Reproducing results of paper about cross_view_transformers HOT 4 CLOSED

1. This is an auxiliary loss (focal loss on vehicle centers) used by FIERY that I tried and left in. works fine without this
2. After major cleanup of the code for release and trying to train mixed-precision this lr seems to be more stable
3. These objects are not visible to the ego-vehicle and need to be filtered out for correctness
4. If you take a look the dataset generation code can the missing index is pedestrian - we included this in the label set since it could be useful for future tasks

The config is accurate - i will check to make sure nothing diverged in the release

Thanks for the questions!

from cross_view_transformers.

Hello bradyz ! Many thanks for your response !

. 3. I understand that, I will clarify. My question is about how you evaluate. In your paper, to obtain the score in table 1, do you evaluate on all vehicles or only on visible vehicles ?

. 1. Ok this is as further experiments, the results in your paper were obtain using the Focal loss
. 2. I see, indeed it is a nice feature to be able to train with mixed-precision
. 4. Ok

from cross_view_transformers.

Table 1 is visible vehicles only - unfortunately almost all methods for this task evaluate slightly differently but I would argue this is the right way to do it

from cross_view_transformers.

Ok I better understand now, many thanks.

from cross_view_transformers.