Which parameter should be set to continue training after a break in training？ about non-local-sparse-attention HOT 12 CLOSED

—resume and you may have to manually adjust the epoch number and learning rate.

from non-local-sparse-attention.

'--resume' Is this one？How do I set the value of this parameter and learning rate?Can you be more specific? Thank you

from non-local-sparse-attention.

For example, if you want to train 100 epochs with learning rate 1e-4 for first 50 and 5e-5 for rest. Suppose you training stop at 53. To resume, please add —resume 53 and change —epoch from 100 to 47 and —lr to 5e-5.

from non-local-sparse-attention.

thank you so much

from non-local-sparse-attention.

thank you so much

from non-local-sparse-attention.

How do I set the value of --resume to model_latest?as shown below

from non-local-sparse-attention.

Why should the parameter of --data_range be set to 801-900 during test? as shown below

from non-local-sparse-attention.

To recover from the latest checkpoint, you have to set —resume to the the latest epoch number.

This parameter does nothing in testing with benchmarks. Free feel to remove.

from non-local-sparse-attention.

thank you very much

from non-local-sparse-attention.

During training, why did the model with fewer parameters prompt that the GPU's memory was insufficient, but the model with more parameters did not ？as shown below

from non-local-sparse-attention.

Memory and parameters are not directly related. For example, when the input is larger, it requires more memory to store activation maps. The —patch_size is the output size. If you want to train X4 model, please set the patch size as 192 (48*4) to make the input same to x2.

from non-local-sparse-attention.

hi,Is there any code in the program to compute FLOPS?thanks

from non-local-sparse-attention.