arxiv: https://arxiv.org/pdf/1703.06868.pdf key points arbitrary style transfer in real time use adaptive instance normalization(AdaIN) layers which aligns the mean and variance of content features allows to control content-style trade-off, style interpolation, color/spatial control previous works optimization approach using backprop of network Read more…
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 Read more…
creating the launch.json file is explained well in official docs. 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 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 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, 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 Read more…
key point compared to resnet, the residual blocks are upgraded to have multiple “paths” or as the paper puts it “cardinality” which can be treated as another model architecture design hyper parameter. resnext architectures that have sufficient cardinality shows improved Read more…
you can apply proxy settings to python requests like this:
instlal PyYAML in python file, load file like the following the data in yaml file will be saved in data variable as a python dict.