Course 2 Week 2, Programming assignment, Exc. 6.1 - Mini-Batch Gradient Descent "ValueError: operands could not be broadcast together with shapes (1,44) (1,64)"

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
1

Hi all. Is there an error in this exercise? In all previous exc. all test passed, and this is not supposed to have any student code:

6.1 - Mini-Batch Gradient Descent

…
…

ValueError 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)
56
57 # Compute cost and add to the cost total
—> 58 cost_total += compute_cost(a3, minibatch_Y)
59
60 # Backward propagation

~/work/release/W2A1/opt_utils_v1a.py in compute_cost(a3, Y)
98 “”"
99
→ 100 logprobs = np.multiply(-np.log(a3),Y) + np.multiply(-np.log(1 - a3), 1 - Y)
101 cost_total = np.sum(logprobs)
102

ValueError: operands could not be broadcast together with shapes (1,44) (1,64)

Thank you!

2

Hi sotofernando,

As a belated reply:
The public tests do not capture all possible bugs in your code. As the error traceback indicates, there is a mismatch of dimensions beween a3 and Y. This means there is a bug somewhere in your code calculating a3 and Y, maybe in your function random_mini_batches.