LibreEfficientNetV2b3 Cls

--- license: apache-2.0 library_name: libreyolo pipeline_tag: image-classification datasets: - imagenet-1k tags: - image-classification - efficientnetv2 - libreyolo --- # LibreEfficientNetV2b3-cls EfficientNetV2-base-b3 image classifier (1000-class ImageNet-1k), repackaged for [LibreYOLO](https://github.com/LibreYOLO/libreyolo). Eval resolution 300px; timm-reported top-1 accuracy ~82.1%. ## Usage ```python from libreyolo import LibreYOLO model = LibreYOLO("LibreEfficientNetV2b3-cls.pt") result = model.predict("image.jpg")[0] print(result.probs.top1, result.probs.top1conf) print(result.probs.top5) ``` ## Source Derived from the timm checkpoint [`tf_efficientnetv2_b3.in1k`](https://huggingface.co/timm/tf_efficientnetv2_b3.in1k) in [huggingface/pytorch-image-models](https://github.com/huggingface/pytorch-image-models). Copyright (c) 2019 Ross Wightman. Licensed under the Apache License 2.0. Original architecture: EfficientNetV2 by Google ([google/automl](https://github.com/google/automl/tree/master/efficientnetv2)), "EfficientNetV2: Smaller Models and Faster Training" ([arXiv:2104.00298](https://arxiv.org/abs/2104.00298)), Apache License 2.0. Only the ImageNet-1k checkpoint is published here — the ImageNet-21k / JFT variants carry extra-data terms and are intentionally excluded. ## Modifications State-dict key remapping only. Learned parameters are unchanged; inference is bit-identical to timm (`max_abs_diff == 0`). See `weights/convert_efficientnetv2_weights.py` in the [LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo). ## License Apache License 2.0. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE) files in this repository.

Source context: 0 downloads · 0 likes · Pipeline image-classification · Library libreyolo · Repo LibreYOLO/LibreEfficientNetV2b3-cls