Hugging Face's logo

tanganke
/
clip-vit-base-patch32_oxford-iiit-pet

Feature Extraction
Transformers
TensorBoard
Safetensors
clip_vision_model
Inference Endpoints
Model card Files Metrics Community

Model Card

Training Details

Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=128). Only the vision encoder is fine-tuned.

alt text

Evaluation Results

Test set accuracy:

  • pre-trained: 0.8331970572471619
  • fine-tuned: 0.9245026111602783
Downloads last month
677
Safetensors
Model size
87.5M params
Tensor type
F32
·
Inference Providers NEW
Feature Extraction
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for tanganke/clip-vit-base-patch32_oxford-iiit-pet

Base model

openai/clip-vit-base-patch32
Finetuned
(56)
this model

Dataset used to train tanganke/clip-vit-base-patch32_oxford-iiit-pet