Hi, I'm trying to test your pre-trained model on Imagenet, namely videomamba_tiny using the /VideoMamba/videomamba/image_sm/exp/videomamba_small/run224.sh with corresbonding checkpoints.
However, the evaluated result is only 3% on the Imagenet-val with 50,000 test images. I just wondering whether the following code changes led to poor performance?
Set the amp default as False to ensure the code running correctly.
The data type of model parameters is torch.float, then I set the image dtype as torch.float as well by simply adding the line 'images = images.type(torch.float)'.
Hi, I'm trying to test your pre-trained model on Imagenet, namely videomamba_tiny using the /VideoMamba/videomamba/image_sm/exp/videomamba_small/run224.sh with corresbonding checkpoints.
However, the evaluated result is only 3% on the Imagenet-val with 50,000 test images. I just wondering whether the following code changes led to poor performance?