roey1rg

Problem with rgb input for the cval parameter, when applying affine transformations to image

3

from the documentation, the cval parameter is described as follows: > The constant value used to fill up pixels in the result image that didn’t exist in the input image...

Very noisy training curves when trying to fine-tune with paired data, what am I doing wrong?

4

I'm trying to train Real-ESRGAN with 400 images. The training curves are very noisy, especially the perceptual loss (l_g_precep). I've tried to use various different learning rates. I'm using 4...

What params should I use for the 128 to 1024 task, and for the 512 to 1024 task? How should I choose the Unet architecture?

3

Specifaclly, I'm asking about the following section in the config file: ``` "unet": { "in_channel": 6, "out_channel": 3, "inner_channel": 64, "channel_multiplier": [?????????], "attn_res": [?????????], "res_blocks": ?????????, "dropout": ????????? }, ```

I'm looking for a high-resolution image synthesizer (4k) and wonder if infinityGan suits this task. I want to train it on my own data and potentially use it as an...

Using subject's betas instead of v_template results in broken motions

1

Hello, I've been trying to use the subject's betas instead of their v_template and the result motions are broken (see attached image). Is it somehow possible to only use the...