I have a TensorFlow 2.x object detection model (ssd resnet50 v1) that was trained on an Ubuntu 20.04 box with a GPU.
The predictions from the model preform as expected on Linux CPU&GPU, Windows 10 CPU&GPU, and Intel MacBook Air CPU, and the M1 MacBook Air CPU.
However, when I install the tensorflow-metal plugin on the M1, I can see the GPU is being used but the predictions are garbage.
I followed these install instruction:
https://developer.apple.com/metal/tensorflow-plugin/
Which gives me:
- tensorflow-macos 2.6.0
- tensorflow-metal 0.2.0
and
- Python 3.9.5
Anyone have insight as to what may be the problem? The M1 Air is running the public release of Monterey.