adipandas

I love how this comment turned a good old physics to a thread about existential reflections - folks debating the meaning of life. :D

I completely agree with you mate.

https://uidai.gov.in/en/my-aadhaar/about-your-aadhaar/aadhaa...

This is what I referred. But never come across a situation where it was followed. Many cases were not progressing without aadhaar.

Learning quantization approaches in deep learning.

Beautiful idea.

My take on it: I find it difficult to generalize the notion of layer removal when the bit depth of that layer goes to zero. It's wouldn't be straight forward although the authors provide equation 5. It feels like lot of information is missing in this work to even reproduce it. And authors do only 1 case study.

I believe some implementation is required to understand the authors completely. Example, optimizer modification for layer when it is removed in training.

Media: https://youtu.be/QHT_sm7OgWY

For now I am not working professionally on those. But I hope to start something.

This is a good resource. I have worked with Arduino and RPi a lot. I want to start going deeper and more detailed. Thank you for sharing this.

I think recently RL or DL is going crazy with design. This is very nice to see.

https://www.nature.com/articles/d41586-021-01515-9

Bosch should use it. ;)

Just came across this on hn.

https://www.reuters.com/technology/bosch-opens-german-chip-p...

I like your take on frame rate of the universe. Nice! :)

Heroku depends on Salesforce.

Super expensive. :D

This article is interesting, I even skimmed through their paper. But I think still the question remains: How to find the unified reward function? Or in other words, how to find answer to life? [It cannot be 42].

Feedback is welcome!

My implementation of kalman filters: https://adipandas.github.io/multi-object-tracker/includeme/a...

I agree. I will not like to give a proof-of-concept in C++. It is definitely possible but again, why to waste time. And it may differ, case by case. Some may like Python, others may like some other programming language. Python has a wealth of libraries easy to setup and easy to code. This is an advantage when you what something done in short amount of time.

This is fantastic. :)

@hgibbs, This is cool. I will go through this in more detail. Thank you.

Yes, I understand this. The system's global stability is unaccounted for when we linearize the system near a fixed point.

By the way, thanks for suggesting SimCLR. I will go through this paper.:)

Oh. This looks interesting. I am interested in applications of AI in manufacturing practices. I think there is lot of data available with industry which may be difficult to label. Thus, approaches like one-shot or few-shot learning can be very promising in problems like quality control using computer vision.

Code for my recent paper. Feedback appreciated. Thank you. :)

Our paper is accepted in IROS-2020.

This is just hitting the nerve of Quora. :D

May be, there may be some answers which can really be helpful.

The top-down view problem is what I was facing when I was trying to use a detection model for a project with quadcopters. For this I had to train my object detector with the data we collected from that view. YOLO was used for this work.

Yes, replacing the fine-tuned model with compiled graph should work. I tried to keep it simple and intuitive to change the model so as to allow the use of any other custom models.

Kalman filter is also one good way to reliably keep track of objects under significant obstruction.

Pytorch makes it even more fun.

Yes. I am actually looking into this idea. I thought instead of recurrent yolo, Correlation Filter is much simpler.

I was referring the following papers:

1. https://ethz.ch/content/dam/ethz/special-interest/baug/igp/p...

2. https://zpascal.net/cvpr2018/He_A_Twofold_Siamese_CVPR_2018_...

3. http://openaccess.thecvf.com/content_ECCV_2018/papers/Yunhua...

@mendeza, Thank you for the feedback. I am planning to add detectron models as well to this repository.

Initial intention of this project was to avoid direct dependency of any deep learning framework. I have only used pre-trained models and opencv for this project.

Making a tool for data labeling is an awesome idea. I will definitely like to work on it. We can collaborate on this if possible. You are also welcome to send in your pull requests.