def __init__(self,
root,
output_size,
dataset_file='meta.json',
clip_n=3,
max_obj_n=11):
self.root = root
self.clip_n = clip_n
self.output_size = output_size
self.max_obj_n = max_obj_n
dataset_path = os.path.join(root, dataset_file)
with open(dataset_path, 'r') as json_file:
meta_data = json.load(json_file)
self.dataset_list = list(meta_data['videos'])
self.dataset_size = len(self.dataset_list)
self.random_horizontal_flip = mytrans.RandomHorizontalFlip(0.3)
self.color_jitter = TF.ColorJitter(0.1, 0.1, 0.1, 0.02)
self.random_affine = mytrans.RandomAffine(degrees=15,
translate=(0.1, 0.1),
scale=(0.95, 1.05),
shear=10)
self.random_resize_crop = mytrans.RandomResizedCrop(
output_size, (0.3, 0.5), (0.95, 1.05))
self.to_tensor = TF.ToTensor()
self.to_onehot = mytrans.ToOnehot(max_obj_n, shuffle=True)
def __init__(self,
root,
output_size,
imset='2017/train.txt',
clip_n=3,
max_obj_n=11):
self.root = root
self.clip_n = clip_n
self.output_size = output_size
self.max_obj_n = max_obj_n
dataset_path = os.path.join(root, 'ImageSets', imset)
self.dataset_list = list()
with open(os.path.join(dataset_path), 'r') as lines:
for line in lines:
dataset_name = line.strip()
if len(dataset_name) > 0:
self.dataset_list.append(dataset_name)
self.random_horizontal_flip = mytrans.RandomHorizontalFlip(0.3)
self.color_jitter = TF.ColorJitter(0.1, 0.1, 0.1, 0.02)
self.random_affine = mytrans.RandomAffine(degrees=15,
translate=(0.1, 0.1),
scale=(0.95, 1.05),
shear=10)
self.random_resize_crop = mytrans.RandomResizedCrop(
output_size, (0.8, 1), (0.95, 1.05))
self.to_tensor = TF.ToTensor()
self.to_onehot = mytrans.ToOnehot(max_obj_n, shuffle=True)
def __init__(self, root, dataset_file='videos.txt', max_obj_n=5):
self.root = root
self.dataset_list = list()
with open(os.path.join(root, dataset_file), 'r') as lines:
for line in lines:
dataset_name = line.strip()
if len(dataset_name) > 0:
self.dataset_list.append(dataset_name)
self.to_tensor = TF.ToTensor()
self.to_onehot = mytrans.ToOnehot(max_obj_n, shuffle=False)
def __init__(self,
root,
img_set='2017/val.txt',
max_obj_n=11,
single_obj=False):
self.root = root
self.single_obj = single_obj
dataset_path = os.path.join(root, 'ImageSets', img_set)
self.dataset_list = list()
with open(os.path.join(dataset_path), 'r') as lines:
for line in lines:
dataset_name = line.strip()
if len(dataset_name) > 0:
self.dataset_list.append(dataset_name)
self.to_tensor = TF.ToTensor()
self.to_onehot = mytrans.ToOnehot(max_obj_n, shuffle=False)
def __init__(self,
root,
dataset_file='meta.json',
output_size=(495, 880),
max_obj_n=11):
self.root = root
self.max_obj_n = max_obj_n
self.out_h, self.out_w = output_size
dataset_path = os.path.join(root, dataset_file)
with open(dataset_path, 'r') as json_file:
self.meta_data = json.load(json_file)
self.dataset_list = list(self.meta_data['videos'])
self.dataset_size = len(self.dataset_list)
self.to_tensor = TF.ToTensor()
self.to_onehot = mytrans.ToOnehot(max_obj_n, shuffle=False)
def __init__(self, img_dir, mask_dir):
self.img_list = sorted(
glob(os.path.join(img_dir, '*.jpg')) +
glob(os.path.join(img_dir, '*.png')))
self.mask_list = sorted(glob(os.path.join(mask_dir, '*.png')))
first_mask = myutils.load_image_in_PIL(self.mask_list[0], 'P')
first_frame = myutils.load_image_in_PIL(self.img_list[0])
self.first_name = os.path.basename(self.img_list[0])[:-4]
first_mask = np.array(first_mask, np.uint8)
self.obj_n = first_mask.max() + 1
self.img_list = self.img_list[1:]
self.video_len = len(self.img_list)
self.to_tensor = TF.ToTensor()
self.to_onehot = mytrans.ToOnehot(self.obj_n, shuffle=False)
first_mask, _ = self.to_onehot(first_mask)
self.first_frame = self.to_tensor(first_frame)
self.first_mask = first_mask[:self.obj_n]
def __init__(self, root, output_size, dataset_file='./assets/pretrain.txt', clip_n=3, max_obj_n=11):
self.root = root
self.clip_n = clip_n
self.output_size = output_size
self.max_obj_n = max_obj_n
self.img_list = list()
self.mask_list = list()
dataset_list = list()
with open(os.path.join(dataset_file), 'r') as lines:
for line in lines:
dataset_name = line.strip()
img_dir = os.path.join(root, 'JPEGImages', dataset_name)
mask_dir = os.path.join(root, 'Annotations', dataset_name)
img_list = sorted(glob(os.path.join(img_dir, '*.jpg'))) + sorted(glob(os.path.join(img_dir, '*.png')))
mask_list = sorted(glob(os.path.join(mask_dir, '*.png')))
if len(img_list) > 0:
if len(img_list) == len(mask_list):
dataset_list.append(dataset_name)
self.img_list += img_list
self.mask_list += mask_list
print(f'\t{dataset_name}: {len(img_list)} imgs.')
else:
print(f'\tPreTrain dataset {dataset_name} has {len(img_list)} imgs and {len(mask_list)} annots. Not match! Skip.')
else:
print(f'\tPreTrain dataset {dataset_name} doesn\'t exist. Skip.')
print(myutils.gct(), f'{len(self.img_list)} imgs are used for PreTrain. They are from {dataset_list}.')
self.random_horizontal_flip = mytrans.RandomHorizontalFlip(0.3)
self.color_jitter = TF.ColorJitter(0.1, 0.1, 0.1, 0.03)
self.random_affine = mytrans.RandomAffine(degrees=20, translate=(0.1, 0.1), scale=(0.9, 1.1), shear=10)
self.random_resize_crop = mytrans.RandomResizedCrop(output_size, (0.8, 1))
self.to_tensor = TF.ToTensor()
self.to_onehot = mytrans.ToOnehot(max_obj_n, shuffle=True)