About batch sampling `iter_perc`
yangbang18 opened this issue · comments
Thanks for your code.
I note that in your paper, you said "We sample the data by making half of the images in a batch containing bounding box annotations".
But the code is:
Lines 82 to 121 in e7b9602
The iter_perc
you used is 0.5, which means only 50% of time, the model takes a batch of image-text-box data and a batch of image-text data as input; and otherwise, the model only takes a batch of image-text data as input.
Therefore, it seems that iter_perc = 1.0
fits your statement in the paper.
According to the ablation study results in Table 4, you have certainly tested the impact of iter_perc = 0.0
(corresponding to the model, X-VLM w/o all).
So, have you tested more values of iter_perc
(e.g., 1.0)?
Hi,
Sorry for my late reply.
I used iter_perc = 1.0. (or at least I used iter_perc = 1.0 in X2-VLM...)
I don't remember clearly.