# Understanding Numpy axis(for 2d & 3d arrays)

understanding the dimensions in python arrays is a little bit tricky. one should understand its basics before jumping into its application and making operations.

prerequisite: having idea behind basic array in numpy, coding in python

let understand it through an example:

suppose we have a 2d array denoted by np_array_2d…

# Understanding through an example: hypothesis test, Null hypothesis, and alternative hypothesis.

SITUATION: you and your boss are arguing about whether more sleep will make you more productive. you sleep for 7 hours every day and your boss is also aware of that fact.

first, we will make a hypothesis and NULL hypothesis from your perspective and then we will move on…

# SPPNet to Fast-RCNN

Fast RCNN are modified version of RCNN where a lot of differ comes with SPPNet.

1. in SPPNet there were 3 to4 layers (0,1,2,3) of pooling where Fast-RCNN the only use one level of 7 by 7 (7x7) grid pooling (max pooling) and named it ROI pooling.
2. they experimentally discover that…

# Python code: Histogram of an image -pixels wise

`yvalue=np.zeros()for i in range(yvalue.size): #this yvalue and loop is only for using ploting y-axis (0-255)    yvalue[i]=iprint(np.shape(img))for x in range(img.shape):    for y in range(img.shape):            rvalue[img[x,y,0]] = rvalue[img[x,y,0]]+1            gvalue[img[x,y,1]] = gvalue[img[x,y,1]]+1            bvalue[img[x,y,2]] = bvalue[img[x,y,2]]+1#ploting histrogramplt.plot(yvalue,rvalue,color='red')plt.plot(yvalue,gvalue,color='green')plt.plot(yvalue,bvalue,color='blue')plt.show()print(np.shape(img))#want to know the number of pixelstotal=0for ccc in range(rvalue.size):    total=total+rvalue[ccc]for ccc in range(gvalue.size):    total=total+gvalue[ccc]for ccc in range(bvalue.size):    total=total+bvalue[ccc]print(total)#just showing the imageimgaa = Image.fromarray(img, 'RGB')imgaa.save('test.png')imgaa.show()`

# best way to remember the implication => truth table

lets say A implies B (i.e A=>B).

Now consider A is son and B is Father. they both are arguing something. so if the father is wrong then son is also wrong (A is false and B is false=true) if the son is right then father must be right(A is true and B is true = true)
the son can be wrong but not the father (A is false and B is true= true)
but never can be son right and father false (A true and B is false= false)

# A simple definition of “Overlapping” term in CNN

The first time I encounter this word after started reading OverFeat paper. … 