UNet for Image Segmentation - What You Need To Know!

No video

UNet for Image Segmentation - What You Need To Know! - Computer Vision

Рет қаралды 37,024

Johannes Frey

Күн бұрын

Пікірлер: 43

@hamzaaslam1999 Ай бұрын

That is how you explain analytically, proper analytical approach, sad to see only 4.45K subscribers, dont worry i will share it

@eyslb359 2 жыл бұрын

You are the best explicator I've seen so far. Thank you!

@JohannesFrey 2 жыл бұрын

Hey… thanks for your kind words :)

@SassePhoto 5 ай бұрын

Gruss aus Vancouver! Ausgezeichnet gemacht, klipp und klar, besten Dank!

@JohannesFrey 5 ай бұрын

Hey, danke dir ☺️

@simpernchong 3 ай бұрын

Thank you Sir for the explanation.

@amineziad5099 2 жыл бұрын

You have a good explanation but your intro is tooooo long

@JohannesFrey 2 жыл бұрын

Hey, thanks for your comment and feedback :)

@zg7860 2 жыл бұрын

extremely dense and clear, thank you sir

@JohannesFrey 2 жыл бұрын

Thank you very much :)

@HafeezUllah 2 жыл бұрын

I got the basic intuition with this video. thank you.

@mayankkumarshaw635 3 ай бұрын

Greatly explained! Thank you. Can you make a video about RBMs and Deep Belief Networks

@riwinzo8133 9 ай бұрын

Thank you for the explanation. Helped a lot.

@fantazzmagazz9156 2 жыл бұрын

Nice and easy overview of Ronnebergers work

@JohannesFrey 2 жыл бұрын

Thank you very much :)

@Tamuzia 5 ай бұрын

great explenation! thanks

@abdelrahmanashraf7636 2 жыл бұрын

Extremely Helpful thanks a lot

@JohannesFrey 2 жыл бұрын

Hey man, thanks a lot :)

@jayeshreddy2581 5 ай бұрын

You were so helpful🙌

@gampangji6171 Жыл бұрын

Thank you so much, I need next Example Project

@lamiakazidali2953 2 жыл бұрын

Thak you for this explanation, I would like to learn more about the relationship between the gradient and the mask at the output, what I know, is that the gradient serves to draw points of mask at the output, then is there another relationship between the gradient and the mask?

@blasttrash Жыл бұрын

too long intro. video starts at 1:50

@mohammadvafaie5537 9 ай бұрын

good information, thanks

@senaraul8626 2 жыл бұрын

Awesome video and very well explained. Maybe in the next videos, you should not switch between you and the architecture of the network, because that confuses me a little.

@JohannesFrey 2 жыл бұрын

Hey, thanks for your comment and your suggestion. I will try not to switch that often in the next videos :)

@alishamerwerth3284 2 жыл бұрын

Wow cool Video! Very well explained!

@LintoGeorge-IIITK Жыл бұрын

This video is very nice and well explained. very useful. will you please make a video in the topic W-Net: A Deep Model for Fully Unsupervised Image Segmentation

@dipankarnandi7708 2 жыл бұрын

Thank you for the explanation. Helped a lot. Just a question if you could cover this topic in one of your videos- What is Anomaly detection?? Like for example detecting defects on surfaces... can u-net be useful there?

@amitsharma8337 2 жыл бұрын

Is it me or the volume of the video is lower than usual?

@anjaliram5050 Жыл бұрын

Boah danke für dieses Video, rettest gerade meinen ass!!!!!

@JohannesFrey Жыл бұрын

👍😂

@SuperLordee 2 жыл бұрын

Hey may I ask what are these channels? I didn‘t understand that part.

@JohannesFrey 2 жыл бұрын

hey man... could you provide me the time in the video of that part?

@ziba89 2 жыл бұрын

if you're referring to the number of channels that change with each level, they're associated with the number of filters you're using for the convolution operation - so each filter (from the convolution operation) will reduce the input size in the x/y dimensions (width and height -- given that it's an unpadded convolution) and will increase the number of channels by 1. for example if you look at the first block, your input image size is 572x572x1 (width x height x num_channels -- 1 for grayscale image, if you have RGB image, it's 3) -- with the first convolution operation (navy blue arrow to the right) a 3x3x64 convolution operation was applied -- meaning 64 different filters of 3x3 size were convolved with the original 572x572x1 image, resulting in an image with output size = [(572 + 2*0 - 3) / 1] + 1 = 570 for each dimension (unpadded convolution - and single stride - equation is (inputSize + 2*padding - filterSize / stride ) + 1 ) -- So you will get an output dimension of 570x570x64, which is what you see in the first convolution operation output in the diagram. As they mentioned, the number of channels are doubled with each level, meaning they increase the number of filters by a factor of 2 each time. You can check out Andrew Ng's video which explains this operation step by step (C4W1L08 Simple Convolutional Network Example on YT)