Closed Calendula597 closed 1 month ago
Hi @Calendula597, thanks for your interest in our work.
In cases where the sequence length $n$ is relatively small, agent attention may occupy more GPU memory compared to the Softmax attention. Maybe you can turn on --amp
or use a smaller batch size.
Hello, I must commend your work; it's truly impressive. However, I've encountered an issue when running AgentSwin under the same batch size configurations that I successfully use with the standard Swin Transformer. Specifically, I'm experiencing out-of-memory errors with AgentSwin that do not arise with Swin Transformer. I wanted to reach out and inquire if this is expected behavior or if there might be some adjustments or optimizations I could consider to alleviate this issue?