Model Card
Model Details
- Architecture: ViT-Base with patch size 32
- Training Data: Standford 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: 0.5987
- fine-tuned: 0.7819
Usage
load vision model
from transformers import CLIPVisionModel
vision_model = CLIPVisionModel.from_pretrained('tanganke/clip-vit-base-patch32_stanford-cars')
substitute the vision encoder of clip
from transformers import CLIPModel
clip_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
clip_model.vision_model.load_state_dict(vision_model.vision_model.state_dict())