EfficientNet
Explore the process of training EfficientNet image classification models with PyTorch. Understand how to select model variants, customize training epochs, and apply advanced data augmentations such as Mixup, Cutmix, AutoAugment, and Augmix to improve model performance effectively.
Supported variants
The PyTorch Image Model supports the following EfficientNet variants:
| Base model | Resolution |
|---|---|
| EfficientNetB0 | 224 |
| EfficientNetB1 | 240 |
| EfficientNetB2 | 260 |
| EfficientNetB3 | 300 |
| EfficientNetB4 | 380 |
EfficientNetB0 is a good start for most use cases. Other variants require higher GPU memory since the base image resolution is higher. ...