Skip to main content

Posts

Showing posts with the label training from scratch vs fine-tuning

Image Classification: Fine-Tune ResNet18 on Kaggle Dataset (PyTorch + Lightning)

Image Classification: Fine-Tuning ResNet-18 on Kaggle's Lions vs Cheetahs Dataset Image classification is a fundamental task in computer vision where the goal is to assign a label or class to an input image. It is widely used in various domains such as medical imaging, autonomous driving, wildlife monitoring, and security. A typical image classification pipeline involves feeding an image into a neural network model, which processes the input and outputs class probabilities corresponding to predefined categories. What is the ImageNet Dataset? ImageNet is one of the most influential datasets in the history of computer vision. It contains over 14 million labeled images across more than 20,000 categories, with a popular subset of 1,000 categories used in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Models trained on ImageNet learn powerful visual features that generalize well to many downstream tasks, making them a popular choice for transfer learning an...