Why does the transposed convolution in TensorFlow take significantly longer after being quantized with TFLite?

[wdfyjnnmkc]

import tensorflow as tf
import os

saved_model_dir = "./model_code/test8/encoder/"

if not os.path.exists(saved_model_dir):
raise FileNotFoundError(f"Model file not found at:{saved_model_dir}")

converter = tf.lite.TFLiteConverter.from_saved_model(saved_model_dir)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
tflite_model = converter.convert()

with open("enc1.tflite", "wb") as f:
f.write(tflite_model)

[123Mrxiao]

你好，邮件我已收到！现在繁忙稍后回复。

[jiandandema]

谢谢您给马坤发送邮件，我会及时查看的，谢谢，辛苦了