How to use tanganke/clip-vit-base-patch32_oxford-iiit-pet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="tanganke/clip-vit-base-patch32_oxford-iiit-pet")
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("tanganke/clip-vit-base-patch32_oxford-iiit-pet") model = AutoModel.from_pretrained("tanganke/clip-vit-base-patch32_oxford-iiit-pet", device_map="auto")
Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=128). Only the vision encoder is fine-tuned.
Test set accuracy:
Files info
Base model
