Issue regarding: "cannot identify image file '/content/drive/MyDrive/Data/test/images/00705.jpg'"

[MHassanlatif]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Hi everyone
I am facing some problem regarding the inference model every time when i run the inference on my data it provides the error that the model didn't identify the image can anyone guide me regarding this @glenn-jocher.

Here is the code which i used:
"import torch
from pathlib import Path
import cv2
from google.colab import drive
drive.mount('/content/drive')

weight_path = '/content/drive/MyDrive/Data/runs/train/exp_100_epoch/weights/best.pt'

Load the custom YOLOv5 model

model = torch.hub.load('ultralytics/yolov5', 'custom', path=weight_path)
img = "/content/drive/MyDrive/Data/test/images/00705.jpg" # or file, Path, PIL, OpenCV, numpy, list
results = model(img)
results.print()"

And the error which i get here:
"Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).
Using cache found in /root/.cache/torch/hub/ultralytics_yolov5_master
YOLOv5 🚀 2024-9-16 Python-3.10.12 torch-2.4.0+cu121 CPU

Fusing layers...
YOLOv5n6 summary: 206 layers, 3096916 parameters, 0 gradients, 4.2 GFLOPs
Adding AutoShape...

UnidentifiedImageError Traceback (most recent call last)
in <cell line: 49>()
47
48 # Inference
---> 49 results = model(img)
50
51 # Results

4 frames
/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py in _wrapped_call_impl(self, *args, **kwargs)
1551 return self._compiled_call_impl(*args, **kwargs) # type: ignore[misc]
1552 else:
-> 1553 return self._call_impl(*args, **kwargs)
1554
1555 def _call_impl(self, *args, **kwargs):

/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py in _call_impl(self, *args, **kwargs)
1560 or _global_backward_pre_hooks or _global_backward_hooks
1561 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1562 return forward_call(*args, **kwargs)
1563
1564 try:

/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py in decorate_context(*args, **kwargs)
114 def decorate_context(*args, **kwargs):
115 with ctx_factory():
--> 116 return func(*args, **kwargs)
117
118 return decorate_context

~/.cache/torch/hub/ultralytics_yolov5_master/models/common.py in forward(self, ims, size, augment, profile)
872 f = f"image{i}" # filename
873 if isinstance(im, (str, Path)): # filename or uri
--> 874 im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith("http") else im), im
875 im = np.asarray(exif_transpose(im))
876 elif isinstance(im, Image.Image): # PIL Image

/usr/local/lib/python3.10/dist-packages/PIL/Image.py in open(fp, mode, formats)
3281 raise TypeError(msg) from e
3282 else:
-> 3283 rawmode = mode
3284 if mode in ["1", "L", "I", "P", "F"]:
3285 ndmax = 2

UnidentifiedImageError: cannot identify image file '/content/drive/MyDrive/Data/test/images/00705.jpg'"

Additional

No response

[UltralyticsAssistant]

👋 Hello @MHassanlatif, thank you for reaching out about your issue with YOLOv5 🚀! This is an automated response to get you started, and an Ultralytics engineer will assist you soon.

It seems you're encountering an UnidentifiedImageError when running inference. To help us debug this 🚀🐛, please ensure you provide a minimum reproducible example. Verify that the image file path is correct and that the file is not corrupted or in an incompatible format.

In the meantime, you might find the following resources helpful:

• Check our ⭐️ Tutorials to ensure your setup and commands align with the recommended practices.
• Review our Custom Data Training guide if you're using custom datasets.
• Double-check your Python and PyTorch versions against our Requirements.

To get started with YOLOv5:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 can be run in various environments:

• Notebooks: Try it in Colab, Kaggle, or Paperspace.
• Cloud: Explore GCP and AWS quickstart guides.
• Docker: Refer to our Docker Quickstart Guide.

New Feature

Explore YOLOv8 for state-of-the-art object detection 🚀:

pip install ultralytics

Please let us know if you have any more information or questions. A team member will be with you shortly to provide further assistance. 😊

[MHassanlatif]

I tried these things again and again but i get the same problem.

[glenn-jocher]

@MHassanlatif please ensure your image file is not corrupted and is in a supported format. You might also try opening the image with a different tool to verify its integrity. If the issue persists, consider updating to the latest YOLOv5 version and re-testing.

[MHassanlatif]

@glenn-jocher Yeah i already sorted out this problem yesterday and the problem was that the images are corrupted.

[glenn-jocher]

Great to hear you resolved the issue. If you have any more questions or need further assistance, feel free to ask.