We deliver AI algorithm tutorials and the latest news, curated by a team of researchers from Peking University, Shanghai Jiao Tong University, Central South University, and leading AI companies such as Huawei, Kuaishou, and SenseTime. Join us in the AI alchemy—making life better!
This article walks through a complete PyTorch implementation of the SRCNN model for image super‑resolution, covering dataset preparation, patch extraction, model architecture, training on a GTX 770 GPU for 2500 epochs, PSNR evaluation, and visual comparisons with bicubic up‑sampling.
This article walks through building and analyzing a minimal GAN—PointGAN—that learns to output the single value 1, covering the linear generator, a two‑layer discriminator, training loops, loss visualizations, instability diagnostics, and practical fixes such as loss easing, weighted examples, weight decay, and noisy generator parameters.
This article reviews the seminal SRCNN paper, detailing its contributions, architecture, training pipeline, hyper‑parameters, and extensive experiments that show how a shallow fully‑convolutional network achieves superior PSNR and runtime compared to traditional sparse‑coding and bicubic methods.
This article explains how to construct an image duplicate and near‑duplicate detection system, compares five similarity methods (Euclidean distance, SSIM, image hashing, cosine similarity, and CNN‑based feature similarity), provides Python implementations, evaluates them on two datasets, and discusses speed, accuracy, and robustness results.
This article explains how to train a convolutional neural network on a remote GPU for image classification, covering convolution, padding, activation, pooling, dropout, flattening, fully‑connected layers, dataset preparation, model definition, training, and prediction using TensorFlow/Keras.
This article explains the fundamentals of denoising diffusion probabilistic models, detailing the forward Gaussian noise injection, the reverse reconstruction via learned conditional densities, model architecture, loss functions, and experimental results on synthetic datasets, all supported by key research citations.
The article explains CNN inference optimization by applying PyTorch quantization and module‑fusion techniques, compares model size and latency before and after quantization, shows code for building, quantizing, and fusing a simple CNN, and presents benchmark results on CPU, highlighting a four‑fold size reduction and up to 1.7× speed‑up.
This article explains the collaborative denoising autoencoder (CDAE) for recommendation, walks through data preparation with MovieLens, shows a full PyTorch Lightning implementation, tunes hyper‑parameters using Ray Tune and CometML, and reports detailed evaluation metrics.
This article explains an end‑to‑end semi‑supervised training pipeline for Transformer‑based NLP models, detailing the unsupervised language‑model pre‑training, supervised fine‑tuning, and the internal architecture of embeddings, encoder layers, and downstream tasks such as text classification and NER.
This article walks through the core PyTorch visualization utilities—making image grids, drawing bounding boxes, segmentation masks, and keypoints—explaining why they are needed, how to set up the pipeline, and providing complete code examples for each computer‑vision task.
