search

leafqycc / rknn-multi-threaded

A simple demo of yolov5s running on rk3588/3588s using Python (about 72 frames). / 一个使用Python在rk3588/3588s上运行的yolov5s简单demo(大约72帧/s)。
Apache License 2.0
229 stars 40 forks source link

大佬您好，请教一下您运行后终端出现这个信息是怎么回事？ #15

Open Ywq-777 opened 7 months ago

Ywq-777 commented 7 months ago

W RKNN: [03:07:58.718] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.751] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride.

leafqycc commented 7 months ago

W RKNN: [03:07:58.718] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.751] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride.

也许是版本不对？或许可以参考下这里https://github.com/leafqycc/rknn-multi-threaded/issues/14

Ywq-777 commented 7 months ago

W RKNN: [03:07:58.718] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.751] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride.

也许是版本不对？或许可以参考下这里#14

感谢您的回复，我的toolkit_litey已经安装了1.4.0，但终端开始打印的信息是这个 I RKNN: [03:42:45.933] RKNN Runtime Information: librknnrt version: 1.5.2 (c6b7b351a@2023-08-23T15:28:22) I RKNN: [03:42:45.933] RKNN Driver Information: version: 0.8.8 I RKNN: [03:42:45.934] RKNN Model Information: version: 2, toolkit version: 1.4.1-source_code(compiler version: 1.4.1b12 (c6f5b0be6@2022-11-01T01:48:10)), target: RKNPU v2, target platform: rk3588, framework name: PyTorch, framework layout: NCHW, model inference type: static_shape ./rknnModel/yolov5s_relu_tk2_RK3588_i8.rknn done 请问是不是librknnrt的版本不对呢

leafqycc commented 7 months ago

W RKNN: [03:07:58.718] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.718] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.751] Output(output0): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(283): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride. W RKNN: [03:07:58.752] Output(285): size_with_stride larger than model origin size, if need run OutputOperator in NPU, please call rknn_create_memory using size_with_stride.

也许是版本不对？或许可以参考下这里#14

感谢您的回复，我的toolkit_litey已经安装了1.4.0，但终端开始打印的信息是这个 I RKNN: [03:42:45.933] RKNN Runtime Information: librknnrt version: 1.5.2 (c6b7b351a@2023-08-23T15:28:22) I RKNN: [03:42:45.933] RKNN Driver Information: version: 0.8.8 I RKNN: [03:42:45.934] RKNN Model Information: version: 2, toolkit version: 1.4.1-source_code(compiler version: 1.4.1b12 (c6f5b0be6@2022-11-01T01:48:10)), target: RKNPU v2, target platform: rk3588, framework name: PyTorch, framework layout: NCHW, model inference type: static_shape ./rknnModel/yolov5s_relu_tk2_RK3588_i8.rknn done 请问是不是librknnrt的版本不对呢

用find命令到根目录下找到对应版本，并替换成官方仓库下的1.5.2的动态链接库看看呢？