Hands-on Computer Vision with PyTorch 1.x: Implement state-of-the art CV models in modern Pytorch

Hands-on Computer Vision with PyTorch 1.x: Implement state-of-the art CV models in modern Pytorch
Hands-on Computer Vision with PyTorch 1.x: Implement state-of-the art CV models in modern Pytorch
English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 2h 57m | 1.57 MB

Provide computer vision and build systems that rival human sight. Designed for beginners to computer vision or PyTorch.

PyTorch is powerful and simple to use. This course will help you leverage the power of PyTorch to perform image processing. Beginning with an introduction to image processing, the course introduces you to basic deep-learning and optimization concepts. Next, you’ll learn to use PyTorch’s APIs such as the dynamic graph computation tensor, which can be used for image classification. Starting off with basic 2D images, the course gradually takes you through recognizing more complex images, color, shapes, and more.

Using the Python API, you’ll move on to classifying and training your model to identify more complex images—for example, recognizing plant species better than humans. Then you’ll delve into AlexNet, ResNet, VGG-net, Generative Adversarial Networks(GANs), neural style transfer, and more–—all by taking advantage of PyTorch’s Deep Neural Networks.

Taking this course is your one-stop, hands-on guide to applying computer vision to your projects using PyTorch. You’ll create and deploy your own models, and gain the necessary intuition to work on real-world projects.

Please note that a understanding of calculus and linear algebra, along with some experience using Python, are assumed for taking this course.

Learn

  • Go from a beginner in the field of computer vision to an advanced practitioner with real-world insights
  • Take advantage of PyTorch’s functionalities such as tensors, dynamic graphs, auto-differentiation, and more
  • Explore various computer-vision sub-topics, such as Conv nets, ResNets, Neural Style Transfer, data augmentation, and more
  • Build state-of-the-art, industrial image classification algorithms
  • Effortlessly split, augment, and draw conclusions from datasets
  • Extract information effortlessly from groundbreaking research papers