def get_transforms_fer_aug( size_input ):
return transforms.Compose([
#------------------------------------------------------------------
#Resize input
mtrans.ToResize( (48, 48), resize_mode='square', padding_mode=cv2.BORDER_REFLECT ),
#------------------------------------------------------------------
#Geometric
mtrans.RandomScale(factor=0.2, padding_mode=cv2.BORDER_REPLICATE ),
mtrans.ToRandomTransform( mtrans.RandomGeometricalTransform( angle=30, translation=0.2, warp=0.02, padding_mode=cv2.BORDER_REFLECT ), prob=0.5 ),
mtrans.ToRandomTransform( mtrans.VFlip(), prob=0.5 ),
#mtrans.ToRandomTransform( mtrans.HFlip(), prob=0.5 ),
#------------------------------------------------------------------
#Colors
mtrans.ToRandomTransform( mtrans.RandomBrightness( factor=0.25 ), prob=0.50 ),
mtrans.ToRandomTransform( mtrans.RandomContrast( factor=0.25 ), prob=0.50 ),
mtrans.ToRandomTransform( mtrans.RandomGamma( factor=0.25 ), prob=0.50 ),
mtrans.ToRandomTransform( mtrans.RandomRGBPermutation(), prob=0.50 ),
mtrans.ToRandomTransform( mtrans.CLAHE(), prob=0.25 ),
mtrans.ToRandomTransform( mtrans.ToGaussianBlur( sigma=0.05 ), prob=0.25 ),
#------------------------------------------------------------------
#Resize
mtrans.ToResize( (size_input+5, size_input+5), resize_mode='square', padding_mode=cv2.BORDER_REFLECT ),
mtrans.RandomCrop( (size_input, size_input), limit=2, padding_mode=cv2.BORDER_REFLECT ),
#------------------------------------------------------------------
mtrans.ToGrayscale(),
mtrans.ToTensor(),
normalize,
])
def get_transforms_det(size_input=256, size_crop=512):
return transforms.Compose([
mtrans.RandomCrop((size_crop, size_crop),
limit=10,
padding_mode=cv2.BORDER_REFLECT_101),
mtrans.ToResize((size_input, size_input),
resize_mode='square',
padding_mode=cv2.BORDER_REFLECT_101),
#mtrans.ToPad( 5 , 5, padding_mode=cv2.BORDER_REFLECT_101 ),
mtrans.ToTensor(),
normalize,
])
def get_transforms_aug(size_input=256, size_crop=512):
return transforms.Compose([
#------------------------------------------------------------------
#Resize
#
mtrans.RandomCrop((size_crop, size_crop),
limit=10,
padding_mode=cv2.BORDER_REFLECT_101),
mtrans.ToResize((size_input, size_input),
resize_mode='square',
padding_mode=cv2.BORDER_REFLECT_101),
#mtrans.ToPad( 5 , 5, padding_mode=cv2.BORDER_REFLECT_101 ),
#------------------------------------------------------------------
#Geometric
mtrans.ToRandomTransform(mtrans.VFlip(), prob=0.5),
mtrans.ToRandomTransform(mtrans.HFlip(), prob=0.5),
mtrans.RandomScale(factor=0.3, padding_mode=cv2.BORDER_REFLECT_101),
mtrans.ToRandomTransform(mtrans.RandomGeometricalTransform(
angle=45,
translation=0.2,
warp=0.02,
padding_mode=cv2.BORDER_REFLECT_101),
prob=0.5),
mtrans.ToRandomTransform(mtrans.RandomElasticDistort(
size_grid=32, deform=12, padding_mode=cv2.BORDER_REFLECT_101),
prob=0.5),
#mtrans.ToResizeUNetFoV(imsize, cv2.BORDER_REFLECT_101),
#------------------------------------------------------------------
#Colors
mtrans.ToRandomTransform(mtrans.RandomBrightness(factor=0.25),
prob=0.50),
mtrans.ToRandomTransform(mtrans.RandomContrast(factor=0.25),
prob=0.50),
mtrans.ToRandomTransform(mtrans.RandomGamma(factor=0.25), prob=0.50),
#mtrans.ToRandomTransform( mtrans.RandomRGBPermutation(), prob=0.50 ),
#mtrans.ToRandomTransform( mtrans.CLAHE(), prob=0.25 ),
#mtrans.ToRandomTransform(mtrans.ToGaussianBlur( sigma=0.05 ), prob=0.25 ),
#------------------------------------------------------------------
mtrans.ToTensor(),
normalize,
])
def main():
# parameters
parser = arg_parser()
args = parser.parse_args()
imsize = args.image_size
parallel = args.parallel
num_classes = 2
num_channels = 3
view_freq = 2
network = SegmentationNeuralNet(
patchproject=args.project,
nameproject=args.name,
no_cuda=args.no_cuda,
parallel=parallel,
seed=args.seed,
print_freq=args.print_freq,
gpu=args.gpu,
view_freq=view_freq,
