Instructions to use timm/maxvit_tiny_tf_384.in1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/maxvit_tiny_tf_384.in1k with timm:
import timm model = timm.create_model("hf_hub:timm/maxvit_tiny_tf_384.in1k", pretrained=True) - Transformers
How to use timm/maxvit_tiny_tf_384.in1k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/maxvit_tiny_tf_384.in1k") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/maxvit_tiny_tf_384.in1k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architecture": "maxvit_tiny_tf_384", | |
| "num_classes": 1000, | |
| "num_features": 512, | |
| "global_pool": "avg", | |
| "pretrained_cfg": { | |
| "tag": "in1k", | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 384, | |
| 384 | |
| ], | |
| "fixed_input_size": true, | |
| "interpolation": "bicubic", | |
| "crop_pct": 1.0, | |
| "crop_mode": "squash", | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "num_classes": 1000, | |
| "pool_size": [ | |
| 12, | |
| 12 | |
| ], | |
| "first_conv": "stem.conv1", | |
| "classifier": "head.fc" | |
| } | |
| } |