Repository navigation
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1) #2192
Description
When coco dataset has empty bbox annotation
following error occured.
How should I handle the empty bbox dataset in cocodataset
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)
[{'boxes': tensor([], device='cuda:1'), 'labels': tensor([], device='cuda:1', dtype=torch.int64), 'image_id': tensor([311877], device='cuda:1'), 'area': tensor([], device='cuda:1'), 'iscrowd': tensor([], device='cuda:1', dtype=torch.int64)}]
len_> 0
class CocoDataset(torch.utils.data.Dataset):
def __init__(self, root, annotation, transforms=None):
self.root = root
self.transforms = transforms
self.coco = COCO(annotation)
self.ids = list(sorted(self.coco.imgs.keys()))
def __getitem__(self, index):
# Own coco file
coco = self.coco
# Image ID
img_id = self.ids[index]
# List: get annotation id from coco
ann_ids = coco.getAnnIds(imgIds=img_id)
# Dictionary: target coco_annotation file for an image
coco_annotation = coco.loadAnns(ann_ids)
# path for input image
path = coco.loadImgs(img_id)[0]['file_name']
# open the input image
img = Image.open(os.path.join(self.root, path))
# number of objects in the image
num_objs = len(coco_annotation)
# Bounding boxes for objects
# In coco format, bbox = [xmin, ymin, width, height]
# In pytorch, the input should be [xmin, ymin, xmax, ymax]
boxes = []
for i in range(num_objs):
xmin = coco_annotation[i]['bbox'][0]
ymin = coco_annotation[i]['bbox'][1]
xmax = xmin + coco_annotation[i]['bbox'][2]
ymax = ymin + coco_annotation[i]['bbox'][3]
boxes.append([xmin, ymin, xmax, ymax])
boxes = torch.as_tensor(boxes, dtype=torch.float32)
# Labels (In my case, I only one class: target class or background)
labels = torch.ones((num_objs,), dtype=torch.int64)
# Tensorise img_id
img_id = torch.tensor([img_id])
# Size of bbox (Rectangular)
areas = []
for i in range(num_objs):
areas.append(coco_annotation[i]['area'])
areas = torch.as_tensor(areas, dtype=torch.float32)
# Iscrowd
iscrowd = torch.zeros((num_objs,), dtype=torch.int64)
# Annotation is in dictionary format
my_annotation = {}
my_annotation["boxes"] = boxes
my_annotation["labels"] = labels
my_annotation["image_id"] = img_id
my_annotation["area"] = areas
my_annotation["iscrowd"] = iscrowd
if self.transforms is not None:
img = self.transforms(img)
return img, my_annotation
def resize_boxes(boxes, original_size, new_size):
ratios = tuple(float(s) / float(s_orig) for s, s_orig in zip(new_size, original_size))
ratio_height, ratio_width = ratios
#print("=============================================================")
#print('ratio_height->',ratio_height,'ratio_width->',ratio_width,'boxes->',boxes)
print('len_>',len(boxes))
xmin, ymin, xmax, ymax = boxes.unbind(1)
xmin = xmin * ratio_width
xmax = xmax * ratio_width
ymin = ymin * ratio_height
ymax = ymax * ratio_height
return torch.stack((xmin, ymin, xmax, ymax), dim=1)
Activity
zhangguanheng66 commentedon May 7, 2020
@fmassa Could we add a check to avoid the out of range problem?
fmassa commentedon May 11, 2020
Hi,
This is an issue with your dataset implementation.
When there are no boxes in it, the boxes are expected to be of shape
0 x 4, but instead you have a tensor of shape0.You can fix this by doing
in order to guarantee your boxes will always have two dimensions.
But I agree with @zhangguanheng66 and we could add another check in the model to validate that the inputs have the correct shapes.
fmassa commentedon May 11, 2020
I propose to add a check in
generalized_rcnn.pyfor now, as it is the main entrypoint for those functions.mmcenta commentedon May 11, 2020
Hello, I would like to work on this issue.
fmassa commentedon May 12, 2020
@mmcenta go for it!
hakontonne commentedon Jul 10, 2020
Hello, couldn't this be done more easily than with extensive tests?
I've encountered this issue myself and fixed it locally by changing
in
GeneralizedRCNNTransformtoThis is simple, fixes the issue and is consistent with the actual check for background image in
roi_heads.py:It's the
bbox.numel() == 0that determines if a label is background or not, then as long as a dataset implementation passes this check for background class, it should work? Would it not appropriate that the network is as agnostic to the dataset implementation as possible? If not, shouldn't the documentation be updated to reflect that?I've checked that this works and this would be more consistent with how a background class is determined. The network will then accept empty boxes tensors and boxes tensors of size
0 x 4and is guaranteed to work as it uses the same test asroi_heads.py.fmassa commentedon Jul 10, 2020
@hakontonne the issue with this approach is that we are propagating "unexpected" tensor shapes, which might work in some cases but is prone to failure.
I think it's ok to ask users to format their dataset in a way which is uniform -- providing boxes which are of shape 0 sometimes is not as uniform as if they have always Nx4 shape (with N potentially being 0).
Mrgove10 commentedon Dec 1, 2020
Facing the same issue.
I am folowing the code from this tutorial btw : https://medium.com/fullstackai/how-to-train-an-object-detector-with-your-own-coco-dataset-in-pytorch-319e7090da5
Applying the
fix does lead to better results but makes a second error popup :
datumbox commentedon Dec 2, 2020
@Mrgove10 This is probably fixed by #3031. Could you try on the latest master and let me know if you still get the problem?
Mrgove10 commentedon Dec 4, 2020
@datumbox In the end i switched and went with Detectron2, not planing to retest anytime soon sorry 😞
vadimkantorov commentedon Sep 23, 2021
@fmassa I propose
resize_boxesto usedim=-1instead ofdim=1. This would allow to use this function for user tensors that are not just Bx4 but also B1xB2x4 and will allow more code reuse. I hope this method would go to a shared box_ops/boxes namespace some day (similar to detectron2)