)
network.create(arch=args.arch,
num_output_channels=num_classes,
num_input_channels=num_channels,
loss=args.loss,
lr=args.lr,
momentum=args.momentum,
optimizer=args.opt,
lrsch=args.scheduler,
pretrained=args.finetuning,
size_input=imsize)
# resume
network.resume(os.path.join(network.pathmodels, args.resume))
cudnn.benchmark = True
# datasets
# training dataset
train_data = tgsdata.TGSDataset(
args.data,
tgsdata.train,
count=16000,
num_channels=num_channels,
transform=transforms.Compose([
mtrans.ToRandomTransform(mtrans.HFlip(), prob=0.5),
mtrans.ToRandomTransform(mtrans.VFlip(), prob=0.5),
mtrans.ToResize((300, 300),
resize_mode='squash',
padding_mode=cv2.BORDER_REFLECT_101),
mtrans.RandomCrop((256, 256),
limit=10,
padding_mode=cv2.BORDER_REFLECT_101),
mtrans.RandomScale(factor=0.2,
padding_mode=cv2.BORDER_REFLECT_101),
mtrans.RandomGeometricalTransform(
angle=30,
translation=0.2,
warp=0.02,
padding_mode=cv2.BORDER_REFLECT_101),
#mtrans.ToResizeUNetFoV(imsize, cv2.BORDER_REFLECT_101),
mtrans.ToRandomTransform(mtrans.RandomBrightness(factor=0.15),
prob=0.50),
mtrans.ToRandomTransform(mtrans.RandomContrast(factor=0.15),
prob=0.50),
mtrans.ToRandomTransform(mtrans.RandomGamma(factor=0.15),
prob=0.50),
mtrans.ToRandomTransform(mtrans.ToGaussianBlur(), prob=0.15),
mtrans.ToTensor(),
mtrans.ToMeanNormalization(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
)
#mtrans.ToNormalization(),
]))
train_loader = DataLoader(train_data,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.workers,
pin_memory=network.cuda,
drop_last=True)
# validate dataset
val_data = tgsdata.TGSDataset(
args.data,
tgsdata.test,
count=4000,
num_channels=num_channels,
transform=transforms.Compose([
mtrans.ToResize((256, 256), resize_mode='squash'),
#mtrans.RandomCrop( (255,255), limit=50, padding_mode=cv2.BORDER_CONSTANT ),
#mtrans.ToResizeUNetFoV(imsize, cv2.BORDER_REFLECT_101),
mtrans.ToTensor(),
mtrans.ToMeanNormalization(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
)
#mtrans.ToNormalization(),
]))
val_loader = DataLoader(val_data,
batch_size=args.batch_size,
shuffle=False,
num_workers=args.workers,
pin_memory=network.cuda,
drop_last=True)
# print neural net class
print('SEG-Torch: {}'.format(datetime.datetime.now()))
print(network)
# training neural net
network.fit(train_loader, val_loader, args.epochs, args.snapshot)
print("Optimization Finished!")
print("DONE!!!")
from pytvision import visualization as view
data = SyntethicCircleDataset(
count=100,
generate=SyntethicCircleDataset.generate_image_mask_and_weight,
imsize=(512,512),
sigma=0.01,
bdraw_grid=True,
transform=transforms.Compose([
## resize and crop
mtrans.ToResize( (400,400), resize_mode='asp' ) ,
#mtrans.CenterCrop( (200,200) ),
mtrans.RandomCrop( (255,255), limit=50, padding_mode=cv2.BORDER_REFLECT_101 ),
#mtrans.ToResizeUNetFoV(388, cv2.BORDER_REFLECT_101),
## color
#mtrans.RandomSaturation(),
#mtrans.RandomHueSaturationShift(),
#mtrans.RandomHueSaturation(),
#mtrans.RandomRGBShift(),
#mtrans.ToNegative(),
#mtrans.RandomRGBPermutation(),
#mtrans.ToGrayscale(),
## blur
#mtrans.ToRandomTransform( mtrans.ToLinealMotionBlur( lmax=1 ), prob=0.5 ),
pathdataset = '/home/pdmf/.datasets/'
namedataset = 'cellcaltech0001'
sub_folder = ''
folders_images = 'images'
folders_labels = 'labels'
base_folder = os.path.join(pathdataset, namedataset)
data = CTECHDataset(
base_folder,
sub_folder,
count=10,
transform=transforms.Compose([
mtrans.ToResize((500, 500), resize_mode='crop'),
mtrans.RandomCrop((255, 255),
limit=50,
padding_mode=cv2.BORDER_CONSTANT),
#mtrans.ToResizeUNetFoV(388, cv2.BORDER_REFLECT_101),
mtrans.ToTensor(),
mtrans.ToNormalization(),
]))
# sample = data[0]
# for k,v in sample.items():
# print( k, ':', v.shape, v.min(), v.max() )
# print('\n')
# #assert(False)
dataloader = DataLoader(data, batch_size=3, shuffle=False, num_workers=1)
label_batched = []