Exposing a sensor to a light – projects points that project to all the sensor – and so all locations on the sensor see light from all the points. Aperture(small hole) – seeing light from only one point(inverted and reduced). How big should the aperture be ? until diffraction happensContinue Reading
During inference, precision in floats is not needed and can be reduced to using 8 bits instead of 32 bits this allows to bin continuous values to discrete ranges, and therefore is known as Quantization. This enables us to increase the bandwith sent (or increase the memory footprint in caseContinue Reading
After training we can optimize a frozen graph or even a dynamic graph by removes training-specific and debug-specific nodes, fusing common operations, and removes code that isn’t used/reached. Code Example from tensorflow.python.tools import optimize_for_inference_lib inputGraph = tf.GraphDef() #read in a frozen model with tf.gfile.Open(‘frozentensorflowModel.pb’, “rb”) as f: data2read = f.read() inputGraph.ParseFromString(data2read) outputGraph = optimize_for_inference_lib.optimize_for_inference(inputGraph, [“inputTensor”], Continue Reading
In prediction/inference mode, variable types are unnecessary, so by freezing the graph we convert all variables in a graph and checkpoint into constants. Also there are structure nodes and operations related to training that we don’t need and can be removed by the freezing process as well. The freezing processContinue Reading
Hidden Markov Model (HMM) is a statistical Markov model in which the system being modeled is assumed to be a Markov process with unobservable (i.e. hidden) states. In simpler Markov models (like a Markov chain), the state is directly visible to the observer, and therefore the state transition probabilities areContinue Reading
Hidden states are the unknowns we try to detect or predict. The Hidden states have a relationship amongst themselves called the transition probabilities. Observations are the evidence variables that we have a priori. Observations and states have a relationship between them called the emission probabilities.Continue Reading
A Markov chain is a stochastic model describing a sequence of possible events in which the probability of each event depends only on the state attained in the previous event. (“memorylessness”)Continue Reading
A variational autoencoder provides a probability distribution for describing an observation/attribute in latent/hidden space.Continue Reading
It can not only process single data points (such as images), but also entire sequences of data (such as speech or video). For example, LSTM is applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition. Unlike standard feedforward neural networks, LSTM has feedback connections that make itContinue Reading
Gradient is a vector that is made up from a the derivatives of multi-variate function. Gradient of an Image = ∇f = [∂f/∂x,∂f/∂y] The gradient of a function is the vector direction/angle of the most rapid increase in Intensity(Getting Brighter), and the magnitude of that vector is how much itContinue Reading