Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @ColeJ71909899
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ColeJ71909899
-
Prikvačeni tweet
Finally got around to my last po- I mean _first_ post of the year! AY-3-8500 MiSTer core is released, plus a bunch of other cool silicon reverse-engineering stuff. https://nerdstuffbycole.blogspot.com/2020/01/end-of-year-update.html …pic.twitter.com/MAW6e5PNXJ
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
[ColeJ] proslijedio/la je TweetHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
[ColeJ] proslijedio/la je Tweet
I made a goose that destroys your computer Download it free here: http://samperson.itch.io/desktop-goose pic.twitter.com/cCGdoOYW1Y
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
[ColeJ] proslijedio/la je Tweet
--- PSX on FPGA --- New Update #4 for Patrons, https://www.patreon.com/posts/project-update-4-33428808 … Project Update #3 gone public for all : https://www.patreon.com/posts/project-update-3-33039605 …
#fpga#MiSTerfpga#psx (Please RT)Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
[ColeJ] proslijedio/la je Tweet
I've written a new article covering the final issue preventing near-perfect emulation of the SNES: exact cycle-timing of the SNES PPUs (video generators.) I've also proposed solutions that are beyond my abilities, so this article is also a call for help.https://byuu.org/articles/edge-of-emulation …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
After smashing a few bugs, the network generates output again. Keras says the accuracy is over 97%, and there is a very noticeable improvement. Here's the section I showed earlier, before and after these changes.pic.twitter.com/K3fTzU3agS
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Programming survey! (RT for exposure) The variables passed into a function/method are ____, while the variables received by a function/method are ____. (If your answer is "other" say what it is below)
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Ok, I just finished implementing data augmentation, which is a fancy way of saying "rotating the images in my dataset to increase its size" Strangely, this decreased the accuracy. No idea as to why yet.pic.twitter.com/KdN8MHIyIB
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I signed up for a class called "Reducing Overfitting in Neural Networks" It would've taught me helpful things, but I dropped outpic.twitter.com/LNjr6MBDnt
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
That's plenty of time to type in at least a dozen commands through a USB port. Plus I could've had sensitive things open on the screen. It's certainly not a one-time thing either. What bugs me is I have no idea which piece of software is responsible for this delay in locking. 2/2
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
When I opened my PC (Linux-based) a few minutes ago, it took a second or two to go from open desktop to login screen. A terminal was open and I managed to type a space in that short window of time. 1/2
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Comments on the future from 2000 (during the Megahertz wars.) Quite funny to readhttps://twitter.com/JCMRVA/status/1216552123921502208 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Ok, I just improved accuracy a little. Neural nets work best when the input value is in a limited range (eg 0.0-1.0) I was using 8 bit integers (per pixel) but simply dividing those values by 255 resulted in a "happier" neural network, and a 2% improvement in accuracy!pic.twitter.com/J2ne6Sfp9i
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
So soon the network's output should hopefully show noticeable improvement compared to current screenshots, like the one below.pic.twitter.com/VO7ce4ideX
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Another thing I need to do is to figure out how to get CUDA working, so this can be run much faster on my GPU.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Second fix is to implement data augmentation, which just means automatically creating rotations & transformations of the training images, which increases the amount of training data with minimal work on my part.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
First, adding dropout layers should reduce overfitting, basically the model is memorizing the training dataset instead of "learning" how to tackle the general problem.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
...problems which are due to an unrepresentative validation dataset and overfitting respectively. Bad results like these are expected since I had no idea what these issues even were when I created this. Now that I'm more educated I can see two immediate fixes...
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

