The assignments are interesting, sometimes time consuming, in particular the last assignment and course project. The material is also very interesting, and quite a bit of it is SOTA toward the end. The lectures are OK, the professor mainly reads from slides, but he is clearly passionate about the topic.

That said, the exams are either intentionally designed for you to fail and generate a curve, or designed and evaluated in the laziest manner possible. If you do not EXACTLY match what their predefined rubric states, you will receive a zero. This includes rederiving formulas which were derived in class (on an open-note exam!) and matching exact keywords in short answer problems. On top of this, the course staff chose deliberately to hide the correct solutions and rubrics on Gradescope to discourage requesting regrades on solutions which appeared to be fully correct. The final grade is also not curved whatsoever (had 89% raw score, received a B+, scored over 100% on all assignments/project). So your entire grade comes down to this sketchy exam where despite knowing 80-90% of the material, you can easily receive a 60% or lower.

If you value your GPA, audit this class. Material is interesting, projects are great, but dealing with this nonsense final is not worth the risk.

Interesting material, but the lectures were pretty confusing to understand. The homeworks take a while to do just because of the training time, and I didn't they were particularly helpful for understanding the material. I thought the final exam was pretty fair. The last project is like a class-wide competition to see who can train the best model

As the lead professor of a Computer Vision research lab in UCLA, Professor Zhou is extremely knowledgeable in the field. While lecture slides are dense with content, they provide a brilliant overview of Deep Learning and CV, including state-of-the-art models such as ResNet, Vision Transformers and Diffusion. Homework assignments are challenging but fun, where we had to make use of PyTorch to build above-mentioned models from scratch. Whenever I struggle to debug, my TA, Zhizheng, was really helpful on Piazza. There was also a final project where we had to read research papers and compare 3 different CV models, which was a great opportunity to gain an in-depth understanding of CV models. The only downside was the tough final exam, but it turned out well eventually as he curved our overall grades. For anyone interested in Deep Learning and Computer Vision, I would highly recommend this class.

Take note that while there are no enforced pre-requisites, this class does require you to have substantial prior knowledge in Machine Learning, Multivariable Calculus and Linear Algebra. Otherwise, this class could be quite challenging and fast-paced.

Enjoyable class where you can learn about many Computer Vision/Neural Network concepts. Lectures were not recorded but the slides were posted.
4 Colab Assigments that were pretty easy
1 group presentation + report on a computer vision topic that was very easy
No midterm but a final that was 50 percent of the grade, the final was quite long and difficult imo, it covered the entire class.
Grades were slightly curved up

Overall - super nice introduction class to general machine learning + computer vision. The lectures were nice in that they went over a lot of history as well as the professor's own experiences with computer vision over the years. The lectures were very high-level theory, whereas assignments had more technical implementation based assignments using PyTorch/its libraries.

The assignments are a little difficult/time consuming due to lack of clarity, but they are definitely doable with questions answered by TAs on Piazza, and it is definitely easy to achieve a good grade on them. The exams were not super easy (but nothing too unexpected) - and the class was curved at the end.