# Week 12 Discussion Thread **URL:** \ **Category:** Fastbook Reading Group\ **Created:** [August 26, 2021, 1:07am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260 "2021-08-26T01:07:13Z")\ **Posts on this page:** 20\ **Page:** 2
**Author:** ![vinayak\_nayak](https://avatars.discourse-cdn.com/v4/letter/v/439d5e/32.png) [@vinayak\_nayak](https://community.wandb.ai/u/vinayak_nayak)\ **Post date:** [August 26, 2021, 3:46am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/21 "2021-08-26T03:46:41Z")
Sure Aman, will do! 🙂 ---
**Author:** ![anujd9](https://avatars.discourse-cdn.com/v4/letter/a/c89c15/32.png) [@anujd9](https://community.wandb.ai/u/anujd9)\ **Post date:** [August 26, 2021, 3:47am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/22 "2021-08-26T03:47:03Z")
Maybe a bit more self-explanatory representation for the Conv2d layer would be something like: ```auto import torch.nn as nn conv_layer = nn.Conv2d(in_channels=1, out_channels=128, kernel_size=(3,3)) ``` Ref.: [Conv2d — PyTorch 1.9.0 documentation](https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html) ---
**Author:** ![bgjuee123](https://avatars.discourse-cdn.com/v4/letter/b/71c47a/32.png) [@bgjuee123](https://community.wandb.ai/u/bgjuee123)\ **Post date:** [August 26, 2021, 3:52am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/23 "2021-08-26T03:52:18Z")
Hello, can anyone tell me is there any forums for solving fastbook Colab notebook errors?? ---
**Author:** ![kevinb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/kevinb/32/36_2.png) [@kevinb](https://community.wandb.ai/u/kevinb)\ **Post date:** [August 26, 2021, 3:54am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/24 "2021-08-26T03:54:01Z")
When would be a scenario when we would want to increase our stride? Just to reduce our image size faster? ---
**Author:** ![girijesh](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/girijesh/32/39_2.png) [@girijesh](https://community.wandb.ai/u/girijesh)\ **Post date:** [August 26, 2021, 3:54am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/25 "2021-08-26T03:54:25Z")
you can post in this [Week 11 Discussion Thread - #9 by bhutanisanyam1](https://community.wandb.ai/t/week-11-discussion-thread/85/9) ---
**Author:** ![kevinb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/kevinb/32/36_2.png) [@kevinb](https://community.wandb.ai/u/kevinb)\ **Post date:** [August 26, 2021, 3:55am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/26 "2021-08-26T03:55:43Z")
~~I guess it would kind of be stride vs kernel size right?~~ figured it out 🙂 Kernel size really doesn’t reduce the image size nearly as much as stride does. Only around the edges. And larger kernel sizes would require more memory intensive processes as well. ---
**Author:** ![skr1125](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/skr1125/32/63_2.png) [@skr1125](https://community.wandb.ai/u/skr1125)\ **Post date:** [August 26, 2021, 3:58am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/27 "2021-08-26T03:58:38Z")
As Aman just said, I tend to think of it as covering more of the image with a larger stride which also results in reduction in size (which can be ameliorated by padding). ---
**Author:** ![nareshr8](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/nareshr8/32/103_2.png) [@nareshr8](https://community.wandb.ai/u/nareshr8)\ **Post date:** [August 26, 2021, 4:00am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/28 "2021-08-26T04:00:02Z")
If the padding is `(p x p)` with input `(n x n)` and a kernel size `(f x f)` with stride `(S x S)` the size of output is `((n+2p-f)/S +1) x ((n+2p-f)/S +1)` One of the formulae I could recollect from **Andrew Ng** ’s classes, if I recollect correctly ---
**Author:** ![amanarora](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/amanarora/32/59_2.png) [@amanarora](https://community.wandb.ai/u/amanarora)\ **Post date:** [August 26, 2021, 4:03am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/29 "2021-08-26T04:03:34Z")
[https://cs231n.github.io/convolutional-networks/](https://cs231n.github.io/convolutional-networks/) ---
