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.