![Kapil Sachdeva](/img/default-banner.jpg)
- Видео 41
- Просмотров 390 876
Kapil Sachdeva
США
Добавлен 26 сен 2013
"Work like Hell. Share all you know. Abide by your handshake. Have fun!" - Dan Geer
I saw this on my mentor’s internal profile page some 20 years back, I shamelessly stole it and made it mine .... years later I discovered Dan Geer, the author of this quote ...but it does not matter who said it, rather the key is to assimilate these adages, these words of wisdom in your very being and is equally important to keep them in your sight as the gentle reminder of what is important!
Amongst the many obligations and responsibilities that we all have, the one that remains most dear to me is to keep learning and then sharing what I learned. I have done this for as long as I can remember; very early on in my life, I had accidentally discovered that you learn more when you share what you know. This is one aspect of my life that has been very consistent & the one I cherish the most.
This youtube channel is my new medium of sharing what "I think I know"!
I saw this on my mentor’s internal profile page some 20 years back, I shamelessly stole it and made it mine .... years later I discovered Dan Geer, the author of this quote ...but it does not matter who said it, rather the key is to assimilate these adages, these words of wisdom in your very being and is equally important to keep them in your sight as the gentle reminder of what is important!
Amongst the many obligations and responsibilities that we all have, the one that remains most dear to me is to keep learning and then sharing what I learned. I have done this for as long as I can remember; very early on in my life, I had accidentally discovered that you learn more when you share what you know. This is one aspect of my life that has been very consistent & the one I cherish the most.
This youtube channel is my new medium of sharing what "I think I know"!
Eliminate Grid Sensitivity | Bag of Freebies (Yolov4) | Essentials of Object Detection
This tutorial explains a training technique that helps in dealing with objects whose center lies on the boundaries of the grid cell in the feature map.
This technique falls under the "Bag of Freebies" category as it adds almost zero FLOPS (additional computation) to achieve higher accuracy during test time.
Pre-requisite:
Bounding Box Prediction
ruclips.net/video/-nLJyxhl8bY/видео.htmlsi=Fv7Bfgxd1I-atZF0
Important links:
Paper - arxiv.org/abs/2004.10934
Threads with a lot of discussion on this subject:
github.com/AlexeyAB/darknet/issues/3293
github.com/ultralytics/yolov5/issues/528
This technique falls under the "Bag of Freebies" category as it adds almost zero FLOPS (additional computation) to achieve higher accuracy during test time.
Pre-requisite:
Bounding Box Prediction
ruclips.net/video/-nLJyxhl8bY/видео.htmlsi=Fv7Bfgxd1I-atZF0
Important links:
Paper - arxiv.org/abs/2004.10934
Threads with a lot of discussion on this subject:
github.com/AlexeyAB/darknet/issues/3293
github.com/ultralytics/yolov5/issues/528
Просмотров: 1 047
Видео
GIoU vs DIoU vs CIoU | Losses | Essentials of Object Detection
Просмотров 4 тыс.Год назад
This tutorial provides an in-depth and visual explanation of the three Bounding Box loss functions. Other than the loss functions you would be able to learn about computing per sample gradients using the new Pytorch API. Resources: Colab notebook colab.research.google.com/drive/1GAXn6tbd7rKZ1iuUK1pIom_R9rTH1eVU?usp=sharing Repo with results of training using different loss functions github.com/...
Feature Pyramid Network | Neck | Essentials of Object Detection
Просмотров 12 тыс.Год назад
This tutorial explains the purpose of the neck component in the object detection neural networks. In this video, I explain the architecture that was specified in Feature Pyramid Network paper. Link to the paper [Feature Pyramid Network for object detection] arxiv.org/abs/1612.03144 The code snippets and full module implementation can be found in this colab notebook: colab.research.google.com/dr...
Bounding Box Prediction | Yolo | Essentials of Object Detection
Просмотров 9 тыс.Год назад
This tutorial explains finer details about the bounding box coordinate predictions using visual cues.
Anchor Boxes | Essentials of Object Detection
Просмотров 10 тыс.Год назад
This tutorial highlights challenges in object detection training, especially how to associate a predicted box with the ground truth box. It then shows and explains the need for injecting some domain/human knowledge as a starting point for the predicted box.
