search

VIPL-SLP / VAC_CSLR

Visual Alignment Constraint for Continuous Sign Language Recognition. ( ICCV 2021)
https://openaccess.thecvf.com/content/ICCV2021/html/Min_Visual_Alignment_Constraint_for_Continuous_Sign_Language_Recognition_ICCV_2021_paper.html
Apache License 2.0
116 stars 19 forks source link

Does your model produce different results each time it is run? #43

Open atonyo11 opened 8 months ago

atonyo11 commented 8 months ago

Hi author. Does your model produce different results each time it is run?

ycmin95 commented 7 months ago

In our experiments, it will produce the deterministic result with the same random seed. As you can find in the code, we fix most of random seeds.

atonyo11 commented 7 months ago

Thank you for your reply. But I run with the default code (uncomment loss_weights: SeqCTC: 1.0, ConvCTC: 1.0 for VAC), but I got different result each time.

ycmin95 commented 7 months ago

It may depend on the environment and the device, thus I couldn't provide clear answer to this question.

ycmin95 commented 7 months ago

It may depend on the environment and the device, thus I couldn't provide clear answer to this question.

For more information: REPRODUCIBILITY