Prediction Using Pre-trained EfficientNet
Explore how to build inference scripts using pre-trained EfficientNet models in PyTorch. Learn about input image preprocessing, running model inference with torch.no_grad, applying softmax to get probabilities, and extracting top predictions using torch.topk. Gain practical understanding of EfficientNet variants and their resolution requirements for image classification tasks.
We'll cover the following...
This lesson will provide a step-by-step guide to building inference scripts using EfficientNet. Moreover, this lesson has multiple interactive playgrounds for you to practice with.
Overview of EfficientNet
EfficientNet is another convolutional neural network architecture that performs well on Imagenet and other image classification tasks. During its initial release in 2019, it was considered a state-of-the-art model.
It’s an efficiency-oriented model that utilizes a scaling method that uniformly scales all dimensions (depth, width, and resolution) using a compound coefficient. Hence, it tends to outperform other architectures without extensive grid search of hyperparameters.
Variant (B0 - B7)
EfficientNet comes with eight different variants, and each one contains ...