Welcome to part 4 of this series on CNN. In the previous lesson, we trained our model with a decent accuracy but the question is if this accuracy is considered to be the best or not. because the model can become overfit in no time.In this lesson, we will learn how to visualize a model and how to select the best model using TensorBoard.
Welcome to the part 3 of this CNN series., previously we learned about the overview of Convolutional Neural Network and how to preprocess the data for training, In this lesson, we will train our Neural network in Google Colab.
Welcome to the part 2 of this series on CNN. In the previous lesson we learned about the working of CNN, Now in this lesson and upcoming lessons, we will build a fully functional model to determine the probability of a car in an image
Today, if you want to analyze an image or video then Convolutional Neural Network is one of the popular choices available on the internet. In this series of lessons, we will cover various topics and TensorBoard and Keras libraries as we build our model onto it.
Bokeh is the Japanese word which means Blur. Bokeh tends to the region which we choose to out of focus. This effect makes the in-focus image so vibrant and clear to eyes which makes the photo looks more elegant. Today I would like to share how to achieve Bokeh effect in Python.
Manually putting values for HSV model can be quite frustrating. The easiest way to deal with it is to make an OpenCV based trackbars which allow us to adjust the values manually using a trackbar. So with the help of this, we can able to adjust the different combination of values in one go.
Our aim is to build a module which is enough to analyze a polygon and return some fruitful information like an angle, slope, sides, corner coordinates etc. So we build py2pyAnalysis. Two line of code is sufficient to tear down a polygon of upto 15 sides.
Sometimes when we build a program, we realize its more than just for one program and can be useful to many, and it's a good thing though. So lets learn how to make your module pip installable.
In image processing we often use HSV model over the RGB model, but what actually lag behind by RGB so that we need the HSV model. for these let's understand the models and then we code some program to view it practically.
Sometimes while importing a module we got a famous error “No Module Found” or sometimes “IndexError: No Module named”, this is a very common error and quite frustrating at the same time, we reinstall the model again and again but every time when we try to import the model we got the same error. So let's learn why this error come and how to remove this one for all