Open Pixie8888 opened 2 weeks ago
Hi, the inference time does not take FLAME optimization into consideration.
For training potrait4d-v2, multi-view images are generating online via the 3D synthesizer. Relevant codes are here: https://github.com/YuDeng/Portrait-4D/blob/da5eec6fa3dfca4d7c8f08daa46326f2de8244db/portrait4d/training/loss/loss_recon_v2.py#L233; https://github.com/YuDeng/Portrait-4D/blob/da5eec6fa3dfca4d7c8f08daa46326f2de8244db/portrait4d/training/loss/loss_recon_v2.py#L336.
Thank you for your reply! I want to try training Portrait4d v2 on the toy dataset on a 24 GB gpu. I set the batch = 1
in portrait4d-v2-vfhq512-toy.yaml
, but it shows error below:
How can I train the model with batchsize of 1?
---------------------------- update -------------------------------
I changed mbstd_group = 1
in default.yaml
and batch=1
in portrait4d_v2_vfhq512_toy.yamlto train on 24 GB gpu. My question is changing batchsize to 1 will affect model's performance? Particularly what is the use of
mbstd_group```?
mbstd_group is a standard operation inherited from StyleGAN's discriminator to calculate some statistic values of real and fake data. A small mbstd_group may have slight influence to the performance of GAN loss.
Thank you for your reply. I have some other question regarding evaluation. Could you please share the code on how to compute the evaluation metric in Table 1? And the video ids that used for evaluation?
Sorry that the evaluation part is not available. I've switched job recently and is unable to reach the original code.
Dear authors,
You mentioned inference speed is 10 fps in the paper. Do you include the time of
full BFM-to-FLAME transformation process
? In my machine, it takes more than 1 minute to generate a result (include the time for Landmark detection, 3D face reconstruction, and cropping, BFM to FLAME parameter transformation).I also have a question about training portrait4d-v2. Did the 3D synthesiser generate multi-view driving images on the fly during training shown in the fig 2? Could you please help me point out where is the relevant code?