Linengyao

> 最后还是item的不同控件单独设置点击事件 holder.getView(R.id.content).setOnClickListener { } holder.getView(R.id.content).setOnLongClickListener { } holder.getView(R.id.tv_delete).setOnClickListener { data.removeAt(holder.adapterPosition) notifyItemRemoved(holder.adapterPosition) val view: EasySwipeMenuLayout = holder.getView(R.id.easy_swipe) view.resetStatus() } 请问这个是放在哪的，是convert吗？我点击任然没用

@Bhavay-2001 hi, i am doing the same search about how to use yolov8 to train video(time sequence) object detection,do u have any process now?(any idea or code?)

> 你好 > > 我想我处理了这个问题。仅用于使用 torchhub 预训练模型进行推理，如果您将以下代码行从 bfloat16 更改为 float16，它可能会起作用。对我有用！ > > GPU：Jetson Nano 4 GB （ARM） CUDA 10.2 Pytorch 1.12 > > 以下是说明： > > `cd ~/.cache/torch/hub/yvanyin_metric3d_main`（或者，如果您使用 pyenv，请在您的环境中查找相应的文件夹） （或者...

i meet the same problem. do u solve it?

> Hello, thank you for your amazing project, I'm trying to run it in a Jetson Orin. > > I appreciate your help in this problem. When I try to...

> （也感谢您提醒我。我现在碰巧手头有个 Orin，我也会在完成工作后测试它） > > 您能否帮助提供您的 jetpack 版本和 pytorch 版本（最好包括链接）？ > > 我一直在使用的 jetpack 版本是内部版本，所以我可能无法复制所有这些。 Hello, I am using Jetson Orin NX 8G, but it is still in the delivery...

> (Thanks for reminding me also. I happened to have an Orin by hand at the moment and I will also test it after I finish my work) > >...

> @Linengyao > > Yes, even with TensorRT and fp16, it still took 0.6s seconds for each image. You may need to export onnx models with a smaller input size....