Did you really run the BEVFromer(Pytorch) on 3090? Or you just copy the result from https://github.com/fundamentalvision/BEVFormer

DerryHub / BEVFormer_tensorrt

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

Apache License 2.0

430 stars 71 forks source link

Open admyxs opened 11 months ago

admyxs commented 11 months ago

Did you really run the BEVFromer(Pytorch) on 3090? Or you just copy the result from https://github.com/fundamentalvision/BEVFormer. I found the bevformer_tiny runned on 8 A100-SXM-80GB in https://github.com/fundamentalvision/BEVFormer, you run bevformer_tiny on 8 3090, but you get a same score compared to https://github.com/fundamentalvision/BEVFormer, that`s weird