Freaks City

Introduction to Functional Automatic Differentiation Automatic differentiation is a core technique in neural network training that enables efficient computation of gradients for optimization. MindSpore implements a functional approach to automatic differentiation through its grad and value_and_grad interfaces, which provide mathematical semanti ...

Introduction to MMDetection MMDetection is an open-source object detection toolbox developed by SenseTime and The Chinese University of Hong Kong. Built on PyTorch, it implements a wide array of object detection algorithms, encapsulating dataset construction, model architecture, and training strategies into modular components. This modular desi ...

Embedding layers serve as fundamental components in neural network architectures that process textual data. These layers transform discrete tokens into continuous vector representations that machines can effectively process. Concept of Token Embedding Token embedding represents the transformation of symbolic text into numerical vectors. This co ...

Understanding Vision Transformers for Image Classification The Vision Transformer (ViT) represents a groundbreaking approach that merges principles from natural language processing with computer vision. This architecture leverages self-attention mechanisms to achieve impressive results in image classification tasks without relying on traditiona ...

Introduction When training deep learning models with Caffe, visualizing the training progress through loss curves is essential for monitoring model convergence. This article presents two practical approaches for generating training visualizations. Method 1: Custom Python Script for Headless Servers The following implementation is specifically d ...

When migrating legacy TensorFlow 1.x code to TensorFlow 2.x, several common attribute errors may occur due to API changes. Below are typical issues and their solutions: 1. module 'tensorflow' has no attribute 'placeholder' tf.placeholder was removed in TensorFlow 2.x. To retain 1.x behavior: import tensorflow.compat.v1 as tf tf.disable_v2_behav ...

1.1 Approach 1: Using os.environ['CUDA_VISIBLE_DEVICES'] import os os.environ['CUDA_VISIBLE_DEVICES'] = '2' model = NeuralNet().cuda() batch = batch.cuda() 1.2 Approach 2: Using torch.device() target_device = torch.device('cuda:2') model = NeuralNet().to(target_device) batch = batch.to(target_device) 1.3 Errer 1: RuntimeError: CUDA error: inv ...

Color adjustment (brightness, saturation, contrast) Random scaling Random cropping PCA-based color augmentation Translation shifting Horizontal/vertical flipping Rotation and affine transformations Gaussian noise additoin Class imbalance correction Implementation Example (NumPy/PIL) from PIL import Image, ImageEnhance import numpy as np impo ...

Chemical Informatics Fundamentals The evolution of artificial intelligence in chemistry involves several stages. Early efforts focused on digitizing chemical knowledge into databases using various representation methods. Mid-stage approaches relied on manual feature engineering to encode existing data, followed by traditional machine learning a ...

Tensor Creaiton and Initialization Basic Tensor Operations import torch # Create tensor from list data_tensor = torch.tensor([1, 2, 3], dtype=torch.float32) # Create tensor with random values (uniform distribution) rand_tensor = torch.rand(2, 3) # Create tensor with normal distribution values normal_tensor = torch.randn(3, 4) # Create tenso ...