Inflating pre-trained models

[varghesealex90]

Hello All,

Upon reading the paper, I see that the authors have repeated the same image numerous time to create a "boring" video. What I fail to understand is the following, upon creating the "boring" video is the I3D model trained from scratch to create pre-trained weights? Or does there exists a schema wherein the 2-D pre-trained weights are converted to 3D in nature to initialize the network?

[joaoluiscarreira]

Hi, the 2D pre-trained weights are converted to 3D directly. The "boring" videos are never created, they're just a concept. Best, Joao

…

On Mon, Oct 5, 2020 at 5:52 AM varghese ***@***.***> wrote: Hello All, Upon reading the paper, I see that the authors have repeated the same image numerous time to create a "boring" video. What I fail to understand is the following, upon creating the "boring" video is the I3D model trained from scratch to create pre-trained weights? Or does there exists a schema wherein the 2-D pre-trained weights are converted to 3D in nature to initialize the network? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#109>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ADXKU2TBESBAK3NGM66SY4DSJFGJFANCNFSM4SEGI7BA> .