Join devRant
Do all the things like
++ or -- rants, post your own rants, comment on others' rants and build your customized dev avatar
Sign Up
Pipeless API
From the creators of devRant, Pipeless lets you power real-time personalized recommendations and activity feeds using a simple API
Learn More
Search - "deeplearning"
-
Dank Learning, Generating Memes with Deep Learning !!
Now even machine can crack jokes better than Me 😣
https://web.stanford.edu/class/...rant deeplearning artificial intelligence ai neural networks stanford machine learning learning devrant ml2 -
!rant
I just woke up a minute before one of my first neural networks finished training
!!rant
My laptops dual core cpu with 4 threads is slooooooooow3 -
Fucking fuck Nvidia. Shit suckers and ass lickers can't make a fucking thing properly. Everytime I have to compile something involving cuDNN and cuda I wish I could kill myself first. It's a piece of garbage software that we're stuck with. Fuck you mother fuckin Nvidia.3
-
Linux has been around since back when dinosaurs punched holes in cards, but for some reason it still takes a few hours of googling and error debugging to do something as basic as connect to a wpa2-enterprise wifi network.
What the fuck? Where's the "connect to any standard work or school wifi network" command line utility distributed with all os flavors? Why can't I just put in a username and password and be done with it instead of sudo editing networking adapter configuration files manually?2 -
Nothing makes me not want to take a full-time job at your company more than having to go through IT tickets every quarter year when my password expires to actually change my password. Why have a fucking self-service portal for employees if logging in with an expired password doesn't work and the reset password link tells me that I need to log in to enroll with security questions (???). It feels like these websites are glued together with sticks and spit and there's a million of them each sporting one specific purpose! I have to go through this shit multiple times since I'm an intern and I didn't have access to my account through the course of the semester. Get your fucking shit together!1
-
Learning Image Processing,Deep Learning,Machine Learning,Data modeling,mining and etc related to and also work on them are so much easier than installing requiremnts, packages and tools related to them!2
-
Quick Question
Suppose I wanted to apply A.I. or deeplearning to a very simple marketing activity I have in mind...
What's my learning curve looking like? I'm a backend programmer with roughly 3-4 years
experience in laravel/php right now. I've used
almost every inch of that framework.
Just curious. And any path anyone would suggest? thanks3 -
Back in middle school I wrote the simple Hello World Java program out on a piece of paper in an attempt to figure out what all the syntax and keywords meant. I didn't get bored
-
Anyone know of any good reference material that teaches you how to implement and train your own Yolo object localization neural network? (Preferably for tensorflow) I'm not looking for pretrained models that you just downloaded and run, rather a tutorial that walks you step by step through the implementation of the network, the reasoning behind the architecture, and examples of the training data used for the training as well as the process of training?
I know it's a lot to ask but it's really frustrating when ever example is just "clone this repo, hit run and use the pretrained models" sure it might get you up and running quickly but it doesn't really teach you anything...
P.s. - seems like every educational post goes from super simple to super complex without any middle ground and the super complex stuff doesn't tell you why its used the way way it is.5 -
The concept and execution of inter-cluster SSL along with keystores, truststores, signing, and similar just clicked in my head today. I feel the burden of undiagnosable https errors just melt off my shoulders. Any other environment tips I should know for kubernetes?
-
OpenCV,OpenFace,Caffe are supported in Arch Linux,but CUDA is not supported!! :| WTF!! How these packages could be supported in Arch but CUDA not!7
-
: Bro! I have CNN exam tomorrow but the accuracy of my Computer Vision Network is too low.
: Have you tried Yolo?
: You're right, exams don't matter anyway.
: What?
: What?9 -
#PytorchUdacityScholar Well this time I won't give up... #Second Scholarship from Udacity #MillionThanks🙏🙏🙏🙏 to Udacity India Facebook #artificialintelligence #machinelearning #deeplearning3
-
Is it legal to use googlenet, alexnet, or any other pretrained model to detect obejct in image for commercial app.?? How to collect data legally for this purpose (google image, imagenet etc)?1
-
8-layer tanh networks don't want to converge. Theory says it's fine, but they have to. The thesis chart will suck otherwise.
-
Where is the mac vs ubuntu vs windows war for developers? I am a Windows user (on a dell latitude e5570), but I am considering a new laptop because everyone says macbooks are great and outperform windows (which on gradle builds is true).
I mainly use my laptop only for developing and programming things like: full-stack, Android and a little bit of deeplearning/ML.
So which one would you recommend and why? These are pretty heavy tasks, from my opinion.10 -
It was my first time doing an NLP task / implementing a RNN and I was using the torchtext library to load and do sentiment analysis on the IMDB dataset. I was able to use collate_fn and batch_sampler and create a DataLoader but it gets exhausted after a single epoch. I’m not sure if this is the expected behavior, if it is then do I need to initialize a new DataLoader for every epoch? If not is something wrong with my implementation, please provide me the correct way to implement the same.
PS. I was following the official changelog() of torchtext from github
You can find my implementation here
changelog - https://github.com/pytorch/text/...
My implementation - https://colab.research.google.com/d...