DGurgurov's picture
Upload README.md with huggingface_hub
1cdda04 verified
|
raw
history blame
No virus
353 Bytes

CLIP ViT Base Patch32 Fine-tuned on Oxford Pets

This model is a fine-tuned version of OpenAI's CLIP model on the Oxford Pets dataset.

Training Information

  • Model Name: openai/clip-vit-base-patch32
  • Dataset: oxford-pets
  • Training Epochs: 4
  • Batch Size: 256
  • Learning Rate: 3e-6
  • Accuracy: 93.74%

License

[MIT]