Python data.base_dataset.get_transform() Examples
The following are 30
code examples of data.base_dataset.get_transform().
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
data.base_dataset
, or try the search function
.
.
Example #1
| Source File: unaligned_dataset.py From 2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement with MIT License | 6 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
"""
BaseDataset.__init__(self, opt)
self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A') # create a path '/path/to/data/trainA'
self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B') # create a path '/path/to/data/trainB'
self.A_paths = sorted(make_dataset(self.dir_A, opt.max_dataset_size)) # load images from '/path/to/data/trainA'
self.B_paths = sorted(make_dataset(self.dir_B, opt.max_dataset_size)) # load images from '/path/to/data/trainB'
self.A_size = len(self.A_paths) # get the size of dataset A
self.B_size = len(self.B_paths) # get the size of dataset B
btoA = self.opt.direction == 'BtoA'
input_nc = self.opt.output_nc if btoA else self.opt.input_nc # get the number of channels of input image
output_nc = self.opt.input_nc if btoA else self.opt.output_nc # get the number of channels of output image
self.transform_A = get_transform(self.opt, grayscale=(input_nc == 1))
self.transform_B = get_transform(self.opt, grayscale=(output_nc == 1))
Example #2
| Source File: synthia_cityscapes.py From MADAN with MIT License | 6 votes |
|
def initialize(self, opt): self.opt = opt self.root = opt.dataroot self.dir_A = os.path.join(opt.dataroot, 'synthia', 'RGB') self.dir_B = os.path.join(opt.dataroot, 'cityscapes', 'leftImg8bit') self.dir_A_label = os.path.join(opt.dataroot, 'synthia', 'GT', 'parsed_LABELS') self.dir_B_label = os.path.join(opt.dataroot, 'cityscapes', 'gtFine') self.A_paths = make_dataset(self.dir_A) self.B_paths = make_dataset(self.dir_B) self.A_paths = sorted(self.A_paths) self.B_paths = sorted(self.B_paths) self.A_size = len(self.A_paths) self.B_size = len(self.B_paths) self.A_labels = make_dataset(self.dir_A_label) self.B_labels = make_cs_labels(self.dir_B_label) self.A_labels = sorted(self.A_labels) self.B_labels = sorted(self.B_labels) self.transform = get_transform(opt) self.label_transform = get_label_transform(opt)
Example #3
| Source File: template_dataset.py From 2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement with MIT License | 6 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
A few things can be done here.
- save the options (have been done in BaseDataset)
- get image paths and meta information of the dataset.
- define the image transformation.
"""
# save the option and dataset root
BaseDataset.__init__(self, opt)
# get the image paths of your dataset;
self.image_paths = [] # You can call sorted(make_dataset(self.root, opt.max_dataset_size)) to get all the image paths under the directory self.root
# define the default transform function. You can use <base_dataset.get_transform>; You can also define your custom transform function
self.transform = get_transform(opt)
Example #4
| Source File: unaligned_triplet_dataset.py From Recycle-GAN with MIT License | 6 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A')
self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B')
self.A_paths = make_dataset(self.dir_A)
self.B_paths = make_dataset(self.dir_B)
self.A_paths = sorted(self.A_paths)
self.B_paths = sorted(self.B_paths)
self.A_size = len(self.A_paths)
self.B_size = len(self.B_paths)
# self.transform = get_transform(opt)
transform_list = [transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5),
(0.5, 0.5, 0.5))]
self.transform = transforms.Compose(transform_list)
Example #5
| Source File: gta5_cityscapes.py From MADAN with MIT License | 6 votes |
|
def initialize(self, opt): self.opt = opt self.root = opt.dataroot self.dir_A = os.path.join(opt.dataroot, 'gta5', 'images') self.dir_B = os.path.join(opt.dataroot, 'cityscapes', 'leftImg8bit') self.dir_A_label = os.path.join(opt.dataroot, 'gta5', 'labels') self.dir_B_label = os.path.join(opt.dataroot, 'cityscapes', 'gtFine') self.A_paths = make_dataset(self.dir_A) self.B_paths = make_dataset(self.dir_B) self.A_paths = sorted(self.A_paths) self.B_paths = sorted(self.B_paths) self.A_size = len(self.A_paths) self.B_size = len(self.B_paths) self.A_labels = make_dataset(self.dir_A_label) self.B_labels = make_cs_labels(self.dir_B_label) self.A_labels = sorted(self.A_labels) self.B_labels = sorted(self.B_labels) self.transform = get_transform(opt) self.label_transform = get_label_transform(opt)
Example #6
| Source File: template_dataset.py From CAG_UDA with MIT License | 6 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
A few things can be done here.