Intersection Over Union (IoU) | Essentials of Object Detection
Просмотров 3,9 тыс.Год назад
This tutorial explains how to compute the similarity between 2 bounding boxes using Jaccard Index, commonly known as Intersection over Union in the field of object detection.
A Better Detection Head | Essentials of Object Detection
Просмотров 2,1 тыс.Год назад
This is a continuation of the Detection Head tutorial that explains how to write the code such that you can avoid ugly indexing into the tensors and also have more maintainable and extensible components. It would beneficial to first watch the DetectionHead tutorial Link to the DetectionHead tutorial: ruclips.net/video/U6rpkdVm21E/видео.html Link to the Google Colab notebook: colab.research.goog...
Detection Head | Essentials of Object Detection
Просмотров 5 тыс.Год назад
This tutorial shows you how to make the detection head(s) that takes features from the backbone or the neck. Link to the Google Colab notebook: colab.research.google.com/drive/1KwmWRAsZPBK6G4zQ6JPAbfWEFulVTtRI?usp=sharing
Reshape,Permute,Squeeze,Unsqueeze made simple using einops | The Gems
Просмотров 4,7 тыс.Год назад
This tutorial introduces to you a fantastic library called einops. Einops provides a consistent API to do reshape, permute, squeeze, unsqueeze and enhances the readabilty of your tensor operations. einops.rocks/ Google colab notebook that has examples shown in the tutorial: colab.research.google.com/drive/1aWZpF11z28KlgJZRz8-yE0kfdLCcY2d3?usp=sharing
Image & Bounding Box Augmentation using Albumentations | Essentials of Object Detection
Просмотров 7 тыс.Год назад
This tutorial explains how to do image pre-processing and data augmentation using Albumentations library. Google Colab notebook: colab.research.google.com/drive/1FoQKHuYuuKNyDLJD35-diXW4435DTbJp?usp=sharing
Bounding Box Formats | Essentials of Object Detection
Просмотров 6 тыс.Год назад
This tutorial goes over various bounding box formats used in Object Detection. Link the Google Colab notebook: colab.research.google.com/drive/1GQTmjBuixxo_67WbvwNp2PdCEEsheE9s?usp=sharing
Object Detection introduction and an overview | Essentials of Object Detection
Просмотров 8 тыс.Год назад
This is an introductory video on object detection which is a computer vision task to localize and identify objects in images. Notes - * I have intentionally not talked about 2-stage detectors. * There will be follow-up tutorials that dedicated to individual concepts
Softmax (with Temperature) | Essentials of ML
Просмотров 3,5 тыс.2 года назад
A visual explanation of why, what, and how of softmax function. Also as a bonus is explained the notion of temperature.
Grouped Convolution - Visually Explained + PyTorch/numpy code | Essentials of ML
Просмотров 4,6 тыс.2 года назад
In this tutorial, the need & mechanics behind Grouped Convolution is explained with visual cues. Then the understanding is validated by looking at the weights generated by the PyTorch Conv layer and by performing the operations manually using NumPy. Google colab notebook: colab.research.google.com/drive/1AUrTK622287NaKHij0YqOCvcdi6gVxhc?usp=sharing Playlist: ruclips.net/video/6SizUUfY3Qo/видео....
Convolution, Kernels and Filters - Visually Explained + PyTorch/numpy code | Essentials of ML
Просмотров 2 тыс.2 года назад
This tutorial explains (provide proofs using code) the components & operations in a convolutional layer in neural networks. The difference between Kernel and Filter is clarified as well. The tutorial also points out that not all kernels convolve/correlate with all input channels. This seems to be a common misunderstanding for many people. Hopefully, this visual and code example can help show th...
Matching patterns using Cross-Correlation | Essentials of ML
Просмотров 1,1 тыс.2 года назад
Matching patterns using Cross-Correlation | Essentials of ML
Let's make the Correlation Machine | Essentials of ML
Просмотров 1,7 тыс.2 года назад
Let's make the Correlation Machine | Essentials of ML
Reparameterization Trick - WHY & BUILDING BLOCKS EXPLAINED!
