| LibreEfficientNetV2 weights | |
| --------------------------- | |
| This product contains weights derived from EfficientNetV2, ported in timm | |
| (PyTorch Image Models, https://github.com/huggingface/pytorch-image-models). | |
| Copyright (c) 2019 Ross Wightman. | |
| Licensed under the Apache License, Version 2.0. | |
| Original architecture: EfficientNetV2 by Google | |
| (https://github.com/google/automl/tree/master/efficientnetv2), | |
| "EfficientNetV2: Smaller Models and Faster Training" | |
| (https://arxiv.org/abs/2104.00298), Apache License 2.0. | |
| These weights are the timm `tf_efficientnetv2_b2.in1k` ImageNet-1k checkpoint | |
| (no ImageNet-21k, no JFT, no extra data). State-dict keys were remapped to the | |
| LibreYOLO native module names; learned parameters are unchanged. | |