Closed puelon closed 1 year ago
Hi @puelon I am getting an inference about 53ms on my Machine. Pleases try the below steps:
wget https://raw.githubusercontent.com/hjonnala/snippets/main/coral_inference.py
python3 coral_inference.py -m /home/Downloads/model_91_test_acc_PQAT_edgetpu.tflite
Please forgive me, due to the amount of optimization on my code I actually forgot to run the command to compile the model for Edge TPU, it is now running around 80ms on my Rpi
I have a Transfer Learning model from a VGG16 that I trained on my thermal images and after doing PQAT to try and compress model size, I notice that it still has a large inference time of around 5 seconds per image. The same model being compressed to an intel neural stick 2 has around 450ms. I suspect that my model may not be compatible layer-wise with the coral usb device. This is the link to my tflite converted model: https://www.mediafire.com/file/e3z930wlh4vkwt8/model_91_test_acc_PQAT.tflite/file It has two outputs and this is the layer summary:
I wonder if this is something with the model or is it a hardware issue?