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(train):
transforms = []
transforms.append(T.ToTensor())
if train:
# Augmentations go here... Won't do any for now
pass
# transforms.append(T.RandomHorizontalFlip(0.5))
return T.Compose(transforms)
def get_transform(train):
transforms = []
transforms.append(T.ToTensor())
if train:
transforms.append(T.RandomHorizontalFlip(0.5))
# 注意：这里将`.ToTensor()`放到`.RandomHorizontalFlip()`前
# 会导致报错 `TypeError: img should be PIL Image. Got <class `torch.Tensor`>`
return T.Compose(transforms)
def get_transform(train):
transforms = []
# converts the image, a PIL image, into a PyTorch Tensor
transforms.append(T.ToTensor())
if train:
# during training, randomly flip the training images
# and ground-truth for data augmentation
transforms.append(T.RandomHorizontalFlip(0.5))
return T.Compose(transforms)
boxes = np.zeros([mask.shape[-1], 4], dtype=np.int32)
for i in range(mask.shape[-1]):
m = mask[:, :, i]
# Bounding box.
horizontal_indicies = np.where(np.any(m, axis=0))[0]
vertical_indicies = np.where(np.any(m, axis=1))[0]
if horizontal_indicies.shape[0]:
x1, x2 = horizontal_indicies[[0, -1]]
y1, y2 = vertical_indicies[[0, -1]]
# x2 and y2 should not be part of the box. Increment by 1.
x2 += 1
y2 += 1
else:
# No mask for this instance. Might happen due to
# resizing or cropping. Set bbox to zeros
x1, x2, y1, y2 = 0, 0, 0, 0
# boxes[i] = np.array([y1, x1, y2, x2])
boxes[i] = np.array([x1, y1, x2, y2])
return boxes.astype(np.int32, copy=False)
if __name__ == "__main__":
dataset = PennFudanDataset(root='./data-ins/train/',
transforms=T.Compose([T.ToTensor()]))
loader = DataLoader(dataset, batch_size=16, shuffle=False, num_workers=0)
for i, image, label in enumerate(loader):
print(image.shape)
def get_transform(train):
transforms = []
transforms.append(T.ToTensor())
if train:
transforms.append(T.RandomHorizontalFlip(0.5))
return T.Compose(transforms)
def get_transform(train):
transforms = []
transforms.append(T.ToTensor())
# transforms.append(T.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)))
return T.Compose(transforms)