{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/acea3459b18247ccb8f2a50eb2972147\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/acea3459b18247ccb8f2a50eb2972147-477fcdc1cf4028fc.gif","duration":265.873,"title":"Mini Scenario Generator Walkthrough 🚀","description":"In this video, I provide a quick walkthrough of my mini scenario generator project, where I trained a small conditional variational autoencoder using motion datasets. I discuss the model architecture, training process, and the challenges I faced, including learning rate adjustments and clipping techniques. I also share some initial results and reflections on how to improve the model further. Please take a look at the figures I present and let me know your thoughts on the learning rate adjustments."}