IPL-Zero-Shot-Generative-Model-Adaptation
IPL-Zero-Shot-Generative-Model-Adaptation copied to clipboard
CUDA out of memory
The paper noted, "The training process includes 300 iterations for prompt learning and 300 iterations for generator adaptation using a single NVIDIA RTX 3090 GPU." However, I followed the example commands to adapt a generator with the CUDA out-of-memory issue in RTX4090. Could you please provide a solution to this problem? Looking for you reply~
Hi, @ZYBOBO. Have you solved it? Or can you provide some additional details? Did you follow the instructions to set up your environment? It can be a little bit hard to tell what is wrong since it works well on my end.