def get_coco(root, image_set, transforms, mode="instances"):
anno_file_template = "{}_{}2017.json"
PATHS = {
"train": (
"train2017",
os.path.join("annotations",
anno_file_template.format(mode, "train")),
),
"val": (
"val2017",
os.path.join("annotations", anno_file_template.format(mode,
"val")),
),
# "train": ("val2017", os.path.join("annotations", anno_file_template.format(mode, "val")))
}
t = [ConvertCocoPolysToMask()]
if transforms is not None:
t.append(transforms)
transforms = T.Compose(t)
img_folder, ann_file = PATHS[image_set]
img_folder = os.path.join(root, img_folder)
ann_file = os.path.join(root, ann_file)
dataset = CocoDetection(img_folder, ann_file, transforms=transforms)
if image_set == "train":
dataset = _coco_remove_images_without_annotations(dataset)
# dataset = torch.utils.data.Subset(dataset, [i for i in range(500)])
return dataset
def get_transform_2(train):
transforms = [T.ToTensor()]
if train:
transforms = [
# transforms on PIL.Image
T.TransformsCOCO('ColorJitter',
brightness=0.4,
contrast=.4,
saturation=.4),
T.RandomCropCOCOSimple(scale=(0.6, 1.3)),
# to tensor
T.ToTensor(),
# transforms on Tensor
T.RandomApplyCOCO([T.LightingCOCO(0.1)], 0.3),
T.RandomHorizontalFlip(0.5)
]
return T.Compose(transforms)
def get_transform(train):
transforms = [T.ToTensor()]
if train:
transforms.append(T.RandomHorizontalFlip(0.5))
return T.Compose(transforms)