50+ days of Machine Learning

 Hello :)  Today is Day 38! (decided to do this one in English) Today's summary: Traffic sign detection model with PyTorch Learned about how Telsa's autopilot works [ 1 , 2 ,  3 ] These days I stay till late, studying and then writing these blog posts ~  Firstly, the model that I struggled to make yesterday - a model where I give it a picture of a sign, and what I get back is - what kind of sign it is + the sign's bounding box. And today, I am happy to say that I got it :)  The dataset I used looks like this: For the processed version, I took the bounding box (bbox) data, the ClassId and the path.  Augmentations - only resize to 112x112 (3 channels by default). Used the albumenations library since it rescales the bounding boxes alongside the image, so no extra resizing for the bbox size was needed Final train and val lengths were 31367 and 7842, after which I batched with size 32. An example image from the data: Class 14 = Stop sign The classification model was the same as