[Python] working on the two_layer_model function in the Week 4 Assignment (W4A2) of the Deep...

I’m working on the two_layer_model function in the Week 4 Assignment (W4A2) of the Deep Learning Specialization on Coursera.

I’ve implemented the model using the required structure: LINEAR -> RELU -> LINEAR -> SIGMOID, and it returns both parameters and costs as expected.

However, when I run the autograder with:

parameters, costs = two_layer_model(train_x,
train_y,
layers_dims=(n_x, n_h, n_y),
num_iterations=2)
print("Cost after first iteration:", costs[0])
two_layer_model_test(two_layer_model)


I get the following error:

Cost after first iteration: 0.6931955461346408
Error: Datatype mismatch.
Error: Wrong shape
Error: Wrong output
Error: Wrong output
0 Tests passed
4 Tests failed


I’ve double-checked that I’m not using global variables, the function signature matches the expected one, and that parameters is a dictionary with keys 'W1', 'b1', 'W2', 'b2'.

Can anyone suggest what might be causing the autograder to fail all tests, even though the cost value looks correct?

Continue reading...