Downloads · 30 days
18.5K
12% of all-time downloads
clip-vit-base-patch32_dtd
tanganke/clip-vit-base-patch32_dtd
clip-vit-base-patch32_dtd is a feature extraction model from tanganke. Use it when you need embeddings to search or compare text. It is set up for transformers.
- Architecture: ViT-Base with patch size 32 - Training Data: DTD dataset
All-time downloads
155K
Public
Parameters
87.5M
350 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors350 MB · 100%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- clip_vision_model
- Access
- Public
- Created
- Apr 28, 2024
- Updated
- Apr 28, 2024
- SHA
- 2ce76d4c
Base models
Datasets
Spaces
Model card
From the Hugging Face model README
Model Card
Model Details
- Architecture: ViT-Base with patch size 32
- Training Data: DTD 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: 0.4388
- fine-tuned: 0.7973
Usage
load vision model
from transformers import CLIPVisionModel
vision_model = CLIPVisionModel.from_pretrained('tanganke/clip-vit-base-patch32_dtd')
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())
- Task
- Feature Extraction
- Library
- transformers
- Type
- clip_vision_model
- Created
- Apr 28, 2024
- Updated
- Apr 28, 2024