about train zero123
VLadImirluren opened this issue · comments
I see the images in logs, but I don't understand what exactly is of the five picture below.
train/conditioning train/inputs train/reconstruction train/samples train/samples_cfg_scale_3.00
Can you give me a introduction of these five images?thanks a lot...
Can you explain what it is...thanks a lot.. ouo
The code is really too complicated, I'm afraid I misunderstood, I would like to ask you to tell me, can you do me a little favor...
Do you know how to train zero123 on custom data?Can you help me?
I see the images in logs, but I don't understand what exactly is of the five picture below.
train/conditioning train/inputs train/reconstruction train/samples train/samples_cfg_scale_3.00
Can you give me a introduction of these five images?thanks a lot...
The ''reconstruction'' is the output of the vae, which usually looks the same as the ''input'' as the vae is an autoencoder.
The ''samples'' and ''samples_cfg_scale_3.00'' is the generated results under the guidance of ''condition'' and ‘’camera RT‘’, the differences between them is that the former one does not use unconditional guidance while the later one uses unconditional guidance and the guidance scale is 3.0. Ideally, the ''samples'' and ''samples_cfg_scale_3.00'' should be the same object as the ''input'', and are shown from another viewpoint different from the ''input''.
The answer comes from #83
@VLadImirluren @xdobetter Do you know how to train zero123 on custom data?Can you help me?