Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
clip-vit-base-patch32_oxford-iiit-pet – AI Model by tanganke | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
tanganke
/
clip-vit-base-patch32_oxford-iiit-pet
like
0
transformers
tensorboard
safetensors
clip_vision_model
feature-extraction
timm/oxford-iiit-pet
openai/clip-vit-base-patch32
finetune
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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
