Question about the configuration for your code

[cyber-ranger]

Hello，

Thanks for sharing the code, and your demo on youtube looks really cool.
We would like to checking on the idea in your paper, but we can't generate the similar results as you showed in your demo.
Now we are retrying the code with different configuration, could you provide some guidence on the key configuration/parameters which we can adjust them for better results? Thanks in advance!

For example, there is the following configuration in your code

    # maintain losses in a consistent order:
    # 1. all ground truth as usual
    # 2. ground truth for TARGET_CLASS removed
    # 3. all ground truth removed
    # 4. ground truth set to the patch with TARGET_CLASS (dpatch loss)
    "maximize_loss": [True, False, False, False],
    "target_loss_index": 3,
    "compute_all_losses": False,

• How shoud I choose from the 4 different options in the comments "maintain losses in a consistent order"?
• What's the meaning of [True, False, False, False] for "maximize_loss"？
• what is the meaning of 3 for "target_loss_index"? is it "3. all ground truth removed"?

[erasaur]

you should use the first one as described in the paper. the others were an attempt to replicate the targeted loss of dpatch paper but don't work very well. the maximize_loss is just picking which of the losses to minimize (instead of maximize).

[cyber-ranger]

Thanks for helping.
So how should "maximize_loss" and "target_loss_index" be configured to setting the options 1/2/3/4 listed in the comments?

From your souce code, "target_loss_index"= 3, does it corresponding to "4. ground truth set to the patch with TARGET_CLASS (dpatch loss)"?
Shoud the "target_loss_index" be 0, so it is corresponding to "1. all ground truth as usual"?

Is my understanding correct?
THX