Просмотров 11 тыс.2 года назад
Reparameterization Trick - WHY & BUILDING BLOCKS EXPLAINED!
Variational Autoencoder - VISUALLY EXPLAINED!
Просмотров 12 тыс.2 года назад
Variational Autoencoder - VISUALLY EXPLAINED!
Probabilistic Programming - FOUNDATIONS & COMPREHENSIVE REVIEW!
Просмотров 4,8 тыс.2 года назад
Probabilistic Programming - FOUNDATIONS & COMPREHENSIVE REVIEW!
Metropolis-Hastings - VISUALLY EXPLAINED!
Просмотров 32 тыс.2 года назад
Metropolis-Hastings - VISUALLY EXPLAINED!
Markov Chains - VISUALLY EXPLAINED + History!
Просмотров 13 тыс.3 года назад
Markov Chains - VISUALLY EXPLAINED History!
Monte Carlo Methods - VISUALLY EXPLAINED!
Просмотров 4,3 тыс.3 года назад
Monte Carlo Methods - VISUALLY EXPLAINED!
Conjugate Prior - Use & Limitations CLEARLY EXPLAINED!
Просмотров 3,1 тыс.3 года назад
Conjugate Prior - Use & Limitations CLEARLY EXPLAINED!
How to Read & Make Graphical Models?
Просмотров 2,9 тыс.3 года назад
How to Read & Make Graphical Models?
Posterior Predictive Distribution - Proper Bayesian Treatment!
Просмотров 6 тыс.3 года назад
Posterior Predictive Distribution - Proper Bayesian Treatment!
Sum Rule, Product Rule, Joint & Marginal Probability - CLEARLY EXPLAINED with EXAMPLES!
Просмотров 6 тыс.3 года назад
Sum Rule, Product Rule, Joint & Marginal Probability - CLEARLY EXPLAINED with EXAMPLES!
Noise-Contrastive Estimation - CLEARLY EXPLAINED!
Просмотров 10 тыс.3 года назад
Noise-Contrastive Estimation - CLEARLY EXPLAINED!
Bayesian Curve Fitting - Your First Baby Steps!
Просмотров 6 тыс.3 года назад
Bayesian Curve Fitting - Your First Baby Steps!
Maximum Likelihood Estimation - THINK PROBABILITY FIRST!
Просмотров 6 тыс.3 года назад
Maximum Likelihood Estimation - THINK PROBABILITY FIRST!
How is this different from U-net? I think they're pretty similar if you think that in the U-net you're going down in the encoder, up in the decoder and sideways with the skip connections. It's like an upside-down U-net
Professor Kaiming He is the GOD of Deep Residual Networks .
How can we use these (predictions_box, predictions_obj, predictions_cls) information from the decoder and create visualizations on input image ?
Thank a lot, this was an amazing explanation! just a question. Why do we need anchor boxes to be a pre-set value when we can just use the original bbox values? Like we use the center of the original bbox and its W and H values. I dont understand this
This ground-up approach is excellent 🙂Thank you for explaining...
Thank you for posting this great video! At 3:53, why did you use a "squared" Euclidean distance, instead of an Euclidean distance? I wonder if you use an Euclidean distance, the properties of the "squared" Euclidean distance are the same?
Amazing !
Very intuitive explanation. Thank you.
Excellent overview. Highly appreciated.
Amazing, thx a lot.
What a wonderful explanation
Thank you so much! Your video really helped me understand the method and remember it, which is equally important. 🙂
It was fantastic. The most informative video of KL divergence
I rarely comment on these kinds of videos but this really was a great exposition, well done.
That's a great explanation. Thanks a lot!
Can you turn on the transcript for this! Great explanation!
He is good! Very good to say, for example, we want the average difference, but when talking about rv we talk about expected value ... . And many other very careful explanations.
Thanks for sharing the knowledge
Kudos for explaining very well. I wish to comment on just one thing. @12:08 I could not see the two colors (red and blue) clearly in the video. Maybe the picture can be made to have white background to make the colors more obvious.
Your videos are very helpful, we want more on object detection! Please sir 🙌 🙏
Great video!
