mlpack IRC logs, 2018-05-04

Logs for the day 2018-05-04 (starts at 0:00 UTC) are shown below.

>
May 2018
Sun
Mon
Tue
Wed
Thu
Fri
Sat
 
 
1
2
3
4
5
6
7
8
9
10
11
19
20
21
22
23
24
25
26
27
28
29
30
31
--- Log opened Fri May 04 00:00:04 2018
02:51 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
05:05 -!- petris [quassel@2600:3c02::f03c:91ff:fe25:b576] has quit [Remote host closed the connection]
05:20 -!- petris [quassel@2600:3c02::f03c:91ff:fe25:b576] has joined #mlpack
06:06 -!- manish7294 [~manish729@2405:205:148a:d063:fd70:1a3c:3a1c:8a41] has joined #mlpack
06:55 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
07:44 -!- manish7294 [~manish729@2405:205:148a:d063:fd70:1a3c:3a1c:8a41] has quit [Ping timeout: 260 seconds]
07:55 -!- govg [~govg@unaffiliated/govg] has quit [Ping timeout: 264 seconds]
07:56 -!- ShikharJ_ [70c4b52b@gateway/web/freenode/ip.112.196.181.43] has joined #mlpack
07:58 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has joined #mlpack
08:53 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 248 seconds]
08:56 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
08:57 -!- govg [~govg@unaffiliated/govg] has joined #mlpack
09:07 < ShikharJ_> zoq: You there? I wanted to discuss the implementation of the Transposed Convolution Layer a bit.
10:00 -!- ShikharJ___ [70c4b52b@gateway/web/freenode/ip.112.196.181.43] has joined #mlpack
10:01 -!- ShikharJ_ [70c4b52b@gateway/web/freenode/ip.112.196.181.43] has quit [Ping timeout: 260 seconds]
10:01 -!- ShikharJ___ is now known as ShikharJ_
10:13 < zoq> ShikharJ_: Hello, please go ahead.
10:17 < ShikharJ_> Referrig from this paper (https://arxiv.org/pdf/1603.07285.pdf), Relation 14, I believe we can let the convolution layer template be as it is, and just change the input to the required size and pass on to the existing routines. But I'm not sure whether it'd be the right thing to do.
10:17 < ShikharJ_> *Referring
10:18 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 260 seconds]
10:20 < zoq> ShikharJ_: Yeah, that way we could simply use the backward pass from the existing conv layer.
10:21 < zoq> we also have to set outputWidth and outputHeight
10:23 < zoq> and we also have to set the output paramter which is set inside the forward pass, but I guess it might be a good idea to just duplicate the code and modify the backward pass?
10:25 < ShikharJ_> I guess that should work, basically, we're swapping backward and forward passes right? From the template?
10:25 < zoq> yes
10:26 < zoq> It might be a good idea to implement a simple test that compares the result of the Forward pass against some manually computed results.
10:27 < zoq> Same for the backward pass.
10:29 < ShikharJ_> That clears up things for me. Thanks, actually the visual 4.7 in the paper had a erroneous description (we would get a 3 x 3 input in whch we have to insert zeroes and not a 2x2).
10:30 < ShikharJ_> Checkout the third line on the description (page 27)
10:34 < zoq> I wonder if the same issue exsists in the coressponding github project
10:40 < ShikharJ_> Seemingly the github project doesn't mention this description, only the technical report does.
10:41 < ShikharJ_> I'll open an issue, let's see.
10:41 < zoq> yeah, good idea
10:59 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
10:59 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has quit [Quit: Leaving]
11:06 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Ping timeout: 264 seconds]
11:12 -!- govg [~govg@unaffiliated/govg] has quit [Ping timeout: 240 seconds]
11:14 -!- govg [~govg@unaffiliated/govg] has joined #mlpack
11:15 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
14:15 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Ping timeout: 256 seconds]
14:17 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
14:23 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Ping timeout: 256 seconds]
14:59 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has joined #mlpack
15:03 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
15:35 -!- ShikharJ_ [70c4b52b@gateway/web/freenode/ip.112.196.181.43] has quit [Quit: Page closed]
15:39 -!- ShikharJ [~ShikharJ@112.196.181.43] has joined #mlpack
16:03 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Ping timeout: 255 seconds]
16:04 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
16:32 -!- ImQ009_ [~ImQ009@unaffiliated/imq009] has joined #mlpack
16:36 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Ping timeout: 256 seconds]
16:50 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has quit [Quit: Leaving]
17:36 -!- ShikharJ [~ShikharJ@112.196.181.43] has quit [Quit: Leaving]
17:49 -!- ShikharJ [~ShikharJ@112.196.181.43] has joined #mlpack
17:50 -!- ShikharJ [~ShikharJ@112.196.181.43] has quit [Client Quit]
18:16 -!- govg [~govg@unaffiliated/govg] has quit [Ping timeout: 240 seconds]
18:35 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has joined #mlpack
20:10 < rcurtin> ok, so since #1382 (OpenMP warning/bugfix) is merged, I think it would be a good idea to release mlpack 3.0.1
20:11 < rcurtin> does anyone have any other open PRs or changes that they would like to see incorporated before the release? (of course, it is easy to just release another 3.0.2 shortly after this too)
20:42 < zoq> I guess you could include Big Batch SGD as well.
21:46 -!- sulan_ [~sulan_@563BE0E4.catv.pool.telekom.hu] has quit [Quit: Leaving]
22:07 -!- ImQ009_ [~ImQ009@unaffiliated/imq009] has quit [Quit: Leaving]
23:16 < rcurtin> right, I'll note that in the history file also
--- Log closed Sat May 05 00:00:05 2018