tanganke/clip-vit-large-patch14_resisc45

Model Card

Model Details

• Architecture: ViT-Large with patch size 14
• Training Data: RESISC45 cars 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: 0.7100892066955566
• fine-tuned: 0.9738245606422424