https://community.nxp.com/t5/i-MX-Processors/Help-Needed-Running-Custom-TensorFlow-Lite-Model-using/m-p/1945531#M227927 <P>Hello NXP Community,</P><P>I’m working on deploying a custom TensorFlow Lite model on the i.MX8M Plus following the guidelines provided in the TensorFlow Lite <A href="https://www.tensorflow.org/lite/models/modify/model_maker/object_detection" target="_self">Model Maker documentation</A>. While the model works fine on the CPU, it fails to run on the NPU despite enabling libvx_delegate.so.</P><P><STRONG>Request:</STRONG></P><UL><LI><STRONG>Model Compatibility</STRONG>: How can I ensure my .tflite model is compatible with the i.MX8M Plus NPU?</LI><LI><STRONG>Configuration</STRONG>: Are there specific settings needed for NPU execution?</LI><LI><STRONG>Troubleshooting</STRONG>: What are common steps for resolving issues where a model runs on CPU but not on NPU?</LI></UL><P>I’ve attached the .tflite model and detection code for reference.</P><P>Thank you for your help!</P><P>Best regards,<BR />Adarsh K V</P> Mon, 02 Sep 2024 14:06:10 GMT adarshkv 2024-09-02T14:06:10Z https://community.nxp.com/t5/i-MX-Processors/Help-Needed-Running-Custom-TensorFlow-Lite-Model-using/m-p/1945531#M227927 <P>Hello NXP Community,</P><P>I’m working on deploying a custom TensorFlow Lite model on the i.MX8M Plus following the guidelines provided in the TensorFlow Lite <A href="https://www.tensorflow.org/lite/models/modify/model_maker/object_detection" target="_self">Model Maker documentation</A>. While the model works fine on the CPU, it fails to run on the NPU despite enabling libvx_delegate.so.</P><P><STRONG>Request:</STRONG></P><UL><LI><STRONG>Model Compatibility</STRONG>: How can I ensure my .tflite model is compatible with the i.MX8M Plus NPU?</LI><LI><STRONG>Configuration</STRONG>: Are there specific settings needed for NPU execution?</LI><LI><STRONG>Troubleshooting</STRONG>: What are common steps for resolving issues where a model runs on CPU but not on NPU?</LI></UL><P>I’ve attached the .tflite model and detection code for reference.</P><P>Thank you for your help!</P><P>Best regards,<BR />Adarsh K V</P> Mon, 02 Sep 2024 14:06:10 GMT https://community.nxp.com/t5/i-MX-Processors/Help-Needed-Running-Custom-TensorFlow-Lite-Model-using/m-p/1945531#M227927 adarshkv 2024-09-02T14:06:10Z https://community.nxp.com/t5/i-MX-Processors/Help-Needed-Running-Custom-TensorFlow-Lite-Model-using/m-p/1946350#M227981 <P>Hello,</P> <P>It looks like the model is not compatible with Tensor flow lite that came in the eIQ of MX8Mplus, you need to create a model with the tensor flow lite 2.1v</P> <P>Regards</P> Tue, 03 Sep 2024 14:22:06 GMT https://community.nxp.com/t5/i-MX-Processors/Help-Needed-Running-Custom-TensorFlow-Lite-Model-using/m-p/1946350#M227981 Bio_TICFSL 2024-09-03T14:22:06Z