def transforms_val(self, sample):
composed_transforms = transforms.Compose([
tr.FixedResize(size=self.input_size),
tr.Normalize(mean=[x / 255.0 for x in [125.3, 123.0, 113.9]],
std=[x / 255.0 for x in [63.0, 62.1, 66.7]]),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_val(self, sample):
composed_transforms = transforms.Compose([
tr.FixedResize(size=self.args['crop_size']),
tr.Normalize(mean=self.mean, std=self.std),
tr.ToTensor()
])
return composed_transforms(sample)
def transform_ts(self, sample):
composed_transforms = transforms.Compose([
tr.FixedResize(size=400),
tr.Normalize(mean=self.source_dist['mean'],
std=self.source_dist['std']),
tr.ToTensor(),
])
return composed_transforms(sample)
def transforms_train_esp(self, sample):
composed_transforms = transforms.Compose([
tr.RandomVerticalFlip(),
tr.RandomHorizontalFlip(),
tr.RandomAffine(degrees=40, scale=(.9, 1.1), shear=30),
tr.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5),
tr.FixedResize(size=self.input_size),
tr.Normalize(mean=[x / 255.0 for x in [125.3, 123.0, 113.9]],
std=[x / 255.0 for x in [63.0, 62.1, 66.7]]),
tr.ToTensor()
])
return composed_transforms(sample)
def get_mean_std(self, ratio=0.1):
trs = tf.Compose(
[tr.FixedResize(512),
tr.Normalize(mean=0, std=1),
tr.ToTensor()])
dataset = LungDataset(root_dir=r'D:\code\U-net',
transforms=trs,
train=True)
print(dataset)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=int(
len(dataset) * ratio),
shuffle=True,
num_workers=4)
for item in dataloader:
train = item['image']
# train = np.array(train) #?
print(train.shape)
print('sample {} images to calculate'.format(train.shape[0]))
mean = np.mean(train.numpy(), axis=(0, 2, 3))
std = np.std(train.numpy(), axis=(0, 2, 3))
return mean, std
def __len__(self):
return len(self.images)
if __name__ == '__main__':
import matplotlib.pyplot as plt
import helpers as helpers
import torch
import custom_transforms as tr
from torchvision import transforms
transform = transforms.Compose([tr.ToTensor()])
composed_transforms_tr = transforms.Compose([
tr.RandomHorizontalFlip(),
tr.ScaleNRotate(rots=(-30, 30), scales=(.9, 1.1), semseg=True),
tr.CropFromMask(crop_elems=('image', 'gt'), zero_pad=True),
tr.FixedResize(resolutions={'crop_image': (512, 512), 'crop_gt': (512, 512)}),
# tr.ExtremePoints(sigma=10, pert=0, elem='crop_gt'),
# tr.ToImage(norm_elem='extreme_points'),
tr.SelectRange(elem = 'crop_image', _min = 20, _max = 250),
tr.Normalize(elems = ['crop_image']),
# tr.ConcatInputs(elems=('crop_image', 'extreme_points')),
tr.AddConfidenceMap(elem = 'crop_image', hm_type = 'l1l2', tau = 7),
tr.ToTensor()])
dataset = ChaosSegmentation(split=['val'], transform=composed_transforms_tr)
dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=False, num_workers=1)
for i, sample in enumerate(dataloader):
five = sample['with_hm'].numpy()[0]
im = np.transpose(five[:3], (1,2,0))
# pts = five[3]
return len(self.images)
if __name__ == '__main__':
import matplotlib.pyplot as plt
import helpers as helpers
import torch
import custom_transforms as tr
from torchvision import transforms
transform = transforms.Compose([tr.ToTensor()])
composed_transforms_tr = transforms.Compose([
tr.RandomHorizontalFlip(),
tr.ScaleNRotate(rots=(-30, 30), scales=(.9, 1.1), semseg=True),
tr.CropFromMask(crop_elems=('image', 'gt'), relax=20, zero_pad=True),
tr.FixedResize(resolutions={
'crop_image': (256, 256),
'crop_gt': (256, 256)
}),
# tr.ExtremePoints(sigma=10, pert=0, elem='crop_gt'),
# tr.ToImage(norm_elem='extreme_points'),
# tr.SelectRange(elem = 'crop_image', _min = -25, _max = 230),
# tr.Normalize(elems = ['crop_image']),
# tr.ConcatInputs(elems=('crop_image', 'extreme_points')),
tr.AddHeatMap(elem='crop_image', hm_type='l1l2', tau=7),
tr.ToTensor()
])
dataset = LV_Segmentation(split=['train'],
transform=composed_transforms_tr)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
if resume_epoch != 0:
runs = sorted(glob.glob(os.path.join(save_directory_root, 'run', 'run_*')))
run_id = int(runs[-1].split('_')[-1]) if runs else 0
else:
runs = sorted(glob.glob(os.path.join(save_directory_root, 'run', 'run_*')))
run_id = int(runs[-1].split('_')[-1]) + 1 if runs else 0
# save_directory = os.path.join(save_directory_root, 'run', 'run_' + str(run_id))
# save_directory = os.path.join(save_directory_root, str(run_id))
save_directory = save_directory_root
# -------------------------------------------------------------------------------
# Load and Initialize Data
# -------------------------------------------------------------------------------
transforms_train = transforms.Compose([
tr.FixedResize(size=(512, 512)),
tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
tr.ToTensor(),
])
transforms_val = transforms.Compose([
tr.FixedResize(size=(512, 512)),
tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
tr.ToTensor(),
])
voc_train = pascal.VOCSegmentation(split='train', transform=transforms_train)
voc_val = pascal.VOCSegmentation(split='val', transform=transforms_val)
trainloader = DataLoader(voc_train,
batch_size=p['trainBatch'],
shuffle=True,