zmmhz

We appreciate you go through Apollo documentations and search previous issues before creating an new one. If neither of the sources helped you with your issues, please report the issue...

We appreciate you go through Apollo documentations and search previous issues before creating an new one. If neither of the sources helped you with your issues, please report the issue...

我训练bevdet时显示需要100多天才能完成20个epoch，这个也太久了吧。。是不是哪里有什么问题？ 训练时我发现gpu利用率极低，cpu倒是一直在跑，是不是数据处理这块的代码需要优化

img_input = torch.zeros([6*B, 3, 900, 400], dtype=torch.int32, device=f'cuda:{args.gpu_id}') 请问在转onnx时为什么要设置成900*400，不直接设置为900*1600？