Hasty visionAI Wiki
Website
User documentation
API documentation
Community
Searchโฆ
Getting started
Introduction
Overview of topics
How to contribute
General best practices
Model families ๐พ
Classifier / Taggers
Semantic Segmentor
Object Detector
Instance Segmentor
Attributor
Model architectures ๐
ResNet
Faster R-CNN
Mask R-CNN
DeepLabv3+
U-Net
FBNetV3
U-Net++
PSPNet
Efficient Net
PAN
LinkNet
FPN
RetinaNet
Cascade RCNN
Metrics ๐
Confusion Matrix
IoU (Intersection over Union)
Accuracy
Hamming Score
Precision
Recall
mAP (mean Average Precision)
Average Loss
Loss ๐
Cross-Entropy Loss
Binary Cross-Entropy Loss
Focal Loss
Bounding Box Regression Loss
Solvers / Optimizers ๐งฎ
Epsilon Coefficient
Momentum (SGD)
SGD
ASGD
Adam
AdamW
AdaMax
Adagrad
Rprop
RMSprop
Adadelta
Base Learning Rate
Weight Decay
Schedulers
Warm-Up
CyclicLR
MultiStepLR
StepLR
CosineAnnealingLR
ReduceLROnPlateau
ExponentialLR
Training parameters
Patience
Min delta
Seed
Batch Size
Iterations
Epoch
Augmentations
Horizontal Flip
Vertical Flip
Random Crop
Random Sized Crop
Rotate
Resize
Blur
Smallest max size
Center Crop
Color Jitter
Gaussian Noise
Shift Scale Rotate
Deployment
Primitive deployment using web frameworks
Commonly used web frameworks
Containerized Deployment
Orchestrated Deployment
Challenges of Deployment
Splits
General Information
Random
Stratification
Powered By
GitBook
Random
A type of data split strategy
In this type of split, the input data in randomly assigned to the test, train and validation set according to the given sizes.
The split is done without replacement, which means that the validation, test and training set doesn't contain the same data.
Random split is the simplest split strategy and is effective in most of the cases.
โ
Splits - Previous
General Information
Next - Splits
Stratification
Last modified
10mo ago
Copy link