Data augmentation

In order to improve models without adding new data, we can do data augmentation, this will work well for images that do make sense to make transformations on top of, so for example it is not a good idea to do it for text or numbers because text the orientation of characters in these cases…

Computer vision algorithms

ORB Algorithm: Oriented Fast and Rotated Brief, creates feature vectors from detected keypoints and is invariant to rotations, changes in illumination, and noise. HOG Algorithm: Histogram of Oriented Gradients works by creating histograms of the distribution of gradient orientations in an image and then normalizing them in a very special way. This special normalization is…

100DaysOfMLCode Index

  100DaysOfMLCode Index Attention mechanisms Batch size CNNs Computer Vision Conda Data Augmentation Defining a network structure Downloading Datasets Dropout Embeddings FastAI Filtered Images Facia-Keypoints-Detector notes GPU States High bias & high variance Hyperparameters Image Captioning Project Notes Intro to Pandas Lab Jobs in Computer Vision Layer Shapes Learning Rates Localization LSTM cells Momentum Machine…

GPU

The GPU performance state APIs are used to get and set various performance levels on a per-GPU basis. P-States are GPU active/executing performance capability and power consumption states. P-States range from P0 to P15, with P0 being the highest performance/power state, and P15 being the lowest performance/power state. Each P-State maps to a performance level.…

Batch Size

Batch size refers to the number of training examples utilized in one step or iteration. One step or iteration is one step of gradiend decent (one update of weights and parameters) The batch size can be either: The same number of the total number of samples which makes one step = an epoch, this is called batch…

Localization

Robot localization in essence is based in two main steps: Sense and Move It will start with a initial belief (or prior) of maximum confusion where the probability distribution will be uniform (flat, which means it has the same value everywhere) Then it will start cycling through sensor measurements (Sense) and movements (Move) When the robot moves…