Closed donghaoye closed 9 months ago
Could you please provide me with the paper version of the hamer_vit_transformer.yaml file?
I am not sure that the batch_size is 8?
The batchsize is the main reason because the loss is a sum loss.
The batchsize is the main reason because the loss is a sum loss. Hello, I have a similar problem: I have trained the hamer on 8*A800 GPU as the original configuration, but the epoch is still 0 until I get to 1,000,000 steps and after I run the demo, there is a mismatch in the visualisation results, what can I do to fix it? Looking forward to your reply.
Maybe the checkpoint is not updated correctly?