At around 4:32, you are saying that that the filter for 2nd Convolution must have same 4 channels as the output after the 1st layer. Should it not be 3 as the coloured image is an RGB, so filter for the 2nd convolution should be "(3x3 x3)x8", 3x3 is the filter size, followed by the no of channel and finally the no of filters applied in 2nd Conv, ie, 8?
Thanks for very clear explanation. I wnat to know for complicated data like music data where we use mel spectograms and the number of feature are diffreent for every song, if we do not apply segmentation then we have to deal with diffrent number of input features lets say , (1456,80) where 1456 are the number of frames and 80 are bins then next song (3789,80) , then next (7867,80) ,.... so how to specify parameters for the cnn for this because input is change every time ? and how many layers for such data will be reasonable ?
I'm asking the same question but generally the answer is : we cannot predict how many hidden layers we need, so you've to test and see what features your model is going to detect
General idea is, if you think, your data has more complicated information, then use more number of hidden layers. You need to test your model by training and checking the accuracy, and chose the number of layers that gives highest accuracy.
![The moment we stopped understanding AI [AlexNet]](/img/n.gif)
You are amazing man, there is something unique in your explaining style , you are so gifted ..
Haha… Thank You so much! Means a lot to me
Your greatness is truly commendable. I extend my heartfelt gratitude for the invaluable information you provided.
LORD OF TEACHING LORD OF ML I HAVE NEVER BEEN IN CURIOSITY TO LEARN THESE TOPICS BUT YOU💥💥💥💥
Haha… thanks a lot! A great comment from you!
I'm So gifted to have your videos !!!! 100% concept Understood
@@Gojo_sataro6 hehe… thank you so much! Glad I could help!
I'm so happy to finally understand this topic! Your videos helped me a lot, you're great :)
Haha! Thanks a ton! Glad I could help
This is fantastic. Kudos bro!
Thank you!
At around 4:32, you are saying that that the filter for 2nd Convolution must have same 4 channels as the output after the 1st layer. Should it not be 3 as the coloured image is an RGB, so filter for the 2nd convolution should be "(3x3 x3)x8", 3x3 is the filter size, followed by the no of channel and finally the no of filters applied in 2nd Conv, ie, 8?
Amazing channel,amazing syllabus.
You are going to grow up in a short term.Please upload more videos
Thank you so much!
The Playlist is really useful bro Thankyou so much👍👍👍
Glad to help!
amazing videos brother thank you so much much love ❤
@@dxlorean2938 Hi, you’re welcome! Glad I could help :)
Best content. Thank you. Please upload more like this.
Thank you very much! I will keep uploading more videos! Hope you find my other playlists useful as well.
@@MachineLearningWithJay Yes. I have watched Neural network and CNN playlist
very good series!
simple is the best ! Great teacher
Thank you 😇
😍😍😍 Well explained
Thank you!
It was very useful video to understand CNN. Thank you.
A small correction at 6:18. I think the dimension of FCL should be 120*288.
Supperb, clear doubt -----thanks sir
You're welcome!
@@MachineLearningWithJay now, also wathching your tutorials
@@Sum-jt7fy That's great! Keep Learning, and let me know for anything :)
@@MachineLearningWithJayOk sir
Thank you for valuable lesson
Thank u broo very appreciate it
No problem
this is gonna save my ass in my midterm exam on saturday!
Excellent Work Bro! Can you also share the pdf version of slides that you have used
Hi... sorry for sharing it so late. Here is the slides for this video. drive.google.com/file/d/1tEcvunzhLpSkjlcRiQA5sIOtbGZwTtJ2/view?usp=sharing
Thanks for very clear explanation. I wnat to know for complicated data like music data where we use mel spectograms and the number of feature are diffreent for every song, if we do not apply segmentation then we have to deal with diffrent number of input features lets say , (1456,80) where 1456 are the number of frames and 80 are bins then next song (3789,80) , then next (7867,80) ,.... so how to specify parameters for the cnn for this because input is change every time ? and how many layers for such data will be reasonable ?
amazing session
👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍👍🤏
Add relu between conv and pooling?
thanks perfect
very nice aaa frr
why you select 120 neuron specially in the FC3, i can not understand
@coding lane - Can u pls share the PDFs for all the videos in this playlist. Even you u charge fee it is fine. Please share it.
How can i khow how many hidden layer used in facenet?
I'm asking the same question but generally the answer is : we cannot predict how many hidden layers we need, so you've to test and see what features your model is going to detect
@@maximeentsi2205 is bottleneck layer size mean the number of hidden layer?
@@maximeentsi2205 can i send to you on whatsapp on facebook or any things else for talk about this topic?
General idea is, if you think, your data has more complicated information, then use more number of hidden layers. You need to test your model by training and checking the accuracy, and chose the number of layers that gives highest accuracy.
bhai mza hi aa gya series mei
ab to lgta topper ki gemd mei hi faadega
lol.......
Waiting for a video on backpropagation in CNN
Okay... I will try to upload it sooner.
Brother, I want to learn much more about CNN. Which book do you recommend to read?
How to calculate bias and weight
Bro why we need ReLU and Bias?
What about CNN architecture ? U haven't explained about Resnet vgg n all
plz urdu maa bana do koi playlist
Hi, I don’t speak urdu 😅. But thanks for the suggestion 🙂
👍🏻
Small correction: You are not going to any beauty contest..For God sake please stop advertising.
Bro please add your instagram I'd in description on upcoming video
Hello... here is my insta handle @jaiminpatel_009