I'm new to TensorFlow and started training my model in Google Collaboratory. After spending a few hours training my model, I was finally able to download the tflite file, and it's working great! The only issue I have with it is its speed. I've looked into post-training quantization, but it seems as if I still need the Keras model to do that, but all I have left is the actual tflite file itself, as the notebook has since been closed and all data lost. Is there any way I can quantize the file itself? Thank you in advance for replies.
I tried using the tf.lite.Interpreter to load the model into a keras optimizer, but that didn't work.
