search

google / automl

Google Brain AutoML
Apache License 2.0
6.22k stars 1.45k forks source link

With TfLite, the last EfficientDet op (TFLite_Detection_PostProcess) is not supported on the GPU #1174

Open saad-palapa opened 2 years ago

saad-palapa commented 2 years ago

I'm running the TfLite model analyzer on the EfficientDet TfLite file like so:

model_path = "/content/efficientdet.tflite"
tf.lite.experimental.Analyzer.analyze(model_path=model_path, gpu_compatibility=True)

One output line shows that the last layer is not a supported TfLite GPU operation:

GPU COMPATIBILITY WARNING: Not supported custom op TFLite_Detection_PostProcess

GPU COMPATIBILITY WARNING: Subgraph#0 has GPU delegate compatibility issues at nodes 482 with TFLite runtime version 2.8.2

This is causing latency issues. Any ideas on how to fix this?