Python torchvision.transforms.RandomSizedCrop() Examples
The following are 30
code examples of torchvision.transforms.RandomSizedCrop().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
torchvision.transforms
, or try the search function
.
.
Example #1
| Source File: test_modules.py From CAMP_iccv19 with Apache License 2.0 | 6 votes |
|
def test_f30k_dataloader():
data_name = "f30k"
data_path = "./data/f30k"
vocab_path = "./vocab/"
vocab = pickle.load(open(os.path.join(vocab_path,
'%s_vocab.pkl' % data_name), 'rb'))
roots, ids = data.get_paths(data_path, data_name, False)
transform = transforms.Compose([transforms.RandomSizedCrop(224),
transforms.ToTensor()])
print (roots, ids)
train_loader = data.get_loader_single(data_name, "train", # !!!
roots["train"]["img"],
roots["train"]["cap"],
vocab, transform, ids=ids["train"],
batch_size=16, shuffle=False,
num_workers=1,
collate_fn=data.collate_fn,
distributed=False)
print ("f30k dataloader output:", train_loader.dataset.img_num)
#for (id, x) in enumerate(train_loader):
#if id > 0 : break
#print (id, x)
Example #2
| Source File: data.py From CAMP_iccv19 with Apache License 2.0 | 6 votes |
|
def get_transform(data_name, split_name, opt):
normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
t_list = []
if split_name == "train":
t_list = [transforms.RandomSizedCrop(opt.crop_size),
transforms.RandomHorizontalFlip()]
elif split_name == "val":
t_list = [transforms.Resize(256), transforms.CenterCrop(224)]
#t_list = [transforms.Resize((224, 224))]
elif split_name == "test":
t_list = [transforms.Resize(256), transforms.CenterCrop(224)]
#t_list = [transforms.Resize((224, 224))]
"""if "CUHK" in data_name:
t_end = [transforms.ToTensor()]
else:"""
t_end = [transforms.ToTensor(), normalizer]
transform = transforms.Compose(t_list + t_end)
return transform
Example #3
| Source File: amnet.py From AMNet with MIT License | 6 votes |
|
def init_transformations(self):
if self.hps.torchvision_version_major == 0 and self.hps.torchvision_version_minor < 2:
_resize = transforms.Scale
_rnd_resize_crop = transforms.RandomSizedCrop
else:
_resize = transforms.Resize
_rnd_resize_crop = transforms.RandomResizedCrop
self.train_transform = transforms.Compose([
_resize([264, 264]),
_rnd_resize_crop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=self.hps.img_mean, std=self.hps.img_std)
])
# Test
self.test_transform = transforms.Compose([
_resize([224, 224]),
transforms.ToTensor(),
transforms.Normalize(mean=self.hps.img_mean, std=self.hps.img_std)
])
return
Example #4
| Source File: ImageNet12.py From quantized_distillation with MIT License | 6 votes |
|
def getTrainLoader(self, batch_size, shuffle=True, num_workers=4):
# first we define the training transform we will apply to the dataset
list_of_transforms = []
list_of_transforms.append(vision_transforms.RandomSizedCrop(self.size_images))
list_of_transforms.append(vision_transforms.RandomHorizontalFlip())
if self.type_of_data_augmentation == 'extended':
list_of_transforms.append(vision_transforms.ColorJitter(brightness=0.4,
contrast=0.4,
saturation=0.4))
list_of_transforms.append(vision_transforms.ToTensor())
if self.type_of_data_augmentation == 'extended':
list_of_transforms.append(vision_transforms_extension.Lighting(alphastd=0.1,
eigval=self.pca['eigval'],
eigvec=self.pca['eigvec']))
list_of_transforms.append(vision_transforms.Normalize(mean=self.meanstd['mean'],
std=self.meanstd['std']))
train_transform = vision_transforms.Compose(list_of_transforms)
train_set = torchvision.datasets.ImageFolder(self.trainFolder, train_transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=batch_size, shuffle=shuffle,
num_workers=num_workers, pin_memory=self.pin_memory)
return train_loader
Example #5
| Source File: imagenet_models.py From imagenet with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def _get_label(self, train_dir): # Normalize on RGB Value normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) # Train -> Preprocessing -> Tensor train_dataset = datasets.ImageFolder( train_dir, transforms.Compose([ transforms.RandomSizedCrop(self._size[0]), #224 , 299 transforms.RandomHorizontalFlip(), transforms.ToTensor(), normalize, ])) # Get number of labels return train_dataset.classes
