# Stanford University CS231n: Deep Learning for Computer Vision https://cs231n.stanford.edu/ [CS231n Home](https://cs231n.stanford.edu/index.html) * [**Schedule**](https://cs231n.stanford.edu/schedule.html) * [**Assignments**](https://cs231n.stanford.edu/assignments.html) * [**Project**](https://cs231n.stanford.edu/project.html) * [**Office Hours**](https://cs231n.stanford.edu/office_hours.html) * [**Lecture Videos**](https://canvas.stanford.edu/courses/222471/external_tools/69960) * [**Ed**](https://edstem.org/us/courses/97362/discussion) * [**Useful Notes**](https://cs231n.github.io/) [ ![](https://cs231n.stanford.edu/img/svl_logo.png) ](http://svl.stanford.edu) [ ![](https://cs231n.stanford.edu/img/stanfordlogo.jpg) ](http://stanford.edu/) # CS231n: Deep Learning for Computer Vision ### Stanford - Spring 2026 *This network is running live in your browser The Convolutional Neural Network in this example is classifying images live in your browser using Javascript, at about 10 milliseconds per image. It takes an input image and transforms it through a series of functions into class probabilities at the end. The transformed representations in this visualization can be loosely thought of as the activations of the neurons along the way. The parameters of this function are learned with backpropagation on a dataset of (image, label) pairs. This particular network is classifying [CIFAR-10](http://www.cs.toronto.edu/~kriz/cifar.html) images into one of 10 classes and was trained with [ConvNetJS](http://cs.stanford.edu/people/karpathy/convnetjs/). Its exact architecture is [conv-relu-conv-relu-pool]x3-fc-softmax, for a total of 17 layers and 7000 parameters. It uses 3x3 convolutions and 2x2 pooling regions. By the end of the class, you will know exactly what all these numbers mean. ## Course Description Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, localization and detection. Recent developments in neural network (aka “deep learning”) approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into the details of deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. During the 10-week course, students will learn to implement and train their own neural networks and gain a detailed understanding of cutting-edge research in computer vision. Additionally, the final assignment will give them the opportunity to train and apply multi-million parameter networks on real-world vision problems of their choice. Through multiple hands-on assignments and the final course project, students will acquire the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks. Previous Offerings [[Winter 2015]](http://cs231n.stanford.edu/2015) [[Winter 2016]](http://cs231n.stanford.edu/2016) [[Spring 2017]](http://cs231n.stanford.edu/2017) [[Spring 2018]](http://cs231n.stanford.edu/2018) [[Spring 2019]](http://cs231n.stanford.edu/2019) [[Spring 2020]](http://cs231n.stanford.edu/2020) [[Spring 2021]](http://cs231n.stanford.edu/2021) [[Spring 2022]](http://cs231n.stanford.edu/2022) [[Spring 2023]](http://cs231n.stanford.edu/2023) [[Spring 2024]](http://cs231n.stanford.edu/2024) [[Spring 2025]](http://cs231n.stanford.edu/2025) ### Instructors [ ![](https://cs231n.stanford.edu/img/fei-fei.jpg) Fei-Fei Li ](https://profiles.stanford.edu/fei-fei-li) [ ![](https://cs231n.stanford.edu/img/ehsan.jpg) Ehsan Adeli ](https://stanford.edu/~eadeli/) [ ![](https://cs231n.stanford.edu/img/justin.jpg) Justin Johnson ](https://web.eecs.umich.edu/~justincj/) [ ![](https://cs231n.stanford.edu/img/zane.jpg) Zane Durante ](https://zanedurante.github.io) [ ![](https://cs231n.stanford.edu/img/tiange.jpg) Tiange Xiang ](https://ai.stanford.edu/~xtiange/) ### Teaching Assistants [ ![](https://cs231n.stanford.edu/img/aditesh_kumar.png) Aditesh Kumar (Head CA) ](https://cs.stanford.edu/~aditesh/) [ ![](https://cs231n.stanford.edu/img/keshigeyan_chandrasegaran.png) Keshigeyan Chandrasegaran ](http://cs.stanford.edu/~keshik/) [ ![](https://cs231n.stanford.edu/img/mark_endo.jpg) Mark Endo ](https://web.stanford.edu/~markendo/) [ ![](https://cs231n.stanford.edu/img/aniket_gupta.jpg) Aniket Gupta ](https://www.linkedin.com/in/ganiket/) [ ![](https://cs231n.stanford.edu/img/Wenlong_Huang.jpg) Wenlong Huang ](https://wenlong.page/) [ ![](https://cs231n.stanford.edu/img/chaitanya.jpg) Chaitanya Patel ](https://chaitanya100100.github.io/) [ ![](https://cs231n.stanford.edu/img/yash_shah.png) Yash Shah ](https://ynshah3.github.io) [ ![](https://cs231n.stanford.edu/img/karan_singh.png) Karan Singh ](https://karanps.com) [ ![](https://cs231n.stanford.edu/img/baileytrang.png) Bailey Trang ](https://baileytrang.github.io/) [ ![](https://cs231n.stanford.edu/img/hengyu.jpg) Heng Yu ](https://heng14.github.io/) [ ![](https://cs231n.stanford.edu/img/koven_yu.jpg) Koven Yu ](https://kovenyu.com) [ ![](https://cs231n.stanford.edu/img/cris.jpeg) Cristóbal Eyzaguirre ](https://ceyzaguirre4.github.io/) [ ![](https://cs231n.stanford.edu/img/fangrui_huang.jpeg) Fangrui Huang ](https://www.linkedin.com/in/fangrui-huang-762376205) [ ![](https://cs231n.stanford.edu/img/eris_zhang.jpg) Eris Zhang ](https://eriszhang.github.io/) [ ![](https://cs231n.stanford.edu/img/favour_nerrise.jpg) Favour Nerrise ](https://www.favournerrise.com/) [ ![](https://cs231n.stanford.edu/img/yalcin_tur.jpeg) Yalcin Tur ](https://www.linkedin.com/in/yalcintur/) [ ![](https://cs231n.stanford.edu/img/june_zheng.jpg) June Zheng ](https://www.linkedin.com/in/yujun-june-zheng32) [ ![](https://cs231n.stanford.edu/img/YangZheng.jpg) Yang Zheng ](https://y-zheng18.github.io/) ## Course Logistics * **Lectures:** Tuesdays and Thursdays 12:00-1:20PM Pacific Time at [NVIDIA Auditorium](https://goo.gl/maps/hRjQYd6MqxB2). * **Lecture Videos:** Will be posted on [Canvas](https://canvas.stanford.edu/courses/222471) 'Panopto Course Videos' tab shortly after each lecture, accessible to enrolled Stanford students. While they are not reflective of this offering CS231n, recordings from previous years are [available on YouTube](https://www.youtube.com/playlist?list=PLoROMvodv4rOmsNzYBMe0gJY2XS8AQg16). * **Office Hours:** We will be holding a mix of in-person and Zoom office hours. You can find a full list of times and locations [on the calendar](https://cs231n.stanford.edu/office_hours.html). * **Contact:** Announcements and all course-related questions will happen on the [Ed](https://edstem.org/us/courses/97362/discussion) forum - post there for the quickest response. For external enquiries, emergencies, or personal matters that you don't wish to put in a private post, you can email us at cs231n-staff-spr26@stanford.edu. ## Coursework ### Prerequisites * Proficiency in Python All class assignments will be in Python (and use numpy) (we provide a tutorial [here](http://cs231n.github.io/python-numpy-tutorial/) for those who aren't as familiar with Python). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Javascript) you will probably be fine. * College Calculus, Linear Algebra (e.g. MATH 19, MATH 51) You should be comfortable taking derivatives and understanding matrix vector operations and notation. * Basic Probability and Statistics (e.g. CS 109 or other stats course) You should have an intuitive understanding of basic probability, gaussian distributions, mean, standard deviation, etc. ### Assignments (45%) See the [Assignments](https://cs231n.stanford.edu/assignments.html) page for details regarding assignments, late days and collaboration policies. ### Midterm (20%) Detailed information regarding the midterm will be made available as an announcement on Ed in the coming weeks. ### Final Project (35%) See the [Project](https://cs231n.stanford.edu/project.html) page for more details regarding the final course project. ### Participation (3% extra credit) Active participation greatly improves the learning experience for all students! Teaching staff will make note of outstanding contributions in Lecture, Section, Office Hours, on EdStem, and elsewhere. The most commended student will receive 3% extra credit, and other outstanding contributors will receive a fraction of that proportionate to their contribution. ### Regrade Requests If you believe that the course staff made an objective error in grading, you may submit a regrade request on Gradescope within **3 days** of the grade release. Your request should briefly summarize why the original grading was incorrect. Note that staff may regrade the entire submission, so it is possible for you to lose more points than you gain if a mistake was overlooked in the first time. ### Late Policy * All students have 4 free late days for the quarter. * You may use up to 2 late days per assignment. * Upon use, each late day provides a 24 hour extension with no penalty. * You may use late days for the assignments, project proposal, and project milestone check-ins. * You may not use late days for the final project report. * Once you have exhausted your free late days, we will deduct a late penalty of 25% per additional late day. * For example: you submit A1 one day late, submit A2 three days late, and submit A3 two days late. You receive no penalty for A1, and exhaust one of your free late days. For A2 the first two late days exhaust two of your free late days; the third day late incurs a 25% penalty. For A3 the first late day exhausts your final free late day; the second late day incurs a 25% penalty. * For the project proposal and milestone, we will deduct late days from each group member independently. The students receive support from [Modal](https://modal.com/), [AWS](https://aws.amazon.com/), and [GCP](https://cloud.google.com/) through cloud credits for final course projects. [ ![Modal](https://cs231n.stanford.edu/img/modal-logo.svg) ](https://modal.com/) [ ![AWS](https://cs231n.stanford.edu/img/aws-logo.svg) ](https://aws.amazon.com/) [ ![Google Cloud](https://cs231n.stanford.edu/img/gcp-logo.svg) ](https://cloud.google.com/) ### FAQ Academic accommodations: If you need an academic accommodation based on a disability, you should initiate the request with the [Office of Accessible Education (OAE)](https://oae.stanford.edu/). The OAE will evaluate the request, recommend accommodations, and prepare a letter for faculty. Students should contact the OAE as soon as possible and at any rate in advance of assignment deadlines, since timely notice is needed to coordinate accommodations. It is the student’s responsibility to reach out to the teaching staff regarding the OAE letter. Please create a private post on Ed in the Accommodations category with your letter attached. Can I take this course on credit/no cred basis? Yes. Credit will be given to those who would have otherwise earned a C- or above. Can I audit or sit in? In general we are very open to auditing if you are a member of the Stanford community (registered student, staff, and/or faculty). Out of courtesy, we would appreciate that you first email us or talk to the instructor after the first class you attend. Can I work in groups for the Final Project? Yes, in groups of up to three people. I have a question about the class. What is the best way to reach the course staff? Almost all questions should be asked on Ed. If you have a sensitive issue, you can email the below address to reach the instructors and head TA directly: cs231n-staff-spr26@stanford.edu. Can I combine the Final Project with another course? Yes, you may. Please read the Honor Code section in the [Project](https://cs231n.stanford.edu/project.html) page.