[DL] How to calculate the number of parameters in a convolutional neural network? Some examples

[urarakono]

I have long been confused about how to count the number of parameters in CNN, but thanks to lots of examples in this video, I have finally understood it! Thank you!

[nagamanitenali]

Very good explanation Sir... I searched many links but didn't find an appropriate video to calculate no.of channels.. this is the best video . Thanks a lot

[ryanp]

this is gooood. Highly recommend to anyone who wants to understand the # of parameters in CNN

[高造擎]

This video is amazing. I have been searching for explanation like this, and those fancy tutorial are pretty disappointing. Thank you Sir!

[varmabhaveshkumarnareshbha]

Finally solved all doubt, Crystal Clear

[mhadnanali]

How 10x10 turns to 8x8, you should have explained. anyway i figured it out formula is output= n-f+1 while n is input and f is filter.

[kk-kkvk]

I can't undrestand, help me please.
Why when our input is 10x10 dimentional and then we apply one 3x3 filter our output becomes 8x8?

[tanishkaachaturvedi]

This was such a brilliant explanation. Thank you so much!!!!

[iyshwaryakannan]

Awesome sir, most wanted explanations with more samples.

[shubhamsongire]

Thank you very much. Now all doubts are clear.

[PawanSingh-xkcj]

how weight is initialized in the 1d conv, if it is not initialized what is the default value.

[lchunleo]

thank you. this is very informative and clear my doubts

[lewisyuu]

Where does the number 8 come from in the first example?

[katsamapolpetchpol]

Thank you for this masterpiece explanatory.

[diliprajdasari]

That was wonderful explanation. Thank you. But What if the input image's width and height are different? Like 228x284. What happens to the output's width and height?

[enderBenBen]

Thank you! This video is helping me do revision!

[jaggujaggu]

Convolution2D (8, 3) implies that we are having 8 3x3 filters. My question is what kind filters they are, all same or all different. If filters are different who decides the filters?

[tsukuruuu]

For Convolution layer :
Number of Params = (filter width × filter height × input channels + 1) × number of filters

For Fully Connected layer:
Number of Params= (current layer neurons c * previous layer neurons p) + c.

[Jinyang-pc]

Is the example 4 incorrect? You have 3 by 3 filters with a depth of 5, should not that be (3*3*5+1)*8

[risingresearchlab]

Plz help me, why parameters is 128 and 25 in input shape 100, 5 (example 4)