- save the options (have been done in BaseDataset)
- get image paths and meta information of the dataset.
- define the image transformation.
"""
# save the option and dataset root
BaseDataset.__init__(self, opt)
# get the image paths of your dataset;
self.image_paths = [] # You can call sorted(make_dataset(self.root, opt.max_dataset_size)) to get all the image paths under the directory self.root
# define the default transform function. You can use <base_dataset.get_transform>; You can also define your custom transform function
self.transform = get_transform(opt)
Example #7
| Source File: template_dataset.py From EvolutionaryGAN-pytorch with MIT License | 6 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
A few things can be done here.
- save the options (have been done in BaseDataset)
- get image paths and meta information of the dataset.
- define the image transformation.
"""
# save the option and dataset root
BaseDataset.__init__(self, opt)
# get the image paths of your dataset;
self.image_paths = [] # You can call sorted(make_dataset(self.root, opt.max_dataset_size)) to get all the image paths under the directory self.root
# define the default transform function. You can use <base_dataset.get_transform>; You can also define your custom transform function
self.transform = get_transform(opt)
Example #8
| Source File: unaligned_dataset.py From ToDayGAN with BSD 2-Clause "Simplified" License | 5 votes |
|
def __init__(self, opt):
super(UnalignedDataset, self).__init__()
self.opt = opt
self.transform = get_transform(opt)
datapath = os.path.join(opt.dataroot, opt.phase + '*')
self.dirs = sorted(glob.glob(datapath))
self.paths = [sorted(make_dataset(d)) for d in self.dirs]
self.sizes = [len(p) for p in self.paths]
Example #9
| Source File: aligned_dataset.py From EverybodyDanceNow_reproduce_pytorch with MIT License | 5 votes |
|
def __getitem__(self, index):
### input A (label maps)
A_path = self.A_paths[index]
A = Image.open(A_path)
params = get_params(self.opt, A.size)
if self.opt.label_nc == 0:
transform_A = get_transform(self.opt, params)
A_tensor = transform_A(A.convert('RGB'))
else:
transform_A = get_transform(self.opt, params, method=Image.NEAREST, normalize=False)
A_tensor = transform_A(A) * 255.0
B_tensor = inst_tensor = feat_tensor = 0
### input B (real images)
if self.opt.isTrain:
B_path = self.B_paths[index]
B = Image.open(B_path).convert('RGB')
transform_B = get_transform(self.opt, params)
B_tensor = transform_B(B)
### if using instance maps
if not self.opt.no_instance:
inst_path = self.inst_paths[index]
inst = Image.open(inst_path)
inst_tensor = transform_A(inst)
if self.opt.load_features:
feat_path = self.feat_paths[index]
feat = Image.open(feat_path).convert('RGB')
norm = normalize()
feat_tensor = norm(transform_A(feat))
input_dict = {'label': A_tensor, 'inst': inst_tensor, 'image': B_tensor,
'feat': feat_tensor, 'path': A_path}
return input_dict
Example #10
| Source File: gta_synthia_cityscapes.py From MADAN with MIT License | 5 votes |
|
