Freaks City

Steps Below we introduce fine‑tuning, a common technique in transfer learning. As illustrated in the following diagram, fine‑tuning consists of four steps. Pre‑train a neural network model (the source model) on a source dataset, e.g., ImageNet. Create a new neural network (the target model). It replicates all model design and parameters from t ...

1. Dataset Acquisition Concrete surface cracks are a primary defect in civil structures. Building inspection is performed to evaluate stiffness and tensile strangth. Crack detection plays a vital role in building health assessment. The dataset contains images of various concrete surfaces with and without cracks. The image data is divided into t ...

Training large-scale neural networks often exceeds the computational and memory capacity of a single device, neecssitating distributed training strategies. Among these, model parallelism (MP) plays a crucial role by partitioning the model itself across multiple devices. Within MP, pipeline parallelism (PP) stands out as an effective technique t ...

Version Checking # Check CUDA version (Command Prompt) nvcc -V or nvcc --version # Check Python version (Command Prompt) python # Check available CUDA versions (Command Prompt) nvidia-smi # CUDA Version is displayed after this text Installation Process 1. Visual Studio Installation Version Selection: For CUDA 11.8.0 (can be higher th ...

Convolution is a foundational operation in deep learning—especially in computer vision—where it enables hierarchical feature extraction through localized, parameter-shared transformations. Unlike general matrix multiplication, convolution exploits spatial locality and translation invariance, making it both computationally efficient and semantic ...

Modern deep-learning stacks rely on a computation graph to represent a neural network as a directed acyclic graph (DAG) whose nodes are tensor operations and whose edges carry multi-dimensional arrays (tensors). This abstraction allows the framework to reason about the entire model ahead of time, insert missing backward operations, schedule ker ...

Text matching aims to determine whether two input sequences are semantical related or similar. This is commonly used in applications like question answering, duplicate dteection, and information retrieval. A typical approach involves encoding each sentence independently using recurrent neural networks such as LSTM, then comparing their final re ...

Data Preparation The dataset originates from a Kaggle competition involving store item demand forecasting. It contains 5 years of sales data (2013-2017) for 50 items across 10 stores, requiring predictions for the next 3 months (January-March 2018). This represents a multi-step multivariate time series problem with 500 distinct time series to f ...

Introduction to Handwritten Digit Classification Classifying handwritten numerals represents a foundational challenge in computer vision. This guide demonstrates implementing a Convolutional Neural Network (CNN) to solve this task using the PyTorch framework. By leveraging the MNIST dataset, we construct a specific architecture to process image ...

Why Move to Code The previous discussion focused on the mathematical modeling behind neural networks. However, theory alone is insufficient without practical implementation. This article shifts the perspective to a code-first approach, translating mathematical concepts into executable PyTorch scripts. Implementation Strategy Following a style s ...