I have 2 questions. How are the 1X1 and 3X3 CNN used trained to obtain the weight parameters? Also shouldn't 3X3 with stride 1 change the dimension, though it keeps the number of channels the same the size of the output feature would have changed and reduced by 2
Your videos are amazing, very clear and concise explanations!
This is the best series I have watched on explanation of object detection algorithms. Also, your approach of asking fundamental questions like "Why in this case, a metric of evaluation can't be used as a loss function" and many more such questions you addressed were so insightful. Really grateful for the efforts you've put in here. Thank you. 🙏🙏
At 11:02, instead of "the first rows of the first four channels will be for box coordinates", do you intend to say "the first cells of the first four channels will be for box coordinates"?
Thank you very much for your video. But I have a question: when g(x) is a function U(a,b), the probability of choosing Y which obeys g(x) is the same for all Y in (a,b). But when the bounding function is Gaussian or something else (i.e. when simulating g(x) we cannot guarantee the probability of selecting each point is the same), does it affects the probability of selecting X which obeys f( x) ? ( Because if the simulation of Y is not equivalent then even if the next steps are effective, we cannot guarantee that we give equal chances to all points X when starting before "reject or accept")
Simply beautiful ❤️
Thanks for the lecture sir! I have a question at 4:54, how did you expand that E[log_p_theta(x)] into Integral(q(z|x)log_p_theta(x)dz)? Thanks!
Thank you so much, First I read the 1st chapter of this book and then I listened to your video. You gave a superb explanation and cleared all doubts. Thanks for your community service :)
Amazing explanation!
Thank you! One request -- can you explain the reason behind the equivalence between assuming that the target variable is normally distributed and the assumption that the errors are normally distributed. While I understand that the two assumptions are simply the two sides of the same coin, the mathematical equivalence between them appeared to me like something that is implicitly assumed in moving from part 2 video to part 3 video.
Very articulated explanations, really appreciate it! thanks!
❤❤🙏🏽🙏🏽🙏🏽 thanks and subscribed
Thank you for your hard work, which enables us to understand crystal clear. Thanks a lot ❤❤❤
Hi, I have got micrsoft form recognizer api which gives bounding box of 8 coordinates for a given class, how to draw bounding box using that. for eg: bounding_regions=[BoundingRegion(page_number=1, polygon=[Point(x=33.0, y=496.0), Point(x=169.0, y=496.0), Point(x=168.0, y=532.0), Point(x=33.0, y=532.0)])] they haven't provided in the documentation as well, if you could help, I would appreciate it. I have converted it into list like this [33.0, 496.0, 169.0, 496.0, 168.0, 532.0, 33.0, 532.0] but don't how to plot.
Excellent
Thank you for these very clear and visually efficient explanations. I'll make sure to use these concepts in my PhD work !
I thought temperature was like getting a fewer and saying random things:)
Depends on the context. Here it is about logits. In LLM apis it is to control the stochasticity/randomness.
The best! Thank you sir
At 5:01 could you please explain why is it [1,5] and not [5,1]? Shouldn't the coordinates be in (x,y) format?
No the coordinates are in [y,x] … nothing specific about it as such, just a convention used in all object detection models.
Thank you a lot for your videos! Selection of subjects in your series is excellent, every tutorial offers very interesting information.
🙏
One stupid question here, Why we were interested in finding max joint probability, in the first place?? were there any other way to find w and beta??
It learns the parameter right?
At 6:39, the distribution p_\theta(x|z) cannot have mean mu and stddev sigma as the mean and std dev live in the latent space (the space of z) and x lives in the input space.
Watching your videos keeps reminding me of the phrase “a picture is worth a thousand words”, to which I want to add “ a great picture is worth thousands in gold”. Many times I had to freeze the video to let a particular moment sink in, because I couldn’t believe the insight that picture brings out . ❤❤❤
I am grateful to your lectures ❤ what a wonderful service you’ve done to all the learners
So, in-depth and with those visualization it is a grate learning experience
In real life we don't know Target distribution - f(x). How did you calculated alpha for various sample points ? f(Xt+1)/f(Xt)
We are okay with imperfections as long as they are useful to us ... great wisdom🙏
Amazing. Thanks for posting.