Open tonieichelkraut opened 1 year ago
Try using interpreter.getOutputTensors()
and interpreter.getInputTensors()
. As the name suggests they return a List of Tensors which get expected.
You could call interpreter.getInputTensors().forEach((tensor) => print(tensor))
to get every input tensor, same or output.
Maybe look into this example. Here the model takes a Tensor of the shape [1, 300, 300, 3] and outputs multiple tensors as you can see in line 142.
You can also get a single input or output tensor by just calling interpreter.getInputTensor(int index)
or interpreter.getOutputTensor(int index)
.
Hi, I have a model with multiple inputs and outputs. When I run the model in python, I use the signature runner
This nicely helps me to map my inputs and outputs. In flutter-tflite this feature does not seem to be present (I am new to flutter/dart). When I use the
I need to know the order of the input and output list. When I run
I get
However, the "StatefulPartitionedCall:X" are not what corresponds to my output names in my python code. I don't want to get the mapping correct, just by trying. Any suggestions, how I can solve this with the available feature set or how I access the "signature runner" from dart?
Thank you!