''module' object is not callable sgd
Here is my code.
from keras.optimizers import gradient_descent_v2 as SGD
sgd=SGD(lr=0.01,momentum=0.9,decay=(0.01/25),nesterov=False)
I get the following error when I try to run it.
----> 1 sgd=SGD(lr=0.01,momentum=0.9,decay=(0.01/25),nesterov=False)
TypeError: 'module' object is not callable
Solution 1:[1]
Try with tensorflow tf.keras.optimizers.SGD(lr=0.01, momentum=0.9, decay=1e-6, nesterov=False).
Solution 2:[2]
You do not need to use the gradient_descent_v2 to import SGD optimizer.
Now, SGD(Stochastic Gradient Descent) optimizer inherits from tf.keras.optimzers, which you can import by giving it's exact alias name as below:
from tensorflow.keras.optimizers import SGD
sgd=SGD(learning_rate=0.01,momentum=0.9,decay=(0.01/25),nesterov=False)
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 | RiveN |
| Solution 2 | TFer2 |