Example #6
| Source File: modular_transforms.py From dlupi-heteroscedastic-dropout with MIT License | 5 votes |
|
def get_reproducible_rand_transform(opt):
""" Image data and side info can be transformed identically. """
return [
reproducible_transforms.RandomSizedCrop(opt.image_size),
reproducible_transforms.RandomHorizontalFlip(),
reproducible_transforms.ToTensor(),
reproducible_transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
]
Example #7
| Source File: preprocess.py From DSGN with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
Example #8
| Source File: preprocess.py From DSGN with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #9
| Source File: preprocess.py From DeepLiDAR with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
Example #10
| Source File: preprocess.py From DeepLiDAR with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #11
| Source File: preprocess.py From DeepLiDAR with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
Example #12
| Source File: preprocess.py From DeepLiDAR with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #13
| Source File: preprocess.py From DSGN with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #14
| Source File: modular_transforms.py From dlupi-heteroscedastic-dropout with MIT License | 5 votes |
|
def get_nonreproducible_rand_transform(opt):
return transforms.Compose([
transforms.RandomSizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
Example #15
| Source File: datasets.py From Deep_Openset_Recognition_through_Uncertainty with MIT License | 5 votes |
|
def __get_transforms(self, patch_size):
train_transforms = transforms.Compose([
transforms.Resize(patch_size + 32),
transforms.RandomSizedCrop(patch_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
])
val_transforms = transforms.Compose([
transforms.Resize(patch_size + 32),
transforms.CenterCrop(patch_size),
transforms.ToTensor(),
])
return train_transforms, val_transforms
Example #16
| Source File: preprocess.py From AnyNet with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
Example #17
| Source File: preprocess.py From AnyNet with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #18
| Source File: preprocess.py From AnyNet with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
Example #19
| Source File: preprocess.py From AnyNet with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #20
| Source File: preprocess.py From 360SD-Net with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #21
| Source File: sun_dataset.py From dogTorch with MIT License | 5 votes |
|
def __init__(self, args, train=True):
self.root_dir = args.data
root_dir = self.root_dir
if train:
self.data_set_list = os.path.join(root_dir,
args.trainset_image_list)
else:
self.data_set_list = os.path.join(root_dir, args.testset_image_list)
self.categ_dict = get_class_names(
os.path.join(root_dir, 'ClassName.txt'))
self.data_set_list = parse_file(self.data_set_list, self.categ_dict)
self.args = args
self.read_features = args.read_features
self.features_dir = args.features_dir
if train:
self.transform = transforms.Compose([
transforms.RandomSizedCrop(args.image_size),
transforms.RandomHorizontalFlip(),
transforms.Scale((args.image_size, args.image_size)),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
])
else:
self.transform = transforms.Compose([
transforms.Scale((args.image_size, args.image_size)),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
])
Example #22
| Source File: preprocess.py From PSMNet with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
Example #23
| Source File: preprocess.py From PSMNet with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #24
| Source File: preprocess.py From PSMNet with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
Example #25
| Source File: preprocess.py From PSMNet with MIT License | 5 votes |
|
def inception_color_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
#transforms.RandomSizedCrop(input_size),
#transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
ColorJitter(
brightness=0.4,
contrast=0.4,
saturation=0.4,
),
Lighting(0.1, __imagenet_pca['eigval'], __imagenet_pca['eigvec']),
transforms.Normalize(**normalize)
])
Example #26
| Source File: __init__.py From DSMnet with Apache License 2.0 | 5 votes |
|
def Imagenet_train():
return transforms.Compose([
transforms.Scale(256), # 重新改变大小为size=(w, h) 或 (size, size)
transforms.RandomSizedCrop(224), # 随机剪切并resize成给定的size大小
transforms.RandomHorizontalFlip(), # 概率为0.5，随机水平翻转。
transforms.ToTensor(), # 转化为tensor数据
ColorJitter(Jitter=0.4, group=1, same_group=False),
Lighting(alphastd=0.1, group=1, same_group=False),
Normalize_Imagenet(),
])
Example #27
| Source File: test_first_block.py From kinetics_i3d_pytorch with MIT License | 5 votes |
|
def test_input_block():
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
dataset = datasets.ImageFolder('/sequoia/data1/yhasson/datasets/test-dataset',
transforms.Compose([
transforms.RandomSizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
normalize,
]))
densenet = torchvision.models.densenet121(pretrained=True)
features = densenet.features
seq2d = torch.nn.Sequential(
features.conv0, features.norm0, features.relu0, features.pool0)
seq3d = torch.nn.Sequential(
inflate.inflate_conv(features.conv0, 3),
inflate.inflate_batch_norm(features.norm0),
features.relu0,
inflate.inflate_pool(features.pool0, 1))
loader = torch.utils.data.DataLoader(dataset, batch_size=2, shuffle=False)
frame_nb = 4
for i, (input_2d, target) in enumerate(loader):
target = target.cuda()
target_var = torch.autograd.Variable(target)
input_2d_var = torch.autograd.Variable(input_2d)
out2d = seq2d(input_2d_var)
time_pad = torch.nn.ReplicationPad3d((0, 0, 0, 0, 1, 1))
input_3d = input_2d.unsqueeze(2).repeat(1, 1, frame_nb, 1, 1)
input_3d_var = time_pad(input_3d)
out3d = seq3d(input_3d_var)
expected_out_3d = out2d.data.unsqueeze(2).repeat(1, 1, frame_nb, 1, 1)
out_diff = expected_out_3d - out3d.data
print(out_diff.max())
assert(out_diff.max() < 0.0001)
Example #28
| Source File: preprocess.py From 360SD-Net with MIT License | 5 votes |
|
def scale_crop(input_size, scale_size=None, normalize=__imagenet_stats):
t_list = [
transforms.ToTensor(),
transforms.Normalize(**normalize),
]
#if scale_size != input_size:
#t_list = [transforms.Scale((960,540))] + t_list
return transforms.Compose(t_list)
# def scale_random_crop(input_size, scale_size=None, normalize=__imagenet_stats):
# t_list = [
# transforms.RandomCrop(input_size),
# transforms.ToTensor(),
# transforms.Normalize(**normalize),
# ]
# if scale_size != input_size:
# t_list = [transforms.Scale(scale_size)] + t_list
#
# transforms.Compose(t_list)
#
#
# def pad_random_crop(input_size, scale_size=None, normalize=__imagenet_stats):
# padding = int((scale_size - input_size) / 2)
# return transforms.Compose([
# transforms.RandomCrop(input_size, padding=padding),
# transforms.RandomHorizontalFlip(),
# transforms.ToTensor(),
# transforms.Normalize(**normalize),
# ])
#
#
# def inception_preproccess(input_size, normalize=__imagenet_stats):
# return transforms.Compose([
# transforms.RandomSizedCrop(input_size),
# transforms.RandomHorizontalFlip(),
# transforms.ToTensor(),
# transforms.Normalize(**normalize)
# ])
Example #29
| Source File: data.py From VSE-C with MIT License | 5 votes |
|
def get_transform(data_name, split_name, opt):
normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
t_list = []
if split_name == 'train':
t_list = [transforms.RandomSizedCrop(opt.crop_size),
transforms.RandomHorizontalFlip()]
elif split_name == 'val':
t_list = [transforms.Scale(256), transforms.CenterCrop(224)]
elif split_name == 'test':
t_list = [transforms.Scale(256), transforms.CenterCrop(224)]
t_end = [transforms.ToTensor(), normalizer]
transform = transforms.Compose(t_list + t_end)
return transform
Example #30
| Source File: preprocess.py From StereoNet-ActiveStereoNet with MIT License | 5 votes |
|
def inception_preproccess(input_size, normalize=__imagenet_stats):
return transforms.Compose([
transforms.RandomSizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(**normalize)
])
