Page Index - HoldenCaulfieldRye/PlantRecog GitHub Wiki

24 page(s) in this GitHub Wiki:

• Home
• Image Recognition With Deep Learning
• Deep Convolutional Neural Nets
• Dimension Hopping
• Replicated Feature Detection
• Our Network's Architecture
• Ideas
• Output layer: softmax, taxon for target values
• Backpropagation Initial Weights: discretely explore error function
• Backpropagation Initial Weights: estimate polynomial order of error function
• Backpropagation Initial Weights: unsupervised pretraining
• Data
• Labelled photos taken by amateurs is the ideal data to look for. Discussion below. NB1: we can't use externally sourced data for the PlantClef competition, so this data would be strictly for the app. NB2: below are my (alexd) opinions, but I may be wrong!
• Amateur Photos
• Labeled Data
• Species Label
• Category Label
• Bounding Box
• Taxon Label
• Location Label
• Other PlantClef Labels
• Professional Wildlife Photos Still Good
• Scientific Scan Images Still Good
• Overview