Amanda-Barbara

Results 21 comments of Amanda-Barbara

@haoyuying 我看了下代码是不是不支持自己训练的模型啊,我试了官方提供的模型,是可以正常标注的,但是自己训练的模型只能加载成功,一旦点击左键开始标注的时候界面就闪崩了。

yeah,I have done it, the last channel value are same. when I ran 940th picture there have an error like this: RuntimeError: cuda runtime error (2) : out of memory...

I have filtered the high-resolution images and the the project can go on running,thanks @yingcong

https://github.com/willyd/caffe-builder/issues/50#issuecomment-434187204 我参照着这个方法解决了,是因为cuda版本过高导致的,

你的意思是说把type: "NormL2"改成type: "Normalize"就可以了是吗?

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 4 On-line CPU(s) list: 0-3 Thread(s) per core: 1 Core(s) per socket: 4 座: 1 NUMA 节点: 1 厂商...

https://github.com/willyd/caffe-builder/issues/50#issuecomment-434187204 我参照着这个方法解决了,是因为cuda版本过高导致的,

@ziyouzizai111 我把系统换成ubuntu18.04就可以正常运行了。

@SyGoing rknn-toolkit/platform-tools/ntp/linux-aarch64 目录下面有[npu_transfer_proxy](https://github.com/rockchip-linux/rknn-toolkit/blob/master/platform-tools/ntp/linux-aarch64/npu_transfer_proxy) ```shell cd platform-tools/ntp/linux-aarch64/ sudo ./npu_transfer_proxy ```

@zen-xingle paddle->pytorch->rknn已实验能转,我试试onnx-simplify版本的模型能不能转成rknn格式的模型,多谢。