A review of the paper that enhances diffusion models using retrieval-based approaches from NLP, achieving high-fidelity image generation with fewer parameters.

Using the Albumentations library for image augmentation in PyTorch, with example pipelines for training and TTA.

Last-minute competition score boosting: test-time augmentation (TTA) with soft voting and half-precision training.

Practical training techniques including AMP, label smoothing, ArcFace loss, class pivot adjustment, and Wandb logging for image classification.

Applying vertical CutMix augmentation for face mask classification to focus patches on facial regions.

CutMix data augmentation in PyTorch: loss computation, accuracy, and F1 score calculation.

Latent variable models explained: variational inference, ELBO, VAE, and adversarial auto-encoders (AAE).

Introduction to generative models: probability distributions, independence assumptions, chain rule, and auto-regressive models.

Practical CNN implementation in PyTorch: add_module, training loops, and batch normalization.

Key CNN architectures from ILSVRC: AlexNet, VGGNet, GoogLeNet, and ResNet, with analysis of receptive fields and 1x1 convolutions.

Convolution fundamentals: stride, padding, parameter counting, and 1x1 convolutions.

CNN fundamentals: convolution operations, kernel mechanics, multi-dimensional convolutions, and backpropagation.