Julien
Thanks for sharing your code! I'll also have a look at what could be causing the reduction in the Pascal VOC performance.
@YoungGer Have you noticed, that the find_min_norm_element method actually uses the projected gradient descent method? Only find_min_norm_element_FW is the Frank-Wolfe algorithm as discussed in the paper. They are only guaranteed...
Hi! Thanks for the quick response. I have been working on applying a crf-rnn layer to my network which works on single instance images (The image contains only one object...
I used the GPU version and compiled with SPATIAL_DIMS=2, INPUT_CHANNELS=2 (object/background) and REFERENCE_CHANNELS=3. In crf_rnn_layer_test_2.py you used an rgb image as reference which appears to be within [0, 255] when...
Great! My email is [email protected]
@kroggen Thanks for the cpu version. Would be nice if you added this as a PR, currently using your code for debugging.
I am having the same issue, any ideas?
Thanks @maksymdolgikh this worked for me, also no idea why this works though.
Set dim = 32 Like so ``` import torch from mamba_ssm.modules.mamba2 import Mamba2 batch, length, dim = 2, 64, 32 x = torch.randn(batch, length, dim).to('cuda') model = Mamba2( # This...