Segment Anything Model
Collection
This collection contains models and demos of SAM and it's smaller friends. • 17 items • Updated • 7
# Load model directly
from transformers import AutoProcessor, AutoModelForMaskGeneration
processor = AutoProcessor.from_pretrained("merve/sam-finetuned")
model = AutoModelForMaskGeneration.from_pretrained("merve/sam-finetuned")Quick Links
sam-finetuned
Model description
This model is a fine-tuned version of facebook/sam-vit-base on an breast cancer dataset. It is not trained for production but for Keras example.
Training procedure
Training hyperparameters
The model was trained for 20 epochs. The following hyperparameters were used during training:
- optimizer: None
- training_precision: float32
Training results
You can see an example inference below.
Framework versions
- Transformers 4.31.0.dev0
- TensorFlow 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for merve/sam-finetuned
Base model
facebook/sam-vit-base
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("mask-generation", model="merve/sam-finetuned")