Compile your TensorFlow Lite model for compatibility with the Edge TPU by uploading your
.tflite file below.
We strongly recommend that you instead use the offline Edge TPU Compiler.
Alternatively, you can also train and compile an Edge TPU model online using AutoML Vision.
To create a TensorFlow model that takes full advantage of the Edge TPU at runtime, it must meet the following requirements:
- Tensor parameters are quantized (8-bit fixed-point numbers). You must use quantization-aware training (post-training quantization is not supported).
- Tensor sizes are constant at compile-time (no dynamic sizes).
- Model parameters (such as bias tensors) are constant at compile-time.
- Tensors are either 1-, 2-, or 3-dimensional. If a tensor has more than 3 dimensions, then only the 3 innermost dimensions may have a size greater than 1.
- The model uses only the operations supported by the Edge TPU (see the following link).
For more details about creating compatible models, read TensorFlow models on the Edge TPU.