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)
•
8 items
•
Updated
Model Card
Model Details
- Architecture: ViT-Large with patch size 14
- Training Data: GTSRB 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: 0.4381546676158905
- fine-tuned: 0.9932354688644409
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.