def initialize(self, opt): # SYNTHIA as dataset 1 # GTAV as dataset 2 self.opt = opt self.root = opt.dataroot self.dir_A_1 = os.path.join(opt.dataroot, 'synthia', 'RGB') self.dir_A_2 = os.path.join(opt.dataroot, 'gta5', 'images') self.dir_B = os.path.join(opt.dataroot, 'cityscapes', 'leftImg8bit') self.dir_A_label_1 = os.path.join(opt.dataroot, 'synthia', 'GT', 'parsed_LABELS') self.dir_A_label_2 = os.path.join(opt.dataroot, 'gta5', 'labels') self.A_paths_1 = make_dataset(self.dir_A_1) self.A_paths_2 = make_dataset(self.dir_A_2) self.B_paths = make_dataset(self.dir_B) self.A_paths_1 = sorted(self.A_paths_1) self.A_paths_2 = sorted(self.A_paths_2) self.B_paths = sorted(self.B_paths) self.A_size_1 = len(self.A_paths_1) self.A_size_2 = len(self.A_paths_2) self.B_size = len(self.B_paths) self.A_labels_1 = make_dataset(self.dir_A_label_1) self.A_labels_2 = make_dataset(self.dir_A_label_2) self.A_labels_1 = sorted(self.A_labels_1) self.A_labels_2 = sorted(self.A_labels_2) self.transform = get_transform(opt) self.label_transform = get_label_transform(opt)
Example #11
| Source File: single_dataset.py From monocularDepth-Inference with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.data_directory
self.dir_A = os.path.join(opt.data_directory)
self.A_paths = make_dataset(self.dir_A)
self.A_paths = sorted(self.A_paths)
self.transform = get_transform(opt)
Example #12
| Source File: aligned_dataset.py From deep-learning-for-document-dewarping with MIT License | 5 votes |
|
def __getitem__(self, index):
### input A (label maps)
A_path = self.A_paths[index]
A = Image.open(A_path)
params = get_params(self.opt, A.size)
if self.opt.label_nc == 0:
transform_A = get_transform(self.opt, params)
A_tensor = transform_A(A.convert('RGB'))
else:
transform_A = get_transform(self.opt, params, method=Image.NEAREST, normalize=False)
A_tensor = transform_A(A) * 255.0
B_tensor = inst_tensor = feat_tensor = 0
### input B (real images)
if self.opt.isTrain or self.opt.use_encoded_image:
B_path = self.B_paths[index]
B = Image.open(B_path).convert('RGB')
transform_B = get_transform(self.opt, params)
B_tensor = transform_B(B)
### if using instance maps
if not self.opt.no_instance:
inst_path = self.inst_paths[index]
inst = Image.open(inst_path)
inst_tensor = transform_A(inst)
if self.opt.load_features:
feat_path = self.feat_paths[index]
feat = Image.open(feat_path).convert('RGB')
norm = normalize()
feat_tensor = norm(transform_A(feat))
input_dict = {'label': A_tensor, 'inst': inst_tensor, 'image': B_tensor,
'feat': feat_tensor, 'path': A_path}
return input_dict
Example #13
| Source File: unaligned_dataset.py From Bayesian-CycleGAN with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A')
self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B')
self.A_paths = make_dataset(self.dir_A)
self.B_paths = make_dataset(self.dir_B)
self.A_paths = sorted(self.A_paths)
self.B_paths = sorted(self.B_paths)
self.A_size = len(self.A_paths)
self.B_size = len(self.B_paths)
self.transform = get_transform(opt)
Example #14
| Source File: single_dataset.py From non-stationary_texture_syn with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot)
self.A_paths = make_dataset(self.dir_A)
self.A_paths = sorted(self.A_paths)
self.transform = get_transform(opt)
Example #15
| Source File: single_dataset.py From colorization-pytorch with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot)
self.A_paths = make_dataset(self.dir_A)
self.A_paths = sorted(self.A_paths)
self.transform = get_transform(opt)
Example #16
| Source File: color_dataset.py From colorization-pytorch with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot)
self.A_paths = make_dataset(self.dir_A)
self.A_paths = sorted(self.A_paths)
self.transform = get_transform(opt)
Example #17
| Source File: unaligned_dataset.py From ComboGAN with BSD 2-Clause "Simplified" License | 5 votes |
|
