search

Vegeta2020 / SE-SSD

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud, CVPR 2021.
Apache License 2.0
811 stars 128 forks source link

Without any weight files(load files) #39

Closed sunwonHong closed 2 years ago

sunwonHong commented 3 years ago

I want to train without any weight files(load files). But in order to train that, many cuda memories are needed(over 18 GiB). I read that you have used a single TITAN Xp GPU, but i think it doesn't work on over 18 GiB things. Did you initially train the model in parallel GPU or by using another GPU(like RTX 3090)?

and if i have enough CUDA memories, can i train the model normally?

Your response will be very helpful. Thank you.

Vegeta2020 commented 2 years ago

@sunwonHong One solution is to train a SSD for several iteration, and then load it to our SE-SSD and continue the next training. By this way, it can utilize the slightly converaged model to avoid the initial predictions to be invalid values, e.g., randomly negative values for IoU calculation. Then, the consumed memory will be very limited and one GPU will be enough.