TPU-MLIR 快速入门指南:效果对比,detect_yolov5.py执行失败

Viewed 96

root@9220c1e7ec55:/workspace/model_yolov5s_onnx_02/workspace# detect_yolov5.py
--input ../image/dog.jpg
--model yolov5s_1684x_f16.bmodel
--output dog_f16.jpg
begin to cmodel init...
mult engine c_model init
[BMRT][bmcpu_setup:431] INFO:cpu_lib 'libcpuop.so' is loaded.
bmcpu init: skip cpu_user_defined
Cannot open libusercpu.so, disable user cpu layer.
[BMRT][load_bmodel:1415] INFO:Loading bmodel from [yolov5s_1684x_f16.bmodel]. Thanks for your patience...
[BMRT][load_bmodel:1343] INFO:pre net num: 0, load net num: 1
BMLIB Send Quit Message
[0]exit api_route
cmodel_deinit complete
Warning: Output node with shape (1, 3, 80, 80, 10) is not vaild, please check.
Warning: Output node with shape (1, 3, 40, 40, 10) is not vaild, please check.
Warning: Output node with shape (1, 3, 20, 20, 10) is not vaild, please check.
Traceback (most recent call last):
File "/workspace/tpu-mlir_v1.3.228-g19ca95e9-20230921/python/samples/detect_yolov5.py", line 368, in
main()
File "/workspace/tpu-mlir_v1.3.228-g19ca95e9-20230921/python/samples/detect_yolov5.py", line 344, in main
scores, boxes_xyxy = postproc(output, input_shape, top, left)
File "/workspace/tpu-mlir_v1.3.228-g19ca95e9-20230921/python/samples/detect_yolov5.py", line 288, in postproc
pred = np.concatenate(z, axis=0)
File "<array_function internals>", line 200, in concatenate
ValueError: need at least one array to concatenate

0 Answers