def __init__(self, opt):
super(UnalignedDataset, self).__init__()
self.opt = opt
self.transform = get_transform(opt)
datapath = os.path.join(opt.dataroot, opt.phase + '*')
self.dirs = sorted(glob.glob(datapath))
self.paths = [sorted(make_dataset(d)) for d in self.dirs]
self.sizes = [len(p) for p in self.paths]
Example #18
| Source File: single_dataset.py From angularGAN with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot)
self.A_paths = make_dataset(self.dir_A)
self.A_paths = sorted(self.A_paths)
self.transform = get_transform(opt)
Example #19
| Source File: unaligned_dataset.py From angularGAN with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A')
self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B')
self.A_paths = make_dataset(self.dir_A)
self.B_paths = make_dataset(self.dir_B)
self.A_paths = sorted(self.A_paths)
self.B_paths = sorted(self.B_paths)
self.A_size = len(self.A_paths)
self.B_size = len(self.B_paths)
self.transform = get_transform(opt)
Example #20
| Source File: single_dataset.py From iSketchNFill with GNU General Public License v3.0 | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot)
self.A_paths = make_dataset(self.dir_A)
self.A_paths = sorted(self.A_paths)
self.transform = get_transform(opt)
Example #21
| Source File: single_dataset.py From 2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement with MIT License | 5 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
"""
BaseDataset.__init__(self, opt)
self.A_paths = sorted(make_dataset(opt.dataroot, opt.max_dataset_size))
input_nc = self.opt.output_nc if self.opt.direction == 'BtoA' else self.opt.input_nc
self.transform = get_transform(opt, grayscale=(input_nc == 1))
Example #22
| Source File: colorization_dataset.py From 2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement with MIT License | 5 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
"""
BaseDataset.__init__(self, opt)
self.dir = os.path.join(opt.dataroot, opt.phase)
self.AB_paths = sorted(make_dataset(self.dir, opt.max_dataset_size))
assert(opt.input_nc == 1 and opt.output_nc == 2 and opt.direction == 'AtoB')
self.transform = get_transform(self.opt, convert=False)
Example #23
| Source File: unaligned_dataset.py From Recycle-GAN with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A')
self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B')
self.A_paths = make_dataset(self.dir_A)
self.B_paths = make_dataset(self.dir_B)
self.A_paths = sorted(self.A_paths)
self.B_paths = sorted(self.B_paths)
self.A_size = len(self.A_paths)
self.B_size = len(self.B_paths)
self.transform = get_transform(opt)
Example #24
| Source File: hdf5_dataset.py From EvolutionaryGAN-pytorch with MIT License | 5 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
A few things can be done here.
- save the options (have been done in BaseDataset)
- get image paths and meta information of the dataset.
- define the image transformation.
"""
# save the option and dataset root
BaseDataset.__init__(self, opt)
# get the image paths of your dataset;
self.hdf5_path = os.path.join(opt.dataroot, opt.hdf5_filename)
self.load_in_mem = opt.load_in_mem
self.imkey = None
self.lkey = None
with h5.File(self.hdf5_path,'r') as f:
key_list = list(f.keys())
for key in key_list:
if key == 'data' or key == 'imgs':
self.imkey = key
self.num_imgs = len(f[self.imkey])
elif key == 'label' or key == 'labels':
self.lkey = key
else:
raise ValueError('Unkown key in the HDF5 file.')
