UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7fd42c66d3b0> - machine-learning

Question

I am trying to do an object detection problem and been working with aquarium dataset from roboflow. I have been trying to create a bounding box for the fishes, but I have getting the error:
UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7fd42c66d3b0>
I also tried to see what images are corrupted and ran a code
import PIL
from pathlib import Path
from PIL import UnidentifiedImageError
count = 0
path = Path("/content/drive/MyDrive/archive/Aquarium Combined").rglob("*.jpg")
for img_p in path:
try:
img = PIL.Image.open(img_p)
except PIL.UnidentifiedImageError:
print(img_p)
count +=1
print(count)
It has given me a count of 651 images, but my dataset has 662 images. I guess PIL doesn't know how to decode it or I don't know what the problem is. I will attach a sample image file name
/content/drive/MyDrive/archive/Aquarium Combined/test/IMG_2301_jpeg_jpg.rf.2c19ae5efbd1f8611b5578125f001695.jpg
Full traceback:
UnidentifiedImageError Traceback (most recent call last)
<ipython-input-31-2785d562a97e> in <module>()
4 sample[1]['boxes'][:, [1, 0, 3, 2]],
5 [classes[i] for i in sample[1]['labels']],
----> 6 width=4).permute(1, 2, 0)
7 )
3 frames
/usr/local/lib/python3.7/dist-packages/PIL/Image.py in open(fp, mode)
2894 if mode == "P":
2895 from . import ImagePalette
-> 2896
2897 im.palette = ImagePalette.ImagePalette("RGB", im.im.getpalette("RGB"))
2898 im.readonly = 1
UnidentifiedImageError: cannot identify image file <_io.BytesIO object at 0x7fd42c66d3b0>
Also I am providing the class functions"
class AquariumDetection(datasets.VisionDataset):
def __init__(
self,
root: str,
split = "train",
transform= None,
target_transform = None,
transforms = None,
) -> None:
super().__init__(root, transforms, transform, target_transform)
self.split = split
self.coco = COCO(os.path.join(root, split, "_annotations.coco.json"))
self.ids = list(sorted(self.coco.imgs.keys()))
self.ids = [id for id in self.ids if (len(self._load_target(id)) > 0)]
def _load_image(self, id: int) -> Image.Image:
path = self.coco.loadImgs(id)[0]["file_name"]
image = cv2.imread(os.path.join(self.root, self.split, path))
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
return image
def _load_target(self, id: int):
return self.coco.loadAnns(self.coco.getAnnIds(id))
def __getitem__(self, index: int):
id = self.ids[index]
image = self._load_image(id)
target = copy.deepcopy(self._load_target(id))
boxes = [t['bbox'] + [t['category_id']] for t in target]
if self.transforms is not None:
transformed = self.transforms(image=image, bboxes=boxes)
image = transformed['image']
boxes = transformed['bboxes']
new_boxes = []
for box in boxes:
xmin = box[0]
ymin = box[1]
xmax = xmin + box[2]
ymax = ymin + box[3]
new_boxes.append([ymin, xmin, ymax, xmax])
boxes = torch.tensor(new_boxes, dtype=torch.float32)
_, h, w = image.shape
targ = {}
targ["boxes"] = boxes
targ["labels"] = torch.tensor([t["category_id"] for t in target], dtype=torch.int64)
targ["image_id"] = torch.tensor([t["image_id"] for t in target])
targ["area"] = (boxes[:, 3] - boxes[:, 1]) * (boxes[:, 2] - boxes[:, 0])
targ["iscrowd"] = torch.tensor([t["iscrowd"] for t in target], dtype=torch.int64)
targ["img_scale"] = torch.tensor([1.0])
targ['img_size'] = (h, w)
image = image.div(255)
normalize = T.Compose([T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
return normalize(image), targ, index
def __len__(self) -> int:
return len(self.ids)