set params when training the flow model about temporal-shift-module HOT 6 CLOSED

Hi, we basically used the same training hyper-parameters for flow models. How much accuracy can you get using optical flow? Note that optical flow model should give a lower performance compared to RGB input.

from temporal-shift-module.

I just stopped the training process before 50 epochs cuz my performance is too low.
It was lower than 30% at 40epochs.
Could you tell me the performance of TSM Flow model on Something v1? (uniform sampling, 8 segments, single inference, ResNet-50)

from temporal-shift-module.

The accuracy of TSM Flow model on Something V1 is about 42%.

from temporal-shift-module.

Thanks for the answer.
I just modified the dense sampling to the uniform sampling, and achieves the similar performance as you said.

from temporal-shift-module.

Thanks for the answer.
I just modified the dense sampling to the uniform sampling, and achieves the similar performance as you said.

Hi, I just trained the TSM-ResNet50 model on SomethingV1 with 8-segments optical flow input only, but the performance is around 37%, far below the 42%, and the two-stream is around 48%. Can you provide the link to download the optical flow for SomethingV1 dataset that you use?

from temporal-shift-module.

@boheumd How did you extract flow data for sthv1?

from temporal-shift-module.