Hi, OK. If you want to get just this appearing in your certificate, then we can do this. Send me the pdf filled out I'll print it and scan it again. The students can come optionally to you for this sheet, I'll mention it to the students tomorrow. Regards, Jochen Garcke Am 30. Oktober 2018 14:32:54 MEZ schrieb Olmo Chiara <olmo.chiara@gmail.com>:

Good afternoon,

I write with some questions.

1. I got in contact with the Bachelor-Master office and they confirmed that I can use the tutorials as a Practical Teaching Course, as it doesn't overlap with the Machine Learning lab module. This would mean that I would both get credit (which I think I won't be able to use since I'll already have the required amount to graduate) and also should have it appear in my certificate afterwards. In any case I would need your approval first - the problem being that I should sign up at some point today as it is when the deadline hits. Of course it's not a problem if it's not possible,

2. In the first class, when talking about the first exercise sheet, the Professor that was there mentioned that people should just do it, but it would not be either corrected or graded. However a couple of students told me that they should have it checked during tomorrow's tutorial. I just wanted to say that in that case I think it would be better to try and organize different time slots, since otherwise everyone will probably try and go just after the class, which might be a bit unpractical since the room is not that big.

3. Any update with respect to the pedestrian dataset?

Thank you very much,

Olmo

-- Diese Nachricht wurde von meinem Android-Mobiltelefon mit K-9 Mail gesendet.

Hi Olmo,

On 30. Oct 2018, at 06:32, Olmo Chiara <olmo.chiara@gmail.com> wrote:

3. Any update with respect to the pedestrian dataset?

I did talk with Mr. Garcke and Bastian about this. As you might know, the problem with the current pedestrian dataset is, that the specific subset we used has license issues. The original Daimler dataset is freely available, our subset isn’t. For legal reasons we need a freely available dataset. I would like to ask you to create a new subset/dataset which we can use for the sheet. You can either use the original Daimler datasets and create a new subset with identical parameters (image size, number of images etc), or look into one of the newer pedestrian classification datasets, which might be more interesting. The survey referenced on the sheet mentions a few newer datasets, I think all of them are in color. It is also easy to find pedestrian datasets on Google. You would have to pick a reasonable number of images of reasonable size, run the tasks of the sheet on them and check if everything stills works in reasonable time. You can decide if you want to adapt the tasks for colored images or greyscale them beforehand, and how large the dataset should be. Regarding the HoG features, I think the C++ implementation can already handle colored input, but the binding might need some modification in order to use this. Kind regards, Jannik