Computer Vision
  • Introduction
    • Neural network basics
    • MLE and Cross Entropy
    • Convolution basics
    • Neural Network Categories
  • 2D Backbones
    • ResNet
    • Transformer
      • Recurrent Neural Network
      • Vision Transformer
      • SwinTransformer
  • Methods for Object Detection
  • Object Detection
    • The R-CNN family
    • ROI pool & ROI align
    • FCOS
    • Object Detection in Detectron2
  • Segmentation
    • Fully Convolutional Network
    • Unet: image segmentation
  • Video Understanding
    • I3D: video understanding
    • Slowfast: video recognition
    • ActionFormer: temporal action localization
  • Generative models
    • Autoregressive model
    • Variational Auto-Encoder
    • Generative Adversarial Network
    • Diffusion Models
    • 3D Face Reconstruction
Powered by GitBook
On this page
  1. Introduction

Convolution basics

Convolution Kernels

PreviousMLE and Cross EntropyNextNeural Network Categories

Last updated 1 year ago

  • 1 * 1 convolution layer is used to change the number of channel

  • To transform a feature map from C1C_1C1​ channels to C2C_2C2​ channels, we will need C1∗C2C_1 * C_2C1​∗C2​ kernels

  • Stride, padding, and kernel size determine the width and height of the output feature map :

  • Pooling changes the size of feature map but not the channel number of it.