zhaobin Chu

icon indicating an email [email protected]

icon location Signal analysis、Machine learning、Deep learning

Results 2 issues of zhaobin Chu

svd的微调脚本可以用在25-frames的视频数据上么？

9 comment

我在用Accelerator的deepspeed做u-net微调时，即使batch_size=1，仍会出现显存溢出

Is anyone trying to train their own SVD-based Camera Motion LoRA model?

5 comment

I tried using LoRA to fine-tune the U-Net with SVD, and even with a batch size of 1, memory overflow occurs on the A100-80G GPU when the dataset consists of...