EfficientNetV2-base-b0 image classifier (1000-class ImageNet-1k), repackaged
for
LibreYOLO. Eval resolution
224px; timm-reported top-1 accuracy ~78.7%.
1from libreyolo import LibreYOLO
2
3model = LibreYOLO("LibreEfficientNetV2b0-cls.pt")
4result = model.predict("image.jpg")[0]
5print(result.probs.top1, result.probs.top1conf)
6print(result.probs.top5)
Derived from the timm checkpoint
tf_efficientnetv2_b0.in1k in
huggingface/pytorch-image-models.
Copyright (c) 2019 Ross Wightman. Licensed under the Apache License 2.0.
Original architecture: EfficientNetV2 by Google
(
google/automl),
"EfficientNetV2: Smaller Models and Faster Training"
(
arXiv: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.
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.
Apache License 2.0. See the
LICENSE and
NOTICE
files in this repository.
