The official repository implement of Res-VMamba: Fine-Grained Food Category Visual Classification Using Selective State Space Models with Deep Residual Learning
As shown in Table 4 of your paper, finetuning Vmamba with retrained weight gets the best performance.
I want to do some modifications based on normal fine-grained datasets but get unsatisfactory results.
Can you please provide me the detail implementation of how you fine-tune mamba-s with pre-trained weights?
Such as lr, epochs, and other hyperparameter settings.
Thanks!
As shown in Table 4 of your paper, finetuning Vmamba with retrained weight gets the best performance. I want to do some modifications based on normal fine-grained datasets but get unsatisfactory results. Can you please provide me the detail implementation of how you fine-tune mamba-s with pre-trained weights? Such as lr, epochs, and other hyperparameter settings. Thanks!