- Practical 3.0 – CNN basics

Practical 3.0 – CNN basics

Convolutional Neural Networks – Basics
Full project: https://github.com/Atcold/torch-Video-Tutorials

Torch7-profiling repo: https://github.com/e-lab/Torch7-profiling
Krizhevsky, Sutskever, Hinton paper: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-netw...
Convolutional Neural Networks – Basics
Full project: https://github.com/Atcold/torch-Video-Tutorials

Torch7-profiling repo: https://github.com/e-lab/Torch7-profiling
Krizhevsky, Sutskever, Hinton paper: https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf

Notes:
0:53 – "omogeneity" spells "homogeneity" in English...
4:50 – the +1 bias term has not being included in the estimate (like it's been done for 2nK at 5:39) because I wanted to stress the dependence with n² only

スペースでAND検索・ORで区切るとOR検索・先頭に「-」で除外検索

– "omogeneity" spells "homogeneity" in English... - Practical 3.0 – CNN basics

– "omogeneity" spells "homogeneity" in English...

Practical 3.0 – CNN basics
2016年09月23日　
00:00:53 - 00:04:50
– the +1 bias term has not being included in the estimate (like it's been done for 2nK at 5:39) because I wanted to stress the dependence with n² only - Practical 3.0 – CNN basics

– the +1 bias term has not being included in the estimate (like it's been done for 2nK at 5:39) because I wanted to stress the dependence with n² only

Practical 3.0 – CNN basics
2016年09月23日　
00:04:50 - 01:10:51
@ Can you please explain the conversion (3, 256, 256) -> (6, 128, 128) with the filter (3, 5, 5) with stride 2? As per my understanding I am expecting the calculation goes something like ( (256 - 5) + 2 * padding / Stride) +1 - Practical 3.0 – CNN basics

@ Can you please explain the conversion (3, 256, 256) -> (6, 128, 128) with the filter (3, 5, 5) with stride 2? As per my understanding I am expecting the calculation goes something like ( (256 - 5) + 2 * padding / Stride) +1

Practical 3.0 – CNN basics
2016年09月23日　
00:46:42 - 01:10:51
@ .I got a different value for #net:forward(torch.rand(3, 256, 256)) = 24576. I don't know, if its only for me or others as well. So, it was giving me errors. - Practical 3.0 – CNN basics

@ .I got a different value for #net:forward(torch.rand(3, 256, 256)) = 24576. I don't know, if its only for me or others as well. So, it was giving me errors.

Practical 3.0 – CNN basics
2016年09月23日　
01:05:07 - 01:10:51
チャンネル登録YouTube RSS

Alfredo Canziani

※本サイトに掲載されているチャンネル情報や動画情報はYouTube公式のAPIを使って取得・表示しています。

概要 カレンダー 動画一覧 タイムテーブル チャンネル分析

Timetable

動画タイムテーブル

スペースでAND検索・ORで区切るとOR検索・先頭に「-」で除外検索

動画数：129件

もっと見る