Please enable JavaScript.
Coggle requires JavaScript to display documents.
Transfer Learning for Image Classification, Training a Network, Using Deep…
Transfer Learning for Image Classification
Transfer learning Remove
Softmax Layer
Classification layer
Fully Connected Layer
The Deep network (Feature Extraction)
Predict
Categories
Score
Train the model
Intial Learning rate
Mini batchsize
max Epochs
Hyperparameters
Images / Datasets
Balance dataset
Partition
Datastore
Alot of dataset that
Pretrained Mode
Alexnet
Googlenet
Resnet50
Etc
Different Input Size
Training a Network
Hyper Parameters
Initial learning rate
Scheduled Learning Rate
Fixed Learning Rate
Optimization
Dataset
Training
Validation
Testing
Mini Batch Size
Methods Hyperparamter
Tuning
Randomsearch
Bayesian Optimization
Gridsearch
MATLAB -> EXPERIMENT MANAGER
Tuning XXX number parameters
CN
FC
Other
Plots / Loss Function
Accuracy
Loss
Improve Accuracy
Architecture
Using Deep Learning for Computer Vision
Object Classification
Pixel Sementation
Object Localization
Yolov2 (YOLO)
You Only Look Once
Pretrained Network
Grid
Anchor
Thresholding
Look in Computer Vision
Toolbox Documentation
Image to Image Regression
Labels
Ground Truthlabler
ImageLabeler
Lidar Labeler
VideoLabeler
Signal labeller
LSTM
Sequence -> Forecast (Future)
Sequence -> Sequence
Train from Scratch
Sequence Input Layer
LSTM Layer
State / Memory
Fully Connected Layer
Sequence -> Classification
Classification Layer
Audio Labeller
Interpreting Network behavior
Activations
CN
Normal
FC
Pooling
Relu
more information of interpretability
LIME
visualize each activations
OcclusionSensitivity
Feature Extraction
ALEXNEt
First Layers are feature extraction
FC7 = 1x4096
ML
Tree
Logistics
SVM
Any other ML
Regression
VECTOR
Creating Networks
Land Cover Classification
4 Channel
B
G
NIR
R
28x28
Create/Training NN
Transfer Learning
Labeled data (Image)
Pretrained Network
Replacing the last 3 layer
First layers -> weights / biases are
trained for Feature Extraction
Hyperparameters
Initial learning rate
Minibatch Size
Plot (training progress)
Epochs
Learning Dropout
Solver
Training From Scratch
Architecture
DAG
resnet50
Series
Alexnet
Pretrained
Image for Inference
Trained with Image net
1000 categories
Performing Image Regression
Classification
Regression
Replace
Remove Classification Layer
Replace Regression Layer
Remove Fully Connect Layer
Replace new Fully Connected layer (OUTPUT is considered)
it is not ImageDatastore
but it is in a for of a Table
Image Location
Regression Values
Color Correction
Presets for R
Presets for G
Presets for B
Image Stabilization
Correction Angle
Scoring
RSME
R2 / R2 adjusted
MAE
MAPE
AUTOMATE
As much as Possible