VQ2D evaluation on validation split takes 70+ hours

[fcakyon]

Hello I am using the VQ2D evaluation script with default config params (siam_rcnn_residual+kys, data.split="val", data.num_processes=2) on a A100 gpu but it takes 70+ hours.

Is this expected?

Some clikp eval durations:

====> Data uid: val_0000000074 | search window :     411 frames | clip read time:   0.01 mins | detection time:   0.51 mins | peak signal time:   0.00 mins | tracking time:   5.03 mins

====> Data uid: val_0000000075 | search window :     251 frames | clip read time:   0.02 mins | detection time:   0.31 mins | peak signal time:   0.00 mins | tracking time:   0.63 mins

====> Data uid: val_0000000076 | search window :     522 frames | clip read time:   0.01 mins | detection time:   0.65 mins | peak signal time:   0.00 mins | tracking time:   0.82 mins

====> Data uid: val_0000000065 | search window :    1230 frames | clip read time:   0.01 mins | detection time:   1.64 mins | peak signal time:   0.00 mins | tracking time:  16.46 mins

[srama2512]

@fcakyon - Yes, this is expected. For the Ego4D experiments, we split the vq2d validation split into 20 different parts and evaluated them parallelly to speed things up. Depending on the GPU memory, you can also increase the number of processes from 2 to something higher. We set 2 as the default to make sure it does not fail for a user. But it is definitely not the optimal setting.

[srama2512]

Closing issue since it has been addressed. Please feel free to open it if there are further questions.