Kodie Amos

Hey there! `movi_d.py` to my understanding is just another worker file There are lots of ways you can go about generating a whole dataset. You could write a new script...

Hello! Please refer to the following > Is there any example of loading objects in the scene? https://github.com/google-research/kubric/issues/185

@WenyuanQ [here](https://github.com/google-research/kubric/tree/b9e7358728c4323f7dfb871b5974eca8e4a96d61/challenges/pretraining_visual) > This dataset contains each ShapeNet object rendered from 25 random perspectives on transparent background. Images are rendered at 512x512 and then cropped to fit the object, so...

what do you enter into the console to get this response from it? :D

I can only assume its intentional Reasoning being: https://github.com/google-research/kubric/blob/ea9556f6f6228aa35298ca35cd6e5db38725e85f/kubric/core/traits.py#L97 Followed by the line: https://github.com/google-research/kubric/blob/ea9556f6f6228aa35298ca35cd6e5db38725e85f/kubric/core/traits.py#L98

From what I've read in the code and here online your assumption on the name convention is correct. When we add an object we need to pass through the noted...

Instead of spam the PR section I've added it into the current fork I have listed in the Pull Requests xD

The current way I understand the Camera to be implemented is a one per scene. If you want a different angle of the same action, specifically program the same action...

@Ziachnix Do the images increment with the frame rate as usual? 😄 Also are all the camera views stored in the same output folder?

made a new function. This is how I've tested it so far. `scene.camera.set_position((6, 0, 3.0))` It basically just updates the position and then grabs the "look_at" parameter and applies it...