Image Feature Extraction
Transformers
Safetensors
dinov2
dino
vision
image-embeddings
pet-recognition
Instructions to use bcd8697/trial-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bcd8697/trial-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="bcd8697/trial-model")# Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("bcd8697/trial-model") model = AutoModel.from_pretrained("bcd8697/trial-model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Dinov2Model" | |
| ], | |
| "model_type": "dinov2", | |
| "hidden_act": "gelu", | |
| "hidden_size": 384, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "layer_norm_eps": 1e-06, | |
| "num_attention_heads": 6, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 14, | |
| "qkv_bias": true, | |
| "attention_dropout": 0.0 | |
| } |