import argparse
NUM_CHANNELS = 3
NUM_CLASSES = 22
color_transform = Colorize()
image_transform = ToPILImage()
input_transform = Compose([
CenterCrop(256),
ToTensor(),
Normalize([.485, .456, .406], [.229, .224, .225]),
])
target_transform = Compose([
CenterCrop(256),
ToLabel(),
Relabel(255, 21),
])
parser = argparse.ArgumentParser(
description='Single Shot MultiBox Detector Training With Pytorch')
parser.add_argument('--datadir', required=False, default="/data_1/data/VOC2012/VOCdevkit/VOC2012")
parser.add_argument('--epochs', default=50, type=int, metavar='N',
help='number of total epochs to run')
parser.add_argument('--save_interval', default=10, type=int, metavar='N',
help='number of epochs to save the model')
parser.add_argument('--batch_size', default=4, type=int,
help='Batch size for training')
parser.add_argument('--resume', default=None, type=str,
help='Checkpoint state_dict file to resume training from')
parser.add_argument('--cuda', action='store_true', default=True)
def __call__(self, input, target):
# do something to both images
input = Scale(self.height, Image.BILINEAR)(input)
target = Scale(self.height, Image.NEAREST)(target)
if (self.augment):
# Random hflip
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
target = target.transpose(Image.FLIP_LEFT_RIGHT)
degree = random.randint(-20, 20)
input = input.rotate(degree, resample=Image.BILINEAR, expand=True)
target = target.rotate(degree, resample=Image.NEAREST, expand=True)
w, h = input.size
nratio = random.uniform(0.5, 1.0)
ni = random.randint(0, int(h - nratio * h))
nj = random.randint(0, int(w - nratio * w))
input = input.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
target = target.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
input = Resize((480, 640), Image.BILINEAR)(input)
target = Resize((480, 640), Image.NEAREST)(target)
brightness_factor = random.uniform(0.8, 1.2)
contrast_factor = random.uniform(0.8, 1.2)
saturation_factor = random.uniform(0.8, 1.2)
#sharpness_factor=random.uniform(0.0,2.0)
hue_factor = random.uniform(-0.2, 0.2)
enhancer1 = ImageEnhance.Brightness(input)
input = enhancer1.enhance(brightness_factor)
enhancer2 = ImageEnhance.Contrast(input)
input = enhancer2.enhance(contrast_factor)
enhancer3 = ImageEnhance.Color(input)
input = enhancer3.enhance(saturation_factor)
#enhancer4=ImageEnhance.Sharpness(input)
#input=enhancer4.enhance(sharpness_factor)
input_mode = input.mode
h, s, v = input.convert('HSV').split()
np_h = np.array(h, dtype=np.uint8)
with np.errstate(over='ignore'):
np_h += np.uint8(hue_factor * 255)
h = Image.fromarray(np_h, 'L')
input = Image.merge('HSV', (h, s, v)).convert(input_mode)
else:
input = Resize((480, 640), Image.BILINEAR)(input)
target = Resize((480, 640), Image.NEAREST)(target)
input = ToTensor()(input)
if (self.enc):
target = Resize((60, 80), Image.NEAREST)(target)
target = ToLabel()(target)
target = Relabel(255, 27)(target)
return input, target
from shutil import copyfile
NUM_CHANNELS = 3
NUM_CLASSES = 28
color_transform = Colorize(NUM_CLASSES)
image_transform = ToPILImage()
input_transform = Compose([
CenterCrop(240),
ToTensor(),
Normalize([.485, .456, .406], [.229, .224, .225]),
])
target_transform = Compose([
CenterCrop(240),
ToLabel(),
Relabel(255, 27),
])
#Augmentations - different function implemented to perform random augments on both image and target
class MyCoTransform(object):
def __init__(self, enc, augment=True, height=480):
self.enc = enc
self.augment = augment
self.height = height
pass
def __call__(self, input, target):
# do something to both images
input = Scale(self.height, Image.BILINEAR)(input)
target = Scale(self.height, Image.NEAREST)(target)
image_transform = ToPILImage()
to_img=transforms.ToPILImage()
input_transform = Compose([
RandomGrayscale(0.02),
CenterCrop((512,512)),
ToTensor(),
Normalize([.485, .456, .406], [.229, .224, .225]),
])
target_transform = Compose([
CenterCrop((512,512)),
ToLabel(),
Relabel(255, 22),
])
)
def train(args, model):
model.train()
weight = torch.ones(22)
weight[0] = 0
if args.cuda:
criterion = CrossEntropyLoss2d(weight.cuda())
def __call__(self, input, target):
## do something to both images
# input = Resize((1086,1351), Image.BILINEAR)(input)
# target = Resize((1086,1351),Image.NEAREST)(target)
input = Resize((512, 1024), Image.BILINEAR)(input)
target = Resize((512, 1024), Image.NEAREST)(target)
# input = Resize((256,512), Image.BILINEAR)(input)
# target = Resize((256,512),Image.NEAREST)(target)
if (self.augment):
rotation_degree = 1
shear_degree = 1
input = RandomAffine(rotation_degree,
None,
None,
shear_degree,
resample=Image.BILINEAR,
fillcolor=0)(input)
target = RandomAffine(rotation_degree,
None,
None,
shear_degree,
resample=Image.NEAREST,
fillcolor=255)(target)
w, h = input.size
nratio = random.uniform(0.5, 1.0)
ni = random.randint(0, int(h - nratio * h))
nj = random.randint(0, int(w - nratio * w))
input = input.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
target = target.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
# input=Resize((256,512),Image.BILINEAR)(input)
# target=Resize((256,512),Image.NEAREST)(target)
input = Resize((512, 1024), Image.BILINEAR)(input)
target = Resize((512, 1024), Image.NEAREST)(target)
brightness = 0.1
contrast = 0.1
saturation = 0.1
hue = 0.1
input = ColorJitter(brightness, contrast, saturation, hue)(input)
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
target = target.transpose(Image.FLIP_LEFT_RIGHT)
else:
# input=Resize((256,512),Image.BILINEAR)(input)
# target=Resize((256,512),Image.NEAREST)(target)
input = Resize((512, 1024), Image.BILINEAR)(input)
target = Resize((512, 1024), Image.NEAREST)(target)
input = ToTensor()(input)
if (self.enc):
target = Resize((64, 128), Image.NEAREST)(target)
target = ToLabel()(target)
target = Relabel(255, 7)(target)
# print(np.max(target))
return input, target
from shutil import copyfile
NUM_CHANNELS = 3
NUM_CLASSES = 8
color_transform = Colorize(NUM_CLASSES)
image_transform = ToPILImage()
input_transform = Compose([
CenterCrop(240),
ToTensor(),
Normalize([.485, .456, .406], [.229, .224, .225]),
])
target_transform = Compose([
CenterCrop(240),
ToLabel(),
Relabel(255, 7),
])
#Important Data Augmentations
#Data Augmentations (Here Only Traditional Augmentations: Geometry + Texture) - different function implemented to perform random augments on both image and target
class MyCoTransform(object):
def __init__(self, enc, augment=True, height=512):
self.enc = enc
self.augment = augment
self.height = height
pass
def __call__(self, input, target):
## do something to both images