Freaks City

Deep learning, a specialized subset of machine learning, utilizes artificial neural networks with multiple layers to model complex patterns in data. This foundational technology powers advancements in computer vision, speech synthesis, and language understanding. Core Components of Neural Networks Neural networks consist of interconnected layer ...

Differences Between Loading Native and RKNN-Converted Models Models developed in frameworks like PyTorch, TensorFlow, or ONNX must be converted into the proprietary RKNN format to leverage Rockchip’s NPU aceleration. The RKNN format is optimized for Rockchip’s neural processing units, enabling efficient execution on embedded platforms such as t ...

This guide walks through the setup of PyTorch across three common environments: Windows (with CUDA), NVIDIA Jetson Nano (JetPack 4.6), and Ubuntu Linux. It covers driver installation, CUDA Toolkit, cuDNN, and final verification. Windows Installation 1.1 Verify or Install NVIDIA Driver The NVIDIA driver acts as the communication bridge betwee ...

PyTorch Extension Framework Fundamentals PyTorch's architecture enables deep customization through two primary extension points. Understanding their distinct capabilities is essential for implementing novel neural network components. nn.Module: Parameterized Component Foundation The nn.Module class serves as the cornerstone for trainable compon ...

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 ...