Thank you for pointing it out! It should be n-f+1.
@Omunamantech3 ай бұрын
@@KshitizVermaDL if it is n-f -1 then it will be n - 1 - 1 = n - 2 = 26, am I right?
@rajshaikh35058 ай бұрын
This channel is extremely underrated. All explanations are really really amazing, cant emphasize enough. Please keep making more such content. Thank you so much
@KshitizVermaDL8 ай бұрын
Thank you so much for the kind words!
@samirz74 жыл бұрын
I can't believe I didn't discover this channel earlier. Simple explanation of difficult concepts. Thank you. Learning in hindi really clears the concept on another level :)
@KshitizVermaDL4 жыл бұрын
Thank you for this awesome comment! Such comments make me keep going!
@somdubey54364 жыл бұрын
very helpful video. I feel like you are gifted in making people easily understand complex things.
@harshjain4256 Жыл бұрын
If we use 1x1 filter how it will detect features? For example edges?
@raj-nq8ke3 жыл бұрын
Simply speaking, 1X1 filter reduces the size of channels
@KshitizVermaDL2 жыл бұрын
You can use it to do so.
@kazimali42734 жыл бұрын
please tell me if we do not use relu function then whtas happen. I mean why we break linearity.
@KshitizVermaDL4 жыл бұрын
There are two videos explaining this! Have a look at them
@kazimali42734 жыл бұрын
@@KshitizVermaDL thanks I will reply after seeing your videos
@fierce102 жыл бұрын
If you keep layering linear functions, result will also be linear only, then all layers can be represented as single layer. But we are using layers to get a non-linear prediction. We are only using linearity within a layer because it is easy to compute transformations. But we break linearity between each layer.
@atiffaridi5073 жыл бұрын
jab koi image of size height x width x channel , single filter (eg. 3x3x3) ke sath convolve hoga to humein height-1 x width-1 x 1 image milega. Agar 16 filter ke sath convolve karenge to height-1 x width-1 x 16 size ka output milega. Plz correct at time: 2.41
@KshitizVermaDL3 жыл бұрын
I tried to check, couldn't find anything wrong! Can you check your calculations with a 1x1 filter?
@gender1214 жыл бұрын
A very good lecture but a slight doubt 28x28x192 * 5x5x192 (#32)=28x28x32 why not 28-5/1+1=23*23*32.Please explain Sir.Whether different padding has been used to make it uniform?
@KshitizVermaDL4 жыл бұрын
Thanks for the comment! You are right. Padding has been used. I have defined the meaning of "same" padding in one of the earlier videos. It means you do padding so as to keep the output dimensions same as input.
@eiesabyasachi3 жыл бұрын
@@KshitizVermaDL Sir, As per my understanding, can be it calculated like this In case of normal scenario, 28x28x192 * 5x5x192 ( #filters = 32 ) = (28-5)/1 + 1 = 24x24x32 No of operations will be ( 28x28x192 ) * ( 5x5x32 ) = 120 M In case of 1:1 convolution scenario, 28x28x192 * 1x1x16 = 28x28x16 * 5x5x16 ( #filters = 32 ) = (28-5)/1 + 1 = 24x24x32 No of operations will be ( 28x28x192 ) * ( 1x1x16 ) = 2.4M No of operations will be ( 28x28x16 ) * ( 5x5x32 ) = 10M All total it will be 12.4M Please correct me, if the calculation is wrong.