Author Archives: Dr. Vaibhav Kumar - Page 2

10 Jul

Hands-On Guide To Detect Objects In Video In 5 Steps

image-13931
image-13931

In this article, we will show how to detect objects seen in the videos in only 5 steps. We will use the pixellib library in this task which detects objects using instance segmentation. We will also use the pre-trained Mask R-CNN model to identify the objects seen in the videos. In this implementation, we will detect vehicle objects in traffic video.

The post Hands-On Guide To Detect Objects In Video In 5 Steps appeared first on Analytics India Magazine.

08 Jul

Hands-On Guide to Implement Deep Autoencoder in PyTorch for Image Reconstruction

image-13868
image-13868

In this article, we will demonstrate the implementation of a Deep Autoencoder in PyTorch for reconstructing images. This deep learning model will be trained on the MNIST handwritten digits and it will reconstruct the digit images after learning the representation of the input images. 

The post Hands-On Guide to Implement Deep Autoencoder in PyTorch for Image Reconstruction appeared first on Analytics India Magazine.

06 Jul

Hands-On Guide to Implement ResNet50 in PyTorch with TPU

image-13801
image-13801

In this article, we will demonstrate the implementation of ResNet50, a Deep Convolutional Neural Network, in PyTorch with TPU. The model will be trained and tested in the PyTorch/XLA environment in the task of classifying the CIFAR10 dataset. We will also check the time consumed in training this model in 50 epochs.

The post Hands-On Guide to Implement ResNet50 in PyTorch with TPU appeared first on Analytics India Magazine.

01 Jul

Multi-Class Text Classification in PyTorch using TorchText

image-13687
image-13687

In this article, we will demonstrate the multi-class text classification using TorchText that is a powerful Natural Language Processing library in PyTorch. For this classification, a model will be used that is composed of the EmbeddingBag layer and linear layer. The EmbeddingBag deals with the text entries with varying length by computing the mean value of the bag of embeddings. This model will be trained on the DBpedia dataset with texts belonging to the 14 classes. After successful training, the model will predict the class label for the input text. 

The post Multi-Class Text Classification in PyTorch using TorchText appeared first on Analytics India Magazine.

30 Jun

Name Language Prediction using Recurrent Neural Network in PyTorch

image-13665
image-13665

In this article, we will demonstrate the implementation of a Recurrent Neural Network (RNN) using PyTorch in the task of multi-class text classification. This RNN model will be trained on the names of the person belonging to 18 language classes. After successful training, the model will predict the language category for a given name that it is most likely to belong. 

The post Name Language Prediction using Recurrent Neural Network in PyTorch appeared first on Analytics India Magazine.

29 Jun

How To Implement CNN Model Using PyTorch With TPU

image-13619
image-13619

This article demonstrates how we can implement a Deep Learning model using PyTorch with TPU to accelerate the training process. Here, we define a Convolutional Neural Network (CNN) model using PyTorch and train this model in the PyTorch/XLA environment. XLA connects the CNN model with the Google Cloud TPU (Tensor Processing Unit) in the distributed multiprocessing environment. In this implementation, 8 TPU cores are used to create a multiprocessing environment.

The post How To Implement CNN Model Using PyTorch With TPU appeared first on Analytics India Magazine.