ResNet, a simple introduction
Residual networks or ResNets for short have been key elements in the computer vision oriented deep learning community. In this...
Greedy layer-wise training of deep networks, a TensorFlow/Keras example
In the early days of deep learning, people training neural networks continuously ran into issues – the vanishing gradients problem...
Quick and easy GPU & TPU acceleration for PyTorch with HuggingFace Accelerate
Deep learning benefits from Graphical Processing Units (GPUs) and Tensor Processing Units (TPUs) because of the way they handle the...
Easy Object Detection with Python, HuggingFace Transformers and Machine Learning
YOLO! If you’re into machine learning, it’s a term that rings a bell. Indeed, You Only Look Once has been...
How to use Upsample for upsampling with PyTorch
Within computer vision, upsampling is a relatively common practice these days. Whereas Convolutional layers and Pooling layers make inputs smaller,...
StyleGAN, a step-by-step introduction
Generative Adversarial Networks have been the go-to machine learning technique for generative content in the past few years. Seemingly magically...
Cropping layers with PyTorch
Sometimes, you may wish to perform cropping on the input images that you are feeding to your neural network. While...
How to use TensorBoard with PyTorch
When your Deep Learning model is training, you are interested in how well it performs. Often, it’s possible to output...
GANs: an Introduction to Fréchet Inception Distance (FID)
The Frechet Inception Distance or FID is a method for comparing the statistics of two distributions by computing the distance between them....
Introduction to Isotropic architectures in Computer Vision
If you are new to Deep Learning, or have worked with neural networks for some time, it’s likely that you’re...
