Encoder can only fit 1 obj?

[Justinfungi]

with torch.no_grad():
    latent = xm.encoder.encode_to_bottleneck(batch)

    render_mode = 'stf' # you can change this to 'nerf'
    size = 128 # recommended that you lower resolution when using nerf

    cameras = create_pan_cameras(size, device)
    images = decode_latent_images(xm, latent, cameras, rendering_mode=render_mode)
    display(gif_widget(images))

It appears that the existing code can only handle one object at a time by loading an initial object into the encoder and modifying it based on a single input. However, there is a desire to feed multiple objects into the encoder and generate latents for each object. Unfortunately, there is currently no callback mechanism available in the code to enable the generation of latents for multiple objects.