args.save_model):
file_name = f'model_fold{fold}_{args.prefix_name}_{args.task}_{args.plane}_test_auc_{test_auc:0.4f}_val_auc_{val_auc:0.4f}_train_auc_{train_auc:0.4f}_epoch_{epoch+1}.pth'
for f in os.listdir('./models/'):
if (args.task in f) and (args.prefix_name
in f) and ('fold' + str(fold)
in f):
os.remove(f'./models/{f}')
torch.save(mrnet, f'./models/{file_name}')
if val_loss < best_val_loss:
best_val_loss = val_loss
iteration_change_loss = 0
if iteration_change_loss == patience:
print(
'Early stopping after {0} iterations without the decrease of the val loss'
.format(iteration_change_loss))
break
t_end_training = time.time()
print(f'training took {t_end_training - t_start_training} s')
from torchsample.transforms import RandomRotate, RandomTranslate, RandomFlip, ToTensor, Compose, RandomAffine
from torchvision import transforms
import torch.nn.functional as F
from data_preprocessor import MRDataset
import model
from sklearn import metrics
augmentor = Compose([
transforms.Lambda(lambda x: torch.Tensor(x)),
RandomRotate(25),
RandomTranslate([0.11, 0.11]),
RandomFlip(),
transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
#Load Dataset
train_dataset = MRDataset('./data/', True,
'axial', transform=augmentor, train=True)
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=1, shuffle=True, num_workers=11, drop_last=False)
validation_dataset = MRDataset(
'./data/', False, 'axial', train=False)
validation_loader = torch.utils.data.DataLoader(
validation_dataset, batch_size=1, shuffle=-True, num_workers=11, drop_last=False)
mrnet = model.MRNet()
def RandomFlip_setup():
tforms = {}
tforms['randomflip_h_01'] = RandomFlip(h=True, v=False)
tforms['randomflip_h_02'] = RandomFlip(h=True, v=False, p=0)
tforms['randomflip_h_03'] = RandomFlip(h=True, v=False, p=1)
tforms['randomflip_h_04'] = RandomFlip(h=True, v=False, p=0.3)
tforms['randomflip_v_01'] = RandomFlip(h=False, v=True)
tforms['randomflip_v_02'] = RandomFlip(h=False, v=True, p=0)
tforms['randomflip_v_03'] = RandomFlip(h=False, v=True, p=1)
tforms['randomflip_v_04'] = RandomFlip(h=False, v=True, p=0.3)
tforms['randomflip_hv_01'] = RandomFlip(h=True, v=True)
tforms['randomflip_hv_02'] = RandomFlip(h=True, v=True, p=0)
tforms['randomflip_hv_03'] = RandomFlip(h=True, v=True, p=1)
tforms['randomflip_hv_04'] = RandomFlip(h=True, v=True, p=0.3)
return tforms
def main():
## For loading complete tensor data into memory
# image_data_file = 'C:/dev/data/Endoviz2018/GIANA/polyp_detection_segmentation/image_data_all_640x640.npy'
# label_data_file = 'C:/dev/data/Endoviz2018/GIANA/polyp_detection_segmentation/gt_data_all_640x640.npy'
## For using csv file to read image locations and use them to load images at run time
image_gt_file_list_all = 'C:/dev/data/Endoviz2018/GIANA/polyp_detection_segmentation/image_gt_data_file_list_all_640x640.csv'
## Transforms to apply
image_transform = transforms.Compose([
ResizePad(640, 'RGB'),
TypeCast('float'),
# RangeNormalize(0, 1),
# StdNormalize(),
RandomGamma(0.2, 1.0),
Brightness(0.1),
RandomSaturation(0.1, 0.2)
])
label_transform = transforms.Compose(
[ResizePad(640, 'L'), TypeCast('float')])
joint_transform = Compose([
RandomFlip(h=True, v=True)
#AffineCompose([Rotate(10), Translate((0.2, 0.2))]),
#SpecialCrop((400, 400))
])
image_gt_file_list_all_df = pd.read_csv(image_gt_file_list_all,
header=None)
## Create Dataset object to read from CSV file
giana_dataset = CSVDataset(image_gt_file_list_all_df,
input_transform=image_transform,
target_transform=label_transform,
co_transform=joint_transform)
## When loading all the data into memory
# image_data = np.load(image_data_file)
# label_data = np.load(label_data_file)
# label_data = np.expand_dims(label_data, axis=3)
# giana_dataset = TensorDataset(image_data, label_data, input_transform=image_transform,
# target_transform=label_transform, co_transform=joint_transform)
## Create pytorch dataloader
giana_dataloader = DataLoader(giana_dataset, batch_size=4, shuffle=True)
idx = 0
for images, labels in giana_dataloader:
print(images.size(), labels.size())
fig = plt.figure(figsize=(10, 5))
timer = fig.canvas.new_timer(interval=2000)
timer.add_callback(close_event)
# idx = 0
# for image, label in zip(images, labels):
# # plt.imshow(np.rollaxis(image.numpy(), 0, 3))
plot_image_label(np.rollaxis(images.numpy(), 1, 4),
np.rollaxis(labels.numpy(), 1, 4))
timer.start()
plt.show()
idx += 1
if idx == 4:
break
def run(args):
log_root_folder = "./logs/{0}/{1}/".format(args.task, args.plane)
if args.flush_history == 1:
objects = os.listdir(log_root_folder)
for f in objects:
if os.path.isdir(log_root_folder + f):
shutil.rmtree(log_root_folder + f)
now = datetime.now()
logdir = log_root_folder + now.strftime("%Y%m%d-%H%M%S") + "/"
os.makedirs(logdir)
writer = SummaryWriter(logdir)
augmentor = Compose([
transforms.Lambda(lambda x: torch.Tensor(x)),
RandomRotate(25),
RandomTranslate([0.11, 0.11]),
RandomFlip(),
transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
train_dataset = MRDataset('/home/niamh/Documents/MRNET/data/', args.task,
args.plane, transform=augmentor, train=True)
train_loader = torch.utils.data.DataLoader(
train_dataset, batch_size=1, shuffle=True, num_workers=11, drop_last=False)
validation_dataset = MRDataset(
'/home/niamh/Documents/MRNET/data/', args.task, args.plane, train=False)
validation_loader = torch.utils.data.DataLoader(
validation_dataset, batch_size=1, shuffle=-True, num_workers=11, drop_last=False)
mrnet = model.UNet(n_channels=3, n_classes=1, bilinear=True)
if torch.cuda.is_available():
mrnet = mrnet.cuda()
optimizer = optim.Adam(mrnet.parameters(), lr=args.lr, weight_decay=0.1)
if args.lr_scheduler == "plateau":
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
optimizer, patience=3, factor=.3, threshold=1e-4, verbose=True)
elif args.lr_scheduler == "step":
scheduler = torch.optim.lr_scheduler.StepLR(
optimizer, step_size=3, gamma=args.gamma)
best_val_loss = float('inf')
best_val_auc = float(0)
num_epochs = args.epochs
iteration_change_loss = 0
patience = args.patience
log_every = args.log_every
t_start_training = time.time()
for epoch in range(num_epochs):
current_lr = get_lr(optimizer)
t_start = time.time()
train_loss, train_auc = train_model(
mrnet, train_loader, epoch, num_epochs, optimizer, writer, current_lr, log_every)
val_loss, val_auc = evaluate_model(
mrnet, validation_loader, epoch, num_epochs, writer, current_lr)
if args.lr_scheduler == 'plateau':
scheduler.step(val_loss)
elif args.lr_scheduler == 'step':
scheduler.step()
t_end = time.time()
delta = t_end - t_start
print("train loss : {0} | train auc {1} | val loss {2} | val auc {3} | elapsed time {4} s".format(
train_loss, train_auc, val_loss, val_auc, delta))
iteration_change_loss += 1
print('-' * 30)
if val_auc > best_val_auc:
best_val_auc = val_auc
if bool(args.save_model):
file_name = f'model_{args.prefix_name}_{args.task}_{args.plane}_val_auc_{val_auc:0.4f}_train_auc_{train_auc:0.4f}_epoch_{epoch+1}.pth'
for f in os.listdir('./models/'):
if (args.task in f) and (args.plane in f) and (args.prefix_name in f):
os.remove(f'./models/{f}')
torch.save(mrnet, f'./models/{file_name}')
if val_loss < best_val_loss:
best_val_loss = val_loss
iteration_change_loss = 0
if iteration_change_loss == patience:
print('Early stopping after {0} iterations without the decrease of the val loss'.
format(iteration_change_loss))
break
t_end_training = time.time()
print(f'training took {t_end_training - t_start_training} s')
def run(args):
log_root_folder = "./logs/{0}/{1}/".format(args.task, args.plane)
if args.flush_history == 1:
objects = os.listdir(log_root_folder)
for f in objects:
if os.path.isdir(log_root_folder + f):
shutil.rmtree(log_root_folder + f)
now = datetime.now()
logdir = log_root_folder + now.strftime("%Y%m%d-%H%M%S") + "/"
os.makedirs(logdir)
writer = SummaryWriter(logdir)
augmentor = Compose([
transforms.Lambda(lambda x: torch.Tensor(x)),
RandomRotate(25),
RandomTranslate([0.11, 0.11]),
RandomFlip(),
transforms.Lambda(lambda x: x.repeat(3, 1, 1, 1).permute(1, 0, 2, 3)),
])
train_dataset = MRDataset('./data/',
args.task,
args.plane,
transform=augmentor,
train=True)
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=1,
shuffle=True,
num_workers=11,
drop_last=False)
validation_dataset = MRDataset('./data/',
args.task,
args.plane,
train=False)
validation_loader = torch.utils.data.DataLoader(validation_dataset,
batch_size=1,
shuffle=- True,
num_workers=11,
drop_last=False)
mrnet = model.MRNet()
mrnet = mrnet.cuda()
optimizer = optim.Adam(mrnet.parameters(), lr=1e-5, weight_decay=0.1)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(optimizer,
patience=3,
factor=.3,
threshold=1e-4,
verbose=True)
best_val_loss = float('inf')
best_val_auc = float(0)
num_epochs = args.epochs
iteration_change_loss = 0
patience = args.patience
for epoch in range(num_epochs):
train_loss, train_auc = train_model(mrnet, train_loader, epoch,
num_epochs, optimizer, writer)
val_loss, val_auc = evaluate_model(mrnet, validation_loader, epoch,
num_epochs, writer)
print("train loss : {0} | train auc {1} | val loss {2} | val auc {3}".
format(train_loss, train_auc, val_loss, val_auc))
if args.lr_scheduler == 1:
scheduler.step(val_loss)
iteration_change_loss += 1
print('-' * 30)
if val_auc > best_val_auc:
best_val_auc = val_auc
if bool(args.save_model):
file_name = f'model_{args.task}_{args.plane}_val_auc_{val_auc:0.4f}_train_auc_{train_auc:0.4f}_epoch_{epoch+1}.pth'
for f in os.listdir('./models/'):
if (args.task in f) and (args.plane in f):
os.remove(f'./models/{f}')
torch.save(mrnet, f'./models/{file_name}')
if val_loss < best_val_loss:
best_val_loss = val_loss
iteration_change_loss = 0
if iteration_change_loss == patience:
print(
'Early stopping after {0} iterations without the decrease of the val loss'
.format(iteration_change_loss))
break
