train pipline for custom dataset

[becauseofAI]

Thx for your jobs.

Can you describe the training pipline for custom dataset clearly? @jiawei-ren

[jiawei-ren]

You may modify the LT_Dataset class here to use a custom dataset.

[becauseofAI]

You may modify the LT_Dataset class here to use a custom dataset.

@jiawei-ren I mean what is the meaning of the pipeline that you described as follow:

Training

End-to-end Training

• Base model (Representation Learning)

  python main.py --cfg ./config/CIFAR10_LT/softmax_imba200.yaml

  Alternatively, you may download a pretrained model here and put it in the corresponding log folder.

• Balanced Softmax

  python main.py --cfg ./config/CIFAR10_LT/balanced_softmax_imba200.yaml

  Decoupled Training

  After obataining the base model, train the classifier with the following command:

• Balanced Softmax

  python main.py --cfg ./config/CIFAR10_LT/decouple_balanced_softmax_imba200.yaml

• BALMS

  python main.py --cfg ./config/CIFAR10_LT/balms_imba200.yaml

Does that mean there are three kinds of training method?

Method 1: End-to-end Training step 1:

• Base model (Representation Learning)

  python main.py --cfg ./config/CIFAR10_LT/softmax_imba200.yaml

  Alternatively, you may download a pretrained model here and put it in the corresponding log folder. step 2:

• Balanced Softmax

  python main.py --cfg ./config/CIFAR10_LT/balanced_softmax_imba200.yaml

Method 2: Decoupled Training step 1:

• Base model (Representation Learning)

  python main.py --cfg ./config/CIFAR10_LT/softmax_imba200.yaml

  Alternatively, you may download a pretrained model here and put it in the corresponding log folder.

step 2:

• Balanced Softmax After obataining the base model, train the classifier with the following command:

  python main.py --cfg ./config/CIFAR10_LT/decouple_balanced_softmax_imba200.yaml

Method 3: Decoupled Training step 1:

• Base model (Representation Learning)

  python main.py --cfg ./config/CIFAR10_LT/softmax_imba200.yaml

  Alternatively, you may download a pretrained model here and put it in the corresponding log folder.

step 2:

• BALMS After obataining the base model, train the classifier with the following command:

  python main.py --cfg ./config/CIFAR10_LT/balms_imba200.yaml

If this is true, which method works better or is more recommended? If not, what is the correct one?

[jiawei-ren]

Does that mean there are three kinds of training method?

It is mostly true, except that there is no step 1 in Method 1. End-to-end training doesn't require a pre-trained backbone.

If this is true, which method works better or is more recommended?

Method 3 is the most recommended. You may refer to the results reported in the README or the paper.

[becauseofAI]

Does that mean there are three kinds of training method?

It is mostly true, except that there is no step 1 in Method 1. End-to-end training doesn't require a pre-trained backbone.

If this is true, which method works better or is more recommended?

Method 3 is the most recommended. You may refer to the results reported in the README or the paper.

Got it. Thx u very much! @jiawei-ren

[cunjunyu]

I will close the issue for now. Feel free to reopen it if you have any further questions.