sovitdc

[sovitdc]

In this deep learning tutorial, learners will use the PyTorch Facenet library to detect faces and facial landmarks.

[sovitdc]

In this article, we will further our discussions on the topic of facial keypoint detection using deep learning. We will learn about some more advanced techniques.

[sovitdc]

In this article, you will get to learn about facial keypoint detection using deep learning and PyTorch. This article will be fully hands-on and practical. We will go through the coding part thoroughly and use a simple dataset for starting out with facial keypoint detection using deep learning PyTorch. This is also known as facial landmark detection.

[sovitdc]

In this tutorial, we will also try to recognize human actions in videos using deep learning and neural networks.

[sovitdc]

We will be detecting road potholes using Faster RCNN deep learning object detector in this tutorial.

[sovitdc]

In this tutorial, we will get hands-on experience with semantic segmentation in deep learning using the PyTorch FCN ResNet models.

[sovitdc]

Image segmentation is one of the most important topics in the field of computer vision. A lot of research, time, and capital is being put into to create more efficient and real time image segmentation algorithms. And deep learning is a great helping hand in this process. In this article, we will take a look the concepts of image segmentation in deep learning.

[sovitdc]

In this article, we will learn how we can reduce distortion in images using the Spatial Transformer Network (STN) using the PyTorch deep learning library.

[sovitdc]

In this tutorial, we will go through the concepts of Spatial Transformer Networks in deep learning and neural networks.

[sovitdc]

In this article, we will use a deep learning object detector to detect objects in images and videos. We will the Faster R-CNN deep learning detector in particular. Faster R-CNN is one of the best object detectors out there in terms of accuracy.

[sovitdc]

In this article, we will learn about the evaluation metrics that are commonly used in object detection. Before moving deep into any object detection project, it is better to have a grasp on these concepts.

[sovitdc]

What will you learn after reading this article?

What is object detection? A basic introduction.

Research papers that we will discuss in this article.

Finally, some new techniques that are worth reading and knowing about.

The RCNN family of object detectors.

The SSD (Single Shot Detection) object detector.

The YOLO (You Only Look Once) family of object detectors.

[sovitdc]

In this tutorial, we will learn about Automatic Mixed Precision Training (AMP) for deep learning using PyTorch.

[sovitdc]

In this tutorial, we will be implementing the Deep Convolutional Generative Adversarial Network architecture (DCGAN).

[sovitdc]

In this tutorial, we will generate the digit images from the MNIST digit dataset using Vanilla GAN. We will use the PyTorch deep learning framework to build and train the Generative Adversarial network.

[sovitdc]

In this article, we will discuss how to get per-class accuracy in a highly imbalanced image/vision dataset.

[sovitdc]

In this article, we will train a ResNet34 deep neural network on the Caltech101 dataset using transfer learning and try to achieve more than 95% test accuracy. The main question is why the Caltech101 dataset for this deep learning tutorial?