First I have a gzipped file named maia-1900.pb.gz, I unzipped it by double clicking on mac and a file named maia-1900.pb was outputted. I tried loading the model with model = tf.saved_model.load("maia-1900") but I got an error saying: OSError: SavedModel file does not exist at: maia-1900/{saved_model.pbtxt|saved_model.pb} .

In the current deep learning support libraries such as tensorflow hub, pytorch torch, hugging face transformer, there are many built-in functions such as tokenizer etc.,

I read some code on the Vgg16 and I have some questions please. In some code I notice that they use the outputs like this :

Using tensorflow
I am using the following model: