Get the intermediate layer output during training and testing

TensorFlow General Discussion
,
1

I have the following demo model:

class MyModel(Model):
    def __init__(self):
        super(MyModel, self).__init__()
        self.conv1 = Conv2D(32, 3, activation='relu')
        self.flatten = Flatten()
        self.d1 = Dense(128, activation='relu')
        self.d2 = Dense(10)
    def call(self, x):
        x1 = self.conv1(x)
        x2 = self.flatten(x1)
        x3 = self.d1(x2)
        return self.d2(x3)

# Create an instance of the model
model = MyModel()

During training, I want to get the output of the intermediate layer, for example self.conv1, x2.

Do you have any suggestions?
thx

3

Yes, Model knows when it’s training or testing, the flag is auto set when you call train() or predict().

4

@Ramyar_Jahani Hi Ramyar, I want to dump the weights and output of some intermediate layers in some iterations to the local disk. Do you have any suggestions?