Getting the angle between two vectors is well known. But finding the ‘rotation angle’ from one vector to another needs a bit more consideration. The following functions can handle this. This function will use cross product between two vectors to identify if the rotation direction is CW or CCW. This Read more…
creating the most basic launch.json file is explained well in official docs. changing execution path However what I really wanted to know was how to configure it to make it run debugging on a file from a specific directory path. For example, I have a workspace structure like this. And Read more…
after creating a virtualenv, one can setup pip.conf file right inside the created virtualenv directory. Here’s an example An example of pip.conf that I use commonly is shown below. The “index-url” may not be necessary since it is the default value, but in case it is overwritten by the system Read more…
Loading multiple tensorflow models at once in tf1.x causes problems because the operations in each model may have same name, and thus cause collision. While this can be avoided by manually giving unique names to tensors when developing a model, this is a cumbersome strategy. Another approach would be to Read more…
https://towardsdatascience.com/advances-in-few-shot-learning-a-guided-tour-36bc10a68b77 great brief summary over matching networks, prototypical networks, model-agnostic meta-learning(MAML). well, the first two topics are well explained but MAML section needs a lot more thinking to understand. Also, I think MAML is closer to the topic of meta-learning rather than few shot learning. https://arxiv.org/pdf/2008.06365.pdf “An Overview of Deep Read more…