[[https://fel.cvut.cz/cz/education/rozvrhy-ng.B212/public/html/predmety/46/84/p4684506.html|Schedule (CZ course)]] [[https://fel.cvut.cz/cz/education/rozvrhy-ng.B212/public/html/predmety/46/85/p4685206.html|Schedule (EN course)]] [[https://cw.felk.cvut.cz/upload/|Upload system]] [[https://cw.felk.cvut.cz/forum/forum-1875.html|Discussion forum]] ====== Computer Vision Methods Labs ====== ===== Labs plan ===== Labs are organized in four main topics: Correspondence problem, Indexing and image retrieval, Object tracking, Convolutional neural networks. Each topic is covered by approximately two to four labs. \\ /*Zoom link for the remote labs (EuroTeQ project students) on Thursday 14:15 https://feectu.zoom.us/j/97922104602 */ ^ Week ^ Date ^ Topic ^ Teacher ^ Recording ^ | 1 | 21.2.| [[courses:mpv:labs:1_intro:start|Introduction to Image Processing in python using PyTorch]]. | DM | [[https://drive.google.com/file/d/1tyeNOc2g6Rl3sP3j8Ruirl7K70GmA6ik/view?usp=sharing|recording 2022]] | | 2 | 28.2. | [[courses:mpv:labs:debugging_pytorch_code| Debugging pytorch code]]. | DM | | | 3 | 6.3. | [[courses:mpv:labs:2_correspondence_problem:start| Correspondence problem I, detection of the interest points]]. | DM |[[http://cmp.felk.cvut.cz/~mishkdmy/MPV2022/MPV_lab_detector_2022_03_10.mp4|recording 2022]] | | 4 | 13.3. | [[courses:mpv:labs:2_correspondence_problem:start#computing_local_invariant_description| Correspondence problem II, computing local invariant description]]. | DM |[[http://cmp.felk.cvut.cz/~mishkdmy/MPV2022/2022-03-17-MPV_lab_descriptor.mp4|recording 2022]] | | 5 | 20.3. | [[courses:mpv:labs:2_correspondence_problem:start#correspondence_problem_and_ransac| Correspondence problem III, finding tenative correspondences and RANSAC]]. | DM | [[http://cmp.felk.cvut.cz/~mishkdmy/MPV2022/MPV_lab_RANSAC_Matching_24_03_2022.mp4|recording 2022]] | | 6 | 27.3. | [[courses:mpv:labs:2_correspondence_problem:start| Correspondence problem, summary]]. | DM | | | 7 | 3.4. | [[courses:mpv:labs:3_indexing:start#bow_image_representation_tf-idf_weighting|Image Retrieval I, BoW TF-IDF]] | PS | | | 8 | 10.4. | [[courses:mpv:labs:3_indexing:start#fast_spatial_verification_query_expansion|Image Retrieval II, fast spatial verification.]] | PS| | | 9 | 17.4. | [[courses:mpv:labs:5_convolutional_networks:start|Convolutional Neural Networks: training a classifier]] | LN |[[https://drive.google.com/file/d/1P1I14LG2PBZuRbs7LFwi6sU7UMpo-7IT/view?usp=sharing|recording 2022]] | | 10 | 24.4. | [[https://gitlab.fel.cvut.cz/mishkdmy/mpv-python-assignment-templates/-/blob/master/debugging_examples/Debugging-learning-pytorch-code.pdf|Convolutional Neural Networks II: debugging training process]] | LN | | | 11 | 1.5. | State Holiday | | | 12 | 9.5. (Thu) | [[Deep metric learning | Deep metric learning]] | PS | | | 13 | 15.5. | [[courses:mpv:labs:4_tracking:start|Tracking I, Kanade-Lucas-Tomasi tracking (KLT tracker)]] | OD | | | 14 | 22.5. | [[courses:mpv:labs:4b_tracking:start|Tracking II, KCF tracker. Finishing the assignments]]| OD | | Labs will be accompanied with a simple programming task. Detailed specification of the tasks is described in each of the labs. Students will upload their results and their codes through the [[https://cw.felk.cvut.cz/upload/|BRUTE]] system. Each lab will usually consists of three parts: - **Discussion on the last lecture**. Students will be free to ask any questions related to the last lecture. At the end of this session, a teacher will pose a question to a volunteer/random student. If the student answers correctly, he/she will get a single //bonus point//. - **Working on the current task**. Students are free to ask any specific questions, discuss their current results, resolve any programming issues. - **Short introduction of the next task**. The teacher will briefly introduce the next problem, give some hints and answer possible questions. /* Each lab will be accompanied with a programming task. The programming tasks are due to the next lab (midnight of the Tuesday before the lab) and should be solved regularly through the semester and uploaded to the upload system. Detailed specifications of the tasks are described in each of the labs. Please, read the description of the task **before** the lab. The upload system for uploading and checking your assignements is available [[https://cw.felk.cvut.cz/upload/|here]].\\ */ ===== Assessment ===== You are obliged to carry out all programming tasks at least a minimal required quality. All tasks must be carried out individually! You are free to discuss the problems with your colleagues, however the code must be written strictly by yourself. See [[https://cw.fel.cvut.cz/wiki/help/common/plagiarism_cheating|plagiarism]] if you are unsure what is allowed. ===== Evaluation Policy ===== The points from the labs will contribute to 50 percent of your course evaluation. \\ There will be **11 tasks** awarded with points throughout the semester (a new task will be given out every week in the lab, with the exception of two labs which are intended to help students with debugging). On top of these tasks, there will also be ability to get **bonus points** in some labs. \\ Each task has a **deadline of 2 weeks and 1 day**. \\ Each task uploaded after the due date is penalized as follows: 0.015pts for every hour after the deadline (= 2.5pts/7days)\\ The maximum penalty is 60% of the maximum points, e.g. for the task uploaded in 1 month late, you will get < =40%. **Experiment.** For the first group of labs -- image correspondences -- there will be no penalties for late submission. However, if the labs completion statistics show that it does not work, we will bring penalties back for the rest of the assignments. ===== Useful Links ===== [[http://vision.stanford.edu/teaching/cs223b/video.html|Computer vision: Facts & Fiction series]]\\ [[http://www.andrew.cmu.edu/course/16-720/|Computer Vision course at CMU]]\\ [[https://cw.fel.cvut.cz/wiki/courses/mpv/labs/general_info|PyTorch & Python development]] | Course Assistants |||| | [[https://cmp.felk.cvut.cz/~neumalu1/|{{:courses:mpv:labs:lukasneumann2.jpg?90x120}}]] | [[http://cmp.felk.cvut.cz/~mishkdmy/|{{:courses:mpv:labs:dmytro2.jpg?90x120}}]] | {{:courses:mpv:labs:pavelsuma.jpg?90x120}} | [[http://cmp.felk.cvut.cz/~drbohlav/|{{http://cmp.felk.cvut.cz/~drbohlav/ondrej_drbohlav.jpg?90x120}}]] | | Lukáš Neumann | Dmytro Mishkin | Pavel Šuma | Ondřej Drbohlav \\ (lead) |