CLIP-ViT-L/14 on the eight image classification tasks
Collection
if you find these models helpful, consider citing [our paper](https://arxiv.org/abs/2406.03280) • 9 items • Updated
Model Card
Model Details
- Architecture: ViT-Large with patch size 14
- Training Data: DTD dataset
Training Details
Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=32). Only the vision encoder is fine-tuned.
Evaluation Results
- pre-trained: 0.554787278175354
- fine-tuned: 0.8547872304916382
- Downloads last month
- 932
Model tree for tanganke/clip-vit-large-patch14_dtd
Base model
openai/clip-vit-large-patch14