Instructions to use wrice/perch-v2-efficientnet-b3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use wrice/perch-v2-efficientnet-b3 with timm:
import timm model = timm.create_model("hf_hub:wrice/perch-v2-efficientnet-b3", pretrained=True) - Transformers
How to use wrice/perch-v2-efficientnet-b3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="wrice/perch-v2-efficientnet-b3") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("wrice/perch-v2-efficientnet-b3", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architecture": "tf_efficientnet_b3", | |
| "num_classes": 0, | |
| "num_features": 1536, | |
| "model_args": { | |
| "in_chans": 1, | |
| "num_classes": 0, | |
| "bn_eps": 1e-05, | |
| "bn_momentum": 0.01 | |
| }, | |
| "pretrained_cfg": { | |
| "tag": "ns_jft_in1k", | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 300, | |
| 300 | |
| ], | |
| "fixed_input_size": false, | |
| "interpolation": "bicubic", | |
| "crop_pct": 0.904, | |
| "crop_mode": "center", | |
| "mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "num_classes": 1000, | |
| "pool_size": [ | |
| 10, | |
| 10 | |
| ], | |
| "first_conv": "conv_stem", | |
| "classifier": "classifier", | |
| "license": "apache-2.0" | |
| }, | |
| "in_chans": 1, | |
| "bn_eps": 1e-05, | |
| "bn_momentum": 0.01, | |
| "input_size": [ | |
| 1, | |
| 500, | |
| 128 | |
| ], | |
| "mean": [ | |
| 0.0 | |
| ], | |
| "std": [ | |
| 1.0 | |
| ], | |
| "crop_pct": 1.0 | |
| } |