**Author:** ![girijesh](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/girijesh/32/39_2.png) [@girijesh](https://community.wandb.ai/u/girijesh)\ **Post date:** [August 26, 2021, 4:07am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/30 "2021-08-26T04:07:21Z")
The best one I follow is … | Image Size | N x N x d | | --- | --- | | Filter Size | F x F x d | | Number of Filters | M | | Padding | P | | Stride | S | | Output size (O x O) | O = (N - F + 2P)/S + 1 | | Number of Weights in One Filter | F x F x d | | Number of Weights for all Filters in a Conv Layer | M x F x F x d | | Number of Calculations per Filter (exc. Activation) | O x O x ( FxFxd Mult + FxFxd Add) | ``` = O x O x 2 x F x F x d ``` Number of Calculations per Conv Layer \> M x O x O x 2 x F x F x d ---
**Author:** ![bgjuee123](https://avatars.discourse-cdn.com/v4/letter/b/71c47a/32.png) [@bgjuee123](https://community.wandb.ai/u/bgjuee123)\ **Post date:** [August 26, 2021, 4:08am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/31 "2021-08-26T04:08:04Z")
Actually formula (n+2p-f)/S+1 ---
**Author:** ![kevinb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/kevinb/32/36_2.png) [@kevinb](https://community.wandb.ai/u/kevinb)\ **Post date:** [August 26, 2021, 4:09am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/32 "2021-08-26T04:09:38Z")
Can you explain how we go from 30 filters down to 1 filter? ---
**Author:** ![nareshr8](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/nareshr8/32/103_2.png) [@nareshr8](https://community.wandb.ai/u/nareshr8)\ **Post date:** [August 26, 2021, 4:13am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/33 "2021-08-26T04:13:52Z")
Thank you. Updated the message ---
**Author:** ![skr1125](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/skr1125/32/63_2.png) [@skr1125](https://community.wandb.ai/u/skr1125)\ **Post date:** [August 26, 2021, 4:14am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/34 "2021-08-26T04:14:50Z")
It is actually (n+2p-f)//S + 1 where // indicates integer divide ---
**Author:** ![kevinb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/kevinb/32/36_2.png) [@kevinb](https://community.wandb.ai/u/kevinb)\ **Post date:** [August 26, 2021, 4:16am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/35 "2021-08-26T04:16:20Z")
Yes, that makes sense ---
**Author:** ![kevinb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/kevinb/32/36_2.png) [@kevinb](https://community.wandb.ai/u/kevinb)\ **Post date:** [August 26, 2021, 4:16am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/36 "2021-08-26T04:16:28Z")
But how do we determine if it’s a 3 or a 7 with this output? Because we would be back where we were right? ---
**Author:** ![kevinb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/kevinb/32/36_2.png) [@kevinb](https://community.wandb.ai/u/kevinb)\ **Post date:** [August 26, 2021, 4:17am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/37 "2021-08-26T04:17:09Z")
Ah, ok I missed that. Thank you! ---
**Author:** ![vinayak\_nayak](https://avatars.discourse-cdn.com/v4/letter/v/439d5e/32.png) [@vinayak\_nayak](https://community.wandb.ai/u/vinayak_nayak)\ **Post date:** [August 26, 2021, 4:17am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/38 "2021-08-26T04:17:48Z")
I think I now understand how it will happen for an RGB image. We’re having kernels which also sum depthwise then I understand… ---
**Author:** ![durgaamma2005](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/durgaamma2005/32/117_2.png) [@durgaamma2005](https://community.wandb.ai/u/durgaamma2005)\ **Post date:** [August 26, 2021, 4:20am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/39 "2021-08-26T04:20:00Z")
like is it 5 rank tensor? ---
**Author:** ![kevinb](https://sea2.discourse-cdn.com/flex020/user_avatar/community.wandb.ai/kevinb/32/36_2.png) [@kevinb](https://community.wandb.ai/u/kevinb)\ **Post date:** [August 26, 2021, 4:20am UTC](https://community.wandb.ai/t/week-12-discussion-thread/260/40 "2021-08-26T04:20:01Z")
Thank you Aman for the wonderful lectures. [Previous page](https://community.wandb.ai/t/week-12-discussion-thread/260.md?page=1) [Next page](https://community.wandb.ai/t/week-12-discussion-thread/260.md?page=3)