#环境

paddlelite==2.10rc0

paddlepaddle-gpu==2.2.1.post101

通过opt生成nb文件

!paddle_lite_opt --model_dir=output_inference/ppyolo_tiny_650e_coco --optimize_out=model --optimize_out_type=naive_buffer

替换yolo-detection-demo里面的模型为自己生成的模型运行

报错

2021-12-31 11:06:40.768 11185-11203/com.baidu.paddle.lite.demo.yolo_detection W/Paddle-Lite: [W 12/31 11: 6:40.767 ..._210rc/Paddle-Lite/lite/api/light_api.cc:355 CheckInputValid] Error input tensor precision type. Input index (1) Tensor name (image) Require precision type (float) Input precision type (int32_t).
2021-12-31 11:06:40.768 11185-11203/com.baidu.paddle.lite.demo.yolo_detection I/Paddle-Lite: [I 12/31 11: 6:40.768 ...rc/Paddle-Lite/lite/operators/conv_op.cc:33 CheckShape] in_dims.size() == 4 || in_dims.size() == 5 test error!
2021-12-31 11:06:40.768 11185-11203/com.baidu.paddle.lite.demo.yolo_detection A/Paddle-Lite: [F 12/31 11: 6:40.768 ...e_210rc/Paddle-Lite/lite/core/program.cc:692 Run] Check failed: op_->CheckShape():
2021-12-31 11:06:40.769 11185-11203/com.baidu.paddle.lite.demo.yolo_detection A/libc: /buildbot/src/android/ndk-release-r21/external/libcxx/../../external/libcxxabi/src/abort_message.cpp:72: abort_message: assertion "terminating with uncaught exception of type paddle::lite::PaddleLiteException: Paddle-Lite C++ Exception:
[F 12/31 11: 6:40.768 ...e_210rc/Paddle-Lite/lite/core/program.cc:692 Run] Check failed: op_->CheckShape():
" failed
2021-12-31 11:06:40.770 11185-11203/com.baidu.paddle.lite.demo.yolo_detection A/libc: Fatal signal 6 (SIGABRT), code -6 in tid 11203 (GLThread 207)