===== Labs and Seminars ===== Two types of labs (tutorials) will be proposed for the course (alternating): * practical labs in which students will implement selected methods discussed in the course and experiment with them, * theoretical labs in which students will discuss solutions of theoretical assignments (made available before the class). ==== Schedule ==== ^ Date ^ Topic ^ Teachers ^ Assignment ^ Notes ^ | 17.02.2022 ^ [[courses:bev033dle:labs:Lab0_ddescent:start | Lab 1: Preparations, Double Descent ]] | AS | |[[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=4fe95e0d91996126e5b2d89d9f98ed679e01c930-1645091701608 | rec 102]] [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=082716b51a5f5fb1155b931cdfd3945f2e32fcba-1645178101319| rec 103]] | | 24.02.2022 ^ Seminar 1 (lecture 1) | BF | {{:courses:bev033dle:labs:sem-neurons-nets.pdf | assignments}} | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=7a16cc561c48f31a86ff9a7058e3ed51f25ffe39-1645696502009| rec 102]] [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=92a226c0348b4388c4a32c10c48d134ec8edeb2a-1645782601618 | rec 103]] | | 03.03.2022 ^ [[courses:bev033dle:labs:Lab1_backprop:start | Lab 2: Backpropagation, Computational graph ]] | AS | | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=9949c7d960b32f10810316141d31df2242502341-1646301001544| rec 102]] [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=ad4d0e66521b3460988747edc6d195211fd9c662-1646387401912| rec 103]] | | 10.03.2022 ^ Seminar 2 (lectures 2,3) | BF | {{:courses:bev033dle:labs:sem-nets-backprop.pdf | assignments}} | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=4d72bd523d1cd49d80f771eccdff932579221636-1646992201140 | rec 103]] | | 17.03.2022 ^ [[courses:bev033dle:labs:Lab2_pytorch:start | Lab 3: Pytorch, project pipeline, CNN, performance metrics ]] | AS | | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=7447ad90d42cea1436242d8cc86e1c59bd5bceea-1647510302036| rec 102]] [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=3d706a4619e28d84d6096f3b173809e54a277184-1647597001255| rec 103]] | | 24.03.2022 ^ Seminar 3 (lectures 4,5) | AS | {{ :courses:bev033dle:labs:sem-sgd-cnn.pdf | assignments}} | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=b5eeb162dc043c8597d041a344478cb69711a359-1648201503309 | rec 103]] | | 31.03.2022 ^ [[courses:bev033dle:labs:Lab3_finetune:start | Lab 4: Pre-trained CNN Fine-tuning with regularization, BN]] | AS | | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=9ff33e4bb571d23eceb4262770fbf7a13707cd4e-1648716301391 | rec 102]] | | 07.04.2022 ^ Seminar 4 (lectures 6,7) | BF | {{ :courses:bev033dle:labs:sem-init-reg.pdf | assignments}} | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=b1daacc2c2f06e62a8abdfd93d7057f88e5e34a7-1649321401083 | rec 102 ]] | | 14.04.2022 ^ [[courses:bev033dle:labs:Lab4_visualization:start | Lab 5: CNN visualization & adversarial patterns]] | BF | | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=9a816cff1f92e0c1ddd2ed4e4d5af1e2aa459863-1649926201865 | rec 102]] | | 21.04.2022 ^ Seminar 5 (lectures 8,9) | AS | {{ :courses:bev033dle:labs:sem-adapt-advers.pdf | assignments}}| [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=94acb0079e4a0ac7587e3b2002f06fa00fe1e9b3-1650530701460 | rec 102 ]] | | 28.04.2022 ^ [[courses:bev033dle:labs:Lab6_metric:start | Lab 6: Metric learning ]] | AS | | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=e5f7c0855b665ec2385bbd2860fd89673184dbcd-1651135501785 | rec 102 ]] | | 05.05.2022 ^ Seminar 6 (lectures 10,11) | AS | {{ :courses:bev033dle:labs:sem-metric-kl-svi.pdf |assignments}} | no record | | 12.05.2022 ^ [[courses:bev033dle:labs:Lab7_VAE:start | Lab 7: VAE ]] | BF | | [[https://bbb04.felk.cvut.cz//playback/presentation/2.0/playback.html?meetingId=4a34f983c078d69d5d7ce51fa0583172df60eb97-1652345101235 | rec 102 ]] | | 19.05.2022 ^ Seminar 7 (lecture 12) | BF | {{ :courses:bev033dle:labs:sem-vae.pdf |assignments}}| no record | ==== Seminars ==== The seminar assignments are published 1 week in advance before the seminar. You are expected to prepare for it at home. We discuss the problems and solutions in the class. You are not required to submit you solutions, but if you solved a problem you will be invited to present it in the class. Seminars are not scored by points but they are important for gaining technical understanding, which will be finally evaluated in the written exam. Examples of problems with solutions: {{ :courses:bev033dle:labs:examples.pdf |}} (to be updated) ==== Labs ==== The solutions of the practical labs have to be submitted using the [[http://cw.felk.cvut.cz/upload/|upload system]] * Your task will be to program a solution of the assigned problems. You have to hand out your code and a report. The report has to contain only answers to the assignments (nothing else). * The programming language is Python/PyTorch. * The deadline for submitting your solutions will be 4 weeks after the date of assignment. This is a hard deadline. * Not submitting a lab is equivalent to getting 0 points. You need at least of 50% of total lab points to pass. ==== Submission Regulations ==== You may choose from the following submission variants: - Report in pdf and Python source code - Annotated Jupyter notebook with inline results and Python source code if applicable Please do not submit data and any other redundant files. Sharing code that is not a required part of the assignment is permitted, for example additional visualization code or test cases for debugging.