Closed blue-blue272 closed 3 years ago
The gradient from the validation set does not update the network, it only updates the sample rate, which can be viewed as a way of hyper-parameter tuning. Recent work [1] adopts the same data split as well.
[1] Jamal et.al., Rethinking class-balanced methods for long-tailed recognition from a domain adaptation perspective
The gradient from the validation set does not update the network, it only updates the sample rate, which can be viewed as a way of hyper-parameter tuning. Recent work [1] adopts the same data split as well.
[1] Jamal et.al., Rethinking class-balanced methods for long-tailed recognition from a domain adaptation perspective
Thank you for your reply. I have one more question. When I use the 'ImageNet_LT/balms_resnet10.yaml' to train the model. It will out of GPU memory. Whether or not you will have this problem? And how many GPUS you use?
We carry out all experiments on a single NVIDIA V100 with 32 GB GPU memory. For ImageNet_LT/balms_resnet10.yaml
, it should take ~22 GB of GPU memory to train, you may change the batch size to reduce the memory consumption.
I will close the issue for now. Feel free to open it if you have further questions.
In this code, I notice that you use the val data as the meta set. I think it will be unfair to compare to other methods since you use the validation set to train your network.