Edge TPU Model Compiler

Compile your model for the Edge TPU

Compile your TensorFlow Lite model for compatibility with the Edge TPU by uploading your .tflite file below.

For more information about how to create a model, see TensorFlow models on the Edge TPU.

Model requirements

DURING BETA

Currently, the Edge TPU compiler requires that your model use one of the following architectures:

  • MobileNet V1/V2:
    224x224 max input size; 1.0 max depth multiplier
  • MobileNet SSD V1/V2:
    320x320 max input size; 1.0 max depth multiplier
  • Inception V1/V2:
    224x224 fixed input size
  • Inception V3/V4:
    299x299 fixed input size

All models must be a quantized TensorFlow Lite model (.tflite file) less than 100MB.

COMING SOON

In a future update, we will remove the architecture-type restrictions. You can then compile any quantized TensorFlow Lite model that meets certain requirements:

  • All tensor sizes are fixed at compile-time (no dynamic sizes).
  • All model parameters (such as bias tensors) are fixed at compile-time.
  • All 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.

Other operation-specific limitations also apply. We will provide those details when the new compiler is available.


Do not close this window

Model successfully compiled.
Download it!