Closed Frost24K closed 5 months ago
Hello, thanks for your interest in our work. Run train_dhe.py
will take up about 12G memory on GPU. Is it possible that other programs are already taking up some memory while you are running this program? You can also reduce the batch_size
and try again.
Hello, I'm currently in the process of attempting to replicate the remarkable work you've shared. However, I've encountered a hurdle along the way. Following the training pipeline outlined in the repository and adhering to the provided requirements, I attempted to train the DHE-VPR using 4090 with 24GB graphics memory, same size with the 3090 . Unfortunately, after training for 1 epoch, the program crashed and reported the following issue:
I believe this issue is related to memory allocation on the CUDA device. Your expertise and guidance in resolving this problem would be immensely valuable to me
Thank you for your time