Synopsis: Deploy a trained ConvNeXt-B model instance on TorchServe for realtime image classification using the categories present in the Food 101 dataset. TorchServe is a framework for serving pyTorch trained models in a seamless, performant manner. In this tutorial, we will walk though the steps for deploying a PyTorch model…

Synopsis: Image classification with ResNet, ConvNeXt along with data augmentation techniques on the Food 101 dataset A quick walk-through on using CNN models for image classification and fine tune them for better accuracy. Dataset used: Food 101 Libraries used: pytorch, torchvision, cudatoolkit, tensorboard Preprocessing…

In this tutorial, we will see how to leverage multiple GPUs in a distributed manner on a single machine. We will be using the Distributed Data-Parallel feature of pytorch. Libraries Used: python 3.8, pytorch 11, CUDA 11.4 We chose to use DistributedDataParallel instead of the DataParallel, as the DDP is…