วีดีโอ

I have orders online . Had to pay extra . If your friends are coming from us , you can order

How to total cost.

@user-yc7uz1kp8v it depends on where you are buying it.

Thanks for the comment . Just learning the big game of TH-cam

Glad you think so!

What is the issue you facing ?

In the field of machine learning and computer vision, receptive field refers to the portion of an input image that a particular feature or neuron in a neural network "sees" or responds to. It is the spatial extent of the input that influences the output of a particular neuron. The receptive field size can vary across different layers of a neural network, depending on the architecture and the number of layers. The receptive field of a neuron in the first layer is usually small and local, while in deeper layers, it becomes larger and covers a larger portion of the input image. Understanding the receptive field is important in designing and optimizing neural networks for image processing and computer vision tasks, as it can affect the ability of the network to capture and learn meaningful features from the input image.

@@BionicBee So i understand from u that the receptive field isn't a technique, is just a expression, cuz the max pooling technique is a part of the CNN that pick the most activated pixels and preserve thae high values , right?

Receptive field the area one pixel can see locally and globally.

Sure , what specific code you need ?

@@BionicBee would be better if you could share the notebook so that we can refer to the video easily

Will share it soon . Thanks

@@BionicBee Thank you sir , please notify us when you have added the link to the notebook

That's Not 100% correct . I will cover it in Next Video.

We can't Calculate How many feature Extractors we need .It;s Going to be intuitive. But it depends on Your Data , The hardware we have to train,

That is correct. That is why we find Blocks in well-known models such as Resnet.

In this context, a feature is a piece of information about gradients and edges in a picture, and channels is a collection of those features. And gradients are essentially the way that colour intensity changes. A coloured image has three distinct channels that are labelled Red, Blue, and Green. Other elements are also handled as channels, such as edges and gradients. One such channel is displayed in below image We employ kernels and filters to fetch each of these distinct channels. Convolution is the process of retrieving channels and feature maps.

That is correct. I will discuss it more in the Next Video

Another aspect to mention is that Nvidia has designed the GPUs to run 3*3 faster. If necessary, 3*3 can also function as 5*5, 7*7, and so on.

By convolving on top of an image, kernels are utilised to extract various features from the image. A kernel is a compact matrix that can carry out a variety of operations on an image. The kernel may be 3x3, 5x5, 7x7, or any other size. We can extract characteristics like vertical and horizontal edges, gradients, and more using the kernel. Kernels are also used in blurring, sharpening, edge detection. The following code employs a kernel that serves as the image's edge extractor. ```python import cv2 import numpy as np #your image img = cv2.imread(r'Path\\*.png') ''' Edge detection Kernal -1 -1 -1 -1 8 -1 -1 -1 -1 ''' x = [[-1,-1,-1],[-1,8,-1],[-1,-1,-1]] kernel = np.asarray(x) output_image = cv2.filter2D(img,-1,kernel) cv2.imwrite(r'Path\\blurred.png',output_image)