Week 2 assignment

Sandeep_Kumar_Kalva · May 29, 2021, 6:00pm

ValueError Traceback (most recent call last)
in
----> 1 params, grads, costs = optimize(w, b, X, Y, num_iterations=100, learning_rate=0.009, print_cost=False)
2
3 print ("w = " + str(params[“w”]))
4 print ("b = " + str(params[“b”]))
5 print ("dw = " + str(grads[“dw”]))

in optimize(w, b, X, Y, num_iterations, learning_rate, print_cost)
35 # YOUR CODE STARTS HERE
36
—> 37 grads, cost = propagate(w, b, X, Y)
38 # YOUR CODE ENDS HERE
39

in propagate(w, b, X, Y)
29 # cost = …
30 # YOUR CODE STARTS HERE
—> 31 A = sigmoid(np.dot(w.T, X) + b)
32 cost = -1./mnp.sum((Ynp.log(A)+(1-Y)*np.log(1-A)))
33 # YOUR CODE ENDS HERE

ValueError: operands could not be broadcast together with shapes (2,3) (2,2)

I cannot find how to solve this error. Please help me in understanding this. Thanks.

albertovilla · May 29, 2021, 8:00