How to determine the strain gauge strain gauge histogram?

Question

I would like to know how to understand the tensor flow graphs / Histograms Created. The code for this can be found here. This graph is easy to understand. Accuracy and loss are understandable.

Accuracy- Accuracy of current state of network for given train data. Higher is better Accuracy/Validation - Accuracy of current state of network for given Validation data which is not seen by network before. Higher is better Loss- Loss of network on train data. Lower is better. Loss/Valadation - Loss of network on test data. Lower is better. If loss increases it a sign of over-fitting. Conv2d/L2-Loss - Loss of particular layer wrt train data. 

Basically, what does a graph mean, and how can I use it to understand my network, and, if possible, what changes can I make to improve it.

How to interpret the histograms?

Answer 1

tf.summary.histogram takes an arbitrary dimensional and shaped tensor and compresses it into a histogram data structure consisting of many bunkers with a width and number of samples. For example, suppose we want to arrange the numbers [0.5, 1.1, 1.3, 2.2, 2.9, 2.99] in boxes. We could make three bunkers: a box containing everything from 0 to 1 (it will contain one element, 0.5), a bunker containing everything from 1-2 (it will contain two elements: 1.1 and 1.3), * cell containing everything: 2-3 (it will contain three elements: 2.2, 2.9 and 2.99).

Below are the links for more details:

answer to the sun

Tensorflow Documentation