Open smichniak opened 2 years ago
I have the same issue, from my analysis it looks like the problem is in the weights of the relation head because the RPN proposals look good.
From what I see the head weights are properly loaded from the checkpoint. Do you think the provided pretrained model weights themselves could be wrong and the listed results come from evaluation on a different set of weights?
Yup, that is my guess, but I also tried with other models (nuralMotif and grcnn) and also got similar results, so it seems unlikely that they uploaded the wrong weights for all of them.
Have you solved this problem?
I got the same result. It seems odd.
Any update on this? I just ran this and got the same results
After evaluating pretrained RelDN model on Visual Genome dataset we get the following results: {"danfei_metric": {"sgdet20": 0.03587473726452877, "sgdet50": 0.059597123157443185, "sgdet100": 0.08203152214357358}, "rowan_metric": {"sgdet20": 0.03556429024402322, "sgdet50": 0.05944168796383135, "sgdet100": 0.08196929203549849}}
Those metrics are extremely different from those listed in the model zoo file.
The testing is run using the following command:
with
NGPUS=4
. Pretrained model is downloaded from here and is located inAttached are the output logs of the evaluation: out.txt