Your browser does not seem to support JavaScript. As a result, your viewing experience will be diminished, and you have been placed in read-only mode.
Please download a browser that supports JavaScript, or enable it if it's disabled (i.e. NoScript).
关于CenterNet res101在tx2上的推理速度?
836ms合理吗?感觉太慢了
@金天 大佬,c++TRT貌似有内存泄露?
@金天 我目前用的是101,50的需要自己写onnx导出吗?
tx2应该跑不起来101的backbone,用50吧
float16推理速度在135ms,我直接在ctdetConfig.h设置input_size报错,必须要设置的和训练时一样吗?
与 ManaAI社区 的连接断开,我们正在尝试重连,请耐心等待