search

WongKinYiu / yolov7

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
GNU General Public License v3.0
13.36k stars 4.22k forks source link

Ensemble multi-scale model with fixed scale #846

Open AmmarOkran opened 2 years ago

AmmarOkran commented 2 years ago

I trained two models, one without multi-scale and the other with multi-scale. However, when I tried to ensemble both weights with the max ensemble I got an error: stack expects each tensor to be equal size, but got [1, 25200, 9] at entry 0 and [1, 25500, 9] at entry 1. How could I ensemble them? any suggestion! @WongKinYiu

yulin010101 commented 2 years ago

I think you need to have both models output the same size results.