# If loading into memory, do so now
if self.load_in_mem:
print('Loading %s into memory...' % self.hdf5_path)
self.data = f[self.imkey][:]
self.labels = f[self.lkey][:] if (self.lkey is not None) else None
# define the default transform function.
self.transform = get_transform(opt)
Example #25
| Source File: single_dataset.py From EvolutionaryGAN-pytorch with MIT License | 5 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
"""
BaseDataset.__init__(self, opt)
self.A_paths = sorted(make_dataset(opt.dataroot, opt.max_dataset_size))
self.transform = get_transform(opt, grayscale=(self.opt.input_nc == 1))
Example #26
| Source File: torchvision_dataset.py From EvolutionaryGAN-pytorch with MIT License | 5 votes |
|
def __init__(self, opt):
"""Initialize this dataset class.
Parameters:
opt (Option class) -- stores all the experiment flags; needs to be a subclass of BaseOptions
A few things can be done here.
- save the options (have been done in BaseDataset)
- get image paths and meta information of the dataset.
- define the image transformation.
"""
# save the option and dataset root
BaseDataset.__init__(self, opt)
# define the default transform function. You can use <base_dataset.get_transform>; You can also define your custom transform function
self.transform = get_transform(opt)
# import torchvision dataset
if opt.dataset_name == 'CIFAR10':
from torchvision.datasets import CIFAR10 as torchvisionlib
elif opt.dataset_name == 'CIFAR100':
from torchvision.datasets import CIFAR100 as torchvisionlib
else:
raise ValueError('torchvision_dataset import fault.')
self.dataload = torchvisionlib(root = opt.download_root,
transform = self.transform,
download = True)
Example #27
| Source File: labeled_dataset.py From iSketchNFill with GNU General Public License v3.0 | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_scribbles = os.path.join(opt.dataroot, 'scribbles') #'pix2pix') #'scribbles' ) #'masks')
self.dir_images = os.path.join(opt.dataroot, 'images') #os.path.join(opt.dataroot, 'images')
self.classes = sorted(os.listdir(self.dir_images)) # sorted so that the same order in all cases; check if you've to change this with other models
self.num_classes = len(self.classes)
self.scribble_paths = []
self.images_paths = []
for cl in self.classes:
self.scribble_paths.append(sorted( make_dataset( os.path.join( self.dir_scribbles , cl ) ) ) )
self.images_paths.append( sorted( make_dataset( os.path.join( self.dir_images , cl ) ) ) )
self.cum_sizes = []
self.sizes = []
size =0
for i in range(self.num_classes):
size += len(self.scribble_paths[i])
self.cum_sizes.append(size)
self.sizes.append(size)
self.transform = get_transform(opt)
self.sparse_transform = get_sparse_transform(opt)
self.mask_transform = get_mask_transform(opt)
Example #28
| Source File: labeled_dataset.py From iSketchNFill with GNU General Public License v3.0 | 5 votes |
|
def get_transform(self):
return self.transform
Example #29
| Source File: unaligned_dataset.py From non-stationary_texture_syn with MIT License | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A')
self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B')
self.A_paths = make_dataset(self.dir_A)
self.B_paths = make_dataset(self.dir_B)
self.A_paths = sorted(self.A_paths)
self.B_paths = sorted(self.B_paths)
self.A_size = len(self.A_paths)
self.B_size = len(self.B_paths)
self.transform = get_transform(opt)
Example #30
| Source File: unaligned_dataset.py From iSketchNFill with GNU General Public License v3.0 | 5 votes |
|
def initialize(self, opt):
self.opt = opt
self.root = opt.dataroot
self.dir_A = os.path.join(opt.dataroot, opt.phase + 'A')
self.dir_B = os.path.join(opt.dataroot, opt.phase + 'B')
self.A_paths = make_dataset(self.dir_A)
self.B_paths = make_dataset(self.dir_B)
self.A_paths = sorted(self.A_paths)
self.B_paths = sorted(self.B_paths)
self.A_size = len(self.A_paths)
self.B_size = len(self.B_paths)
self.transform = get_transform(opt)
