it's too slow and result with cube
Opened this issue · 7 comments
I was use the GPU device with 4090 (24GB) to generate a class knife
, batch_size 16.
It's show that need 126 batch total, each batch cost about 20~30min, somethings wrong with it?
# total 0/126
Category knife: 0%| | 0/126 [00:00<?, ?it/s]
# each
55%|█████████████████████▉ | 562/1024 [09:06<15:16, 1.98s/it]
A1: We recommended to run it on a GPU with high VRAM capacity (40GB or above)
A2: Please check if you have correctly loaded the ckpt file. The correct output should contain the following information:
=> Loading checkpoint from local file...
Loading Stage2 Model Success
A1: We recommended to run it on a GPU with high VRAM capacity (40GB or above) A2: Please check if you have correctly loaded the ckpt file. The correct output should contain the following information: => Loading checkpoint from local file...
Loading Stage2 Model Success
thx for answer 🙏
I think checkpoint was loaded!
the process was not finish yet, but Stage2_3584000_3001.obj
, ..., Stage2_3584000_3032.obj
generated as cube.
I'm sorry, but there are still some issues with the current ckpt. I will update it within this week.
I also encountered the same problem here.
请问下ckpt更新了吗