Optimization methods 6.1

[AIchemist]

Hi There,
Please help! Thanks very much!

My codes run well before 6.1 - Mini-Batch Gradient Descent, no error showing up.
However, after running 6.1, i get this:

TypeError Traceback (most recent call last)
in
1 # train 3-layer model
2 layers_dims = [train_X.shape[0], 5, 2, 1]
----> 3 parameters = model(train_X, train_Y, layers_dims, optimizer = “gd”)
4
5 # Predict

in model(X, Y, layers_dims, optimizer, learning_rate, mini_batch_size, beta, beta1, beta2, epsilon, num_epochs, print_cost)
44 # Define the random minibatches. We increment the seed to reshuffle differently the dataset after each epoch
45 seed = seed + 1
—> 46 minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
47 cost_total = 0
48

in random_mini_batches(X, Y, mini_batch_size, seed)
19
20 # Step 1: Shuffle (X, Y)
—> 21 permutation = list(np.random.permutation(m))
22 shuffled_X = X[:, permutation]
23 shuffled_Y = Y[:, permutation].reshape((1, m))

TypeError: ‘numpy.ndarray’ object is not callable

[TMosh]

The only way that line 21 throws that error is if there is a problem with your code in random_mini_batches() where it computes ‘m’. So that’s the first place to look.

One way that could happen is if there is a mistake in your model() function, which is triggered the first time the model() is called using the ‘gd’ optimizer.

[paulinpaloalto]

One mistake that could cause that error message is that if you have assigned a value to the variable list which is a numpy array. list is originally a python function, but in python you can overwrite any variable name with a different value. It is a very dangerous practice to overwrite python’s predefined objects.