Luke Neumann PRO

LukeNeumann

https://overlai.ai/

AI & ML interests

Fine tuning training data

Recent Activity

posted an update 1 day ago

I had a question about Trending datasets. Our initial dataset "Oregon Coast in 4K" was trending at #3 for video at about 700 downloads. Over the past two days our downloads have spiked, now up to over 2,000, but the dataset has dropped down to the 3rd or 4th page of Trending. What metrics are used to determine dataset Trending position?

liked a dataset 5 days ago

Overlaiai/OregonCoastin4K

liked a dataset 5 days ago

Overlaiai/SubArcticPolarBear

View all activity

Organizations

Posts 4

Post

599

I had a question about Trending datasets. Our initial dataset "Oregon Coast in 4K" was trending at #3 for video at about 700 downloads.

Over the past two days our downloads have spiked, now up to over 2,000, but the dataset has dropped down to the 3rd or 4th page of Trending.

What metrics are used to determine dataset Trending position?

Post

549

Something I've been thinking about regarding fine-tuning video models.

How well are these models trained on the fundamentals of image capture? Take shutter speed/angle, for instance.

The difference in a video with a 1/2000 speed shutter and a 1/60 speed shutter is drastic.

What about color science? HDR vs. SDR, Anamorphic vs. spherical, sensor size, aspect ratio.

Is it worth doing an open-source dataset "film school series"?

It may seem too granular but I wonder if this level of granularity makes for better downstream results.

View all posts

models

None public yet

datasets

None public yet