Closed lbj96347 closed 1 year ago
Hi, it seems like the error you encountered is expected due to insufficient GPU memory.
--sample_batch_size
(default: 8) to a lower number (e.g. 2, 4). Besides, you can use the 8-bit optimizer to train on a 16GB GPU, please refer to this tutorial.@hao-pt thanks for your reply. Yes! The GPU caused the issue. After I changed to a 80GB A100 GPU, everything works fine.
Background
I want to make a workaround in Google Colab for experiencing Anti-DreamBooth. Here is my ipynb. But I failed in Step 3 by running
Google Colab Virtual ENV:
Details
After running
attack_with_aspl.sh
, it callsAnti-DreamBooth/attacks/aspl.py
to run perturbation training. It is expected to outputnoise-ckpt
in output dir. But it didn't.When
Anti-DreamBooth/attacks/aspl.py
runs into line 715 , it throws error.Even I have changed
--max_train_steps
to 10, the execution was also being killed. I guess reason of execution being killed is GPU exhausted?Because noise-ckpt was not outputed, the program was crashed with this final message:
Questions