Rico贾若童的博客

Deep Learning - Neural Style Transfer

What Conv Net Is Learning

What Do Conv Nets Learn? For the ease of explanation, below I will use an example, where a conv layer has 3 input channels, and 5 output channels. As a recap: this layer has 3 filters, each filter...

Posted by Rico's Nerd Cluster on March 1, 2022

Deep Learning - Face Recognition

Siamese Network, Deep Face

Introduction Face verification (easier) vs face recognition (harder) Face verfifaction takes input image, name and an ID. Then, it ouptuts if the image corresponds to the ID. Face recogniti...

Posted by Rico's Nerd Cluster on February 25, 2022

Deep Learning - Face Recognition Prelude

2D Frontalization, 3D Face Alignment

Introduction DeepFace introduced a 3D alignment step that projects 2D face images into a frontal view [1]. This is called “frontalization”. A very cool 2D->3D problem. A frontal view is a view ...

Posted by Rico's Nerd Cluster on February 23, 2022

Deep Learning - Hands-On UNet Image Segmentation From Scratch

UNet

This article is inspired by this referece The source code of this project can be found here Data Loading When making a dataset, do NOT use jpeg and stick to png instead. Jpeg will compress the d...

Posted by Rico's Nerd Cluster on February 19, 2022

Deep Learning - Hands-On YOLO V1 Transfer Learning

YOLO V1 Theory & Transfer Learning

You Only Look Once (YOLO) V1 The main idea is to divide an image into a 7x7 grid. Each grid will detect the existence of 2 bounding box whose center is within the grid cell and outputs [p_1, bx_1,...

Posted by Rico's Nerd Cluster on February 19, 2022

Deep Learning - Performance Metrics

mean Average Precision (mAP), Precision, Recall, ROC Curve, F1 Score, EMA Weights

GIoU \[\mathrm{GIoU} = \mathrm{IoU} - \frac{\left|\,C \setminus (A \cup B)\,\right|}{\left|\,C\,\right|}\] Area Under Curve Area Under Curve = AUC. True Positives, False Positives, True Negat...

Posted by Rico's Nerd Cluster on February 15, 2022

Deep Learning - Image Segmentation

Encoder-Decoder, Fully-Convolutional Networks (FCN), U-Net

Pre-Requitstes Encoder-Decoder framework Autoencoders (or encoders) and autodecoders (or decoders) were introduced in the late 1980. An autoencoder compresses input data into smaller dimensions, ...

Posted by Rico's Nerd Cluster on February 13, 2022

Deep Learning - Object Detection Notes Part 2

R-CNN

Region Based CNN (R-CNN, Girshick et al. CVPR 2014) Zhihu Regional Proposal is the core of R-CNN. It first uses a segmentation algorithm to find regions with objects, then use these regions as “r...

Posted by Rico's Nerd Cluster on February 13, 2022

Deep Learning - Object Detection Notes Part 1

Convolution Implementation of Sliding Window, OverFeat

Introduction Image classification is given an image, output a class lable of the image Image classification and Object localization is Object Detection. For example, if there are 4 classes, [Pede...

Posted by Rico's Nerd Cluster on February 9, 2022

Deep Learning - Hands-On ResNet Transfer Learning For CIFAR-10 Dataset

Data Normalization, Conv Net Training

ResNet-50 Transfer Learning COMPLETE CODE can be found here Data Loading Please see this blogpost for data loading Model Definition PyTorch Built-In Model 1 2 3 4 model = models.resnet50(weig...

Posted by Rico's Nerd Cluster on February 7, 2022

Rico's Nerd Cluster