Instructions to use Foxasdf/EfficientNetV2_Small_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Foxasdf/EfficientNetV2_Small_v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Foxasdf/EfficientNetV2_Small_v1") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("Foxasdf/EfficientNetV2_Small_v1") model = AutoModelForImageClassification.from_pretrained("Foxasdf/EfficientNetV2_Small_v1", device_map="auto") - timm
How to use Foxasdf/EfficientNetV2_Small_v1 with timm:
import timm model = timm.create_model("hf_hub:Foxasdf/EfficientNetV2_Small_v1", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "architecture": "tf_efficientnetv2_s", | |
| "architectures": [ | |
| "TimmWrapperForImageClassification" | |
| ], | |
| "do_pooling": true, | |
| "dtype": "float32", | |
| "initializer_range": 0.02, | |
| "label_names": [ | |
| "0", | |
| "1" | |
| ], | |
| "model_args": null, | |
| "model_type": "timm_wrapper", | |
| "num_classes": 2, | |
| "num_features": 1280, | |
| "pretrained_cfg": { | |
| "classifier": "classifier", | |
| "crop_mode": "center", | |
| "crop_pct": 1.0, | |
| "custom_load": false, | |
| "first_conv": "conv_stem", | |
| "fixed_input_size": false, | |
| "input_size": [ | |
| 3, | |
| 300, | |
| 300 | |
| ], | |
| "interpolation": "bicubic", | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "pool_size": [ | |
| 10, | |
| 10 | |
| ], | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "tag": "in21k", | |
| "test_input_size": [ | |
| 3, | |
| 384, | |
| 384 | |
| ] | |
| }, | |
| "problem_type": "single_label_classification", | |
| "transformers_version": "5.2.0", | |
| "use_cache": false | |
| } | |