https://cw.fel.cvut.cz/b211/ 2026-04-20T16:50:51+0200 https://cw.fel.cvut.cz/b211/ https://cw.fel.cvut.cz/b211/lib/tpl/bulma-cw/images/favicon.ico text/html 2021-10-30T18:14:25+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/classification?rev=1635610465&do=diff Classification - Materials In order to learn on your own, you should be able to program answers to questions below every topic. Some video materials are taken from Deep learning course of Andrew Ng from Stanford. spacearrows Mnist Classification (4.Lab) Starting files and tutorials, how to work with basic pytorch$Loss = Training Loss + \lambda * \sum(w_i^2)$ text/html 2021-09-17T12:50:09+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/hw01_pybullet?rev=1631875809&do=diff HW 01 - Quadruped locomotion using random search [ Gif] Your first homework will be to write a neural network and optimization algorithm which makes a quadruped model move towards a given location. You will not be using any more advanced techniques like gradient descent in this case because the evaluation function is not differentiable with respect to the parameters. Instead you will implement a simple heuristic random search algorithm which will optimize the task. The point of this homework i… text/html 2021-11-03T12:59:11+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/hw02_classification?rev=1635940751&do=diff HW 02 - Image recognition Your second homework will be Image recognition. For this task, we have created our own dataset, which is based on ImageNet. The homework will be introduced in the labs in the 5th week, we will try to clear any doubts in Video. Dataset $$pts_{individual} = 12\times\text{clip}(\frac{acc - 0.4}{0.6 - 0.4}, 0, 1)$$ text/html 2021-11-24T17:19:21+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/hw04?rev=1637770761&do=diff HW 04 - Object Detection The lab presentation related to this homework is recorded online at this link. Please see the video before attending the labs. The labs will be mainly for consultation. Goals The goal of this homework is to implement, train and evaluate the object detector. The input of this neural network is an RGB image, and the output will be the position of the survivor's torso in the image with a corresponding bounding box.\begin{align*} loss = \lambda_\textbf{coord}& \sum_{i … text/html 2021-11-29T12:43:33+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/hw05?rev=1638186213&do=diff HW 05 - Generative Networks This lab is lectured by David Coufal. The following tutorial links to labs and homework page. Data can be downloaded on the homework page or [ here]. Submission You are going to upload the dcgan3X.py only. The final score consist of linear scaling from the maximum amount of PTS acquired from the tasks. The maximum amount of score for homework is 13.33 (one third of total 40 points for all HW3,HW4,HW5). text/html 2021-11-28T11:59:09+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/hw3_-_lidar_segmentation?rev=1638097149&do=diff HW 03 - Lidar Segmentation Semantic Segmentation The goal of semantic segmentation is to classify every point in the input data to chosen classes in a supervised way (from labels). We will not use RGB images, but Lidar point clouds from autonomous driving scenarios, see illustration images, how it looks like. Good overview of the segmentation can be found: $IoU = \frac{TP}{TP + FP + FN} $ text/html 2021-10-06T18:30:24+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/lab_3?rev=1633537824&do=diff Lab 3 - MLE, Computational graph and Backpropagation In this lab, we are going to test your knowledge about the math behind neural networks. These simple exercises are application of theory in lecture [ Lecture] (slides 10-62). Tutorial solution to the first two exercises is $$ y = \sin(\textbf{w}^T~\textbf{x}) - b $$$$\textbf{x} = [2, 1] , ~\textbf{w} = [\pi/2, \pi] ,~ b = 0 ,~ \tilde{y} = 2$$$\frac{\partial y}{\partial \textbf{w}}$$L_2$$\tilde{y}$$\frac{\partial L}{\partial \textbf{w}}$$\alph… text/html 2021-10-17T14:32:45+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/lab_4?rev=1634473965&do=diff Lab 4 1) Neural Net training is a leaky abstraction (requires cognitive load) based on: Andrej Karpathy blog follow the Guide to practice on your own It is allegedly easy to get started with training neural nets. Numerous libraries and frameworks take pride in displaying 30-line miracle snippets that solve your data problems, giving the (false) impression that this stuff is plug and play. It’s common see things like: text/html 2021-10-20T15:33:01+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/lab_5?rev=1634736781&do=diff Lab 5 1) Convolutional Layer You are given input feature map x and kernel w: $$ \textbf{x} = \left(\begin{array}{ccc} 1 & 0 & 2 \\ 2 & 1 & -1 \\ 0 & 0 & 2 \\ \end{array}\right) ,~ \textbf{w} = \left(\begin{array}{cc} 1 & -1 \\ 0 & 2 \end{array}\right) $$ Stride denotes length of convolutional stride, padding denotes symetric zero-padding, max denotes maxpool layer (takes maximum over the kernel window). Compute outputs of following layers:$$1)~ conv(~\textbf{x}, \textbf{w}, ~stride=1, ~p… text/html 2021-12-15T16:13:22+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/lab_6?rev=1639581202&do=diff Reinforcement learning labs We will implement the A2C algorithm for balancing the cartpole system. The gym-like continuous-cartpole environment, which is part of the template, provides rewards for keeping the pendulum in an upward position. The interface corresponds to the usual gym environment: text/html 2021-12-20T09:59:40+0200 Anonymous (anonymous@undisclosed.example.com) https://cw.fel.cvut.cz/b211/courses/b3b33vir/tutorials/start?rev=1639990780&do=diff Labs datum č.t. S/L náplň Učitel Tutoriály  Materiály 20.09.2021 - 23.09.2021 1 L Python, Numpy, Pytorch intro - Home exercise! NumPy & PyTorch tutorial 27.09.2021 - 29.09.2021 2 S Optimization Task - Blackbox Legged Robot KZ HW1 4.10.2021 - 6.10.2021