loiccordone / object-detection-with-spiking-neural-networks

Repository code for the IJCNN 2022 paper "Object Detection with Spiking Neural Networks on Automotive Event Data"
MIT License
57 stars 12 forks source link

How to work with smaller batch size & Replicate results #12

Open ghost opened 2 years ago

ghost commented 2 years ago

Hello Loic, I am trying to obtain the same results as you. I am using a 22GB GPU. I am trying to figure out a way to obtain the same results as you while using a 22GB GPU. Lowering batch size allows me to start training but this does not allow me to get the same mAP scores as you. Should I lower batch size while increasing number of epochs? Can you please share how I can get close to your results with the current hardware that I have? Regards, same_error