Custom Model Upload from Colab Failed

[smile04455660]

I created a dataset, annotated the image, and trained a yolov8 object detection model using Colab. I stored the train folder and model in my Google drive. When I tried uploading the model using Colab, it seemed the deployment successed.
However, it shows ‘Model Upload Failed’ in the versions tab.

I tried generating a new version and reupload with a lateset version of ultralytics, but it didn’t help.

[Lenny]

I’m sorry to hear that you’re having trouble uploading your model to Roboflow. Based on the information provided in the extracts, there could be a few reasons why this is happening.

Firstly, ensure that you’re following the correct steps to upload your model. According to the Roboflow blog, you should use the following line of code to upload your weights to Roboflow:

project.version(DATASET_VERSION).deploy(model_type="yolov8", model_path=f"{HOME}/runs/detect/train/")

Replace DATASET_VERSION with the version number associated with your project. The DATASET_VERSION number is stored in the dataset.version value. Also, ensure that the model_path correctly points to the location of your model in your Google Drive.

If you’re still encountering issues, it might be helpful to check the console for any error messages. As mentioned in a forum post, one user experienced a similar issue and found an error in the browser console.

If the problem persists, it could be due to a temporary issue with Roboflow’s model upload feature. In a forum post, a user reported a similar issue and a support agent suggested trying to upload the model again. In another case, the issue was resolved after Roboflow pushed a fix for newer v8 models.

If none of these suggestions work, I recommend reaching out to Roboflow’s support team directly for further assistance.

---

Hi! I’m Roboflow’s AI powered bot. This is an automated response powered using AI with knowledge from our docs, blog, and forum. If this solves your issue, please mark it as the solution using the checkbox icon. If this doesn’t solve your issue, please follow up with what you’ve tried/why, and the community will continue to chime in as usual.