演示边缘tpu模型都不起作用-“提供的模块具有模型标识符'l>< b',应该是'tfl3'”

u3r8eeie  于 2021-09-29  发布在  Java
关注(0)|答案(0)|浏览(210)

使用珊瑚板,并尝试运行 detect.py 归档自https://github.com/google-coral/pycoral/blob/master/examples/detect_image.py 模型放在table上https://coral.ai/models/object-detection/ 页尝试 ssd mobilenetv2EfficientDet Lite ,两者都会得到相同的错误:

Traceback (most recent call last):
  File "detect.py", line 108, in <module>
    main()
  File "detect.py", line 73, in main
    interpreter = make_interpreter(args.model)
  File "/usr/lib/python3/dist-packages/pycoral/utils/edgetpu.py", line 93, in make_interpreter
    model_path=model_path_or_content, experimental_delegates=delegates)
  File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 351, in __init__
    experimental_preserve_all_tensors))
ValueError: Model provided has model identifier 'l><b', should be 'TFL3'

不确定问题出在哪里,因为两者都会得到完全相同的错误。谢谢你的帮助!

暂无答案!

目前还没有任何答案,快来回答吧!

相关问题