I am trying to fine tune a model using doctor handwritings to detect the prescriptions. The problem is the images are skipped because they’re assumed to be CAPTCHAs. But, I believe, this is a valid use case that should be allowed. Is there any way to circumvent this restriction?
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Issue with Too Many Image Skipping During Vision-Fine-Tuning | 2 | 49 | February 24, 2025 | |
Vision Finetuning failure: Too many images were skipped due to moderation | 3 | 187 | October 2, 2024 | |
Vision API - "Image not allowed by our safety system" | 9 | 1467 | May 29, 2024 | |
Fine-tuning fails due to zero examples | 5 | 105 | October 15, 2024 | |
We've added support for vision fine-tuning | 50 | 1765 | January 18, 2025 |