EfficientNet-B5 is one of the EfficientNet family of models, which are convolutional neural network architecture and scaling methods that uniformly scales all dimensions of depth/width/resolution using a compound coefficient.
| Model | Download | #Params (M) | #FLOPs (B) | Top-1 accuracy (%) | Top-5 accuracy (%) |
|---|---|---|---|---|---|
| EfficientNet-B5 | 119MB | 30 | 9.9 | 83.6 | 96.7 |
- EfficientNet-B5 is from the paper titled EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.
- This pre-train onnx model is converted from a pytorch model, which is from the lukemelas/EfficientNet-PyTorch.
Apache 2.0