What It Does One-Shot learning can be useful when you want to identify someone just by giving the predicting model a single picture of them. Similarity Function A model can perform One-shot learning by learning a “similarity” function. When the…
The Main 4 Steps There are mainly 4 steps for data preprocessing. Data Quality Assessment Data Cleaning Data Transformation Data Reduction 1. Data Quality Assessment Before jumping into coding, evaluating the overall data quality is essential. Here are several problems…
Overview Model-Based Learning Creates a function F(x) using the given data to predict the output. EX): Support Vector Machines Instance-Based Learning Uses the given data itself as the model. If an input is given, it will look through the current…
Creating Templates Jinja2 is a template engine for Python which can be useful when you want to keep track of model training configuration versions. Here is one way to Implement it by combining them with a YAML file. 1. Create…
Abstract Point Pillar is an architecture proposed for 3D object detection using point clouds as inputs. Architecture The architecture consists of mainly 3 elements. Pillar Feature Net BackBone Detection Head 1. Pillar Feature Net This phase takes the following steps.…
Depth Estimation The main challenges in monocular 3D object detection lie in accurately predicting object depth. CaDDN(Categorical Depth Distribution Network) uses a predicted categorical depth distribution for each pixel to project appropriate depth in 3D space. Approaches There are several…
The 2 Stages There are mainly 2 stages when training a generative model. 1. Perceptual Compression Process of removing high-frequency details Encapsulate data into an abstract representation GANS accomplish this by projecting data from pixel space to a hyperspace called…
Pytorch Profiler can help you detect performance bottlenecks when training/deploying a model Here is one implementation import torch import torchvision.models as models from torch.profiler import profile, record_function, ProfilerActivity model = models.resnet18() inputs = torch.randn(1, 3, 512, 512) with profile(activities=[ProfilerActivity.CPU], record_shapes=True)…
Types Here are some approaches to measure depth by only using RGB images from motion. Optical Expansion Observe how the length of an object changes as the camera moves closer. If the object is close, the length will dramatically change…
Implementation Here is one way you can Fine-tune Vgg16 while adding a batch normalization layer using Keras. 1. Import from keras.applications.vgg16 import VGG16 from keras.optimizers import SGD from keras.layers import Input, Dense, Flatten, BatchNormalization, Activation from keras.models import Sequential from…