[EdgeTPU] RuntimeError: Found too many dimensions in the input array of operation 'reshape'.

[sinclairnick]

I have experimented with a few models in the repo and run into this error several times. Namely, YOLOv3-lite and the mobilenet-MNSFPN compiled using the edge-tpu compiler result in this error when run using the DetectionEngine. Is this some error on my part, or have you also found the same errors?

P.S. the compilation works successfully

[Namburger]

@sinclairnick The detection engine expects 4 outputs tensors, I don't know much about these models but the outputs may be mismatched. You can try using the tflite interpreter to check the model outputs or use netron tool to understand the model

[sinclairnick]

The detection engine throws a very specific error when this is the case, along the lines of “Expected 4 output tensors, but got {}”. I came across this error when using TFLite also. Thanks Nam

…

On 9/07/2020, at 5:51 AM, Nam Vu ***@***.***> wrote: @sinclairnick <https://github.com/sinclairnick> The detection engine expects 4 outputs tensors, I don't know much about these models but the outputs may be mismatched. You can try using the tflite interpreter to check the model outputs or use netron tool to understand the model — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#12 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AC2V3H4QGCAUIMV3P7TSBRTR2SW27ANCNFSM4OONS2PQ>.

[PINTO0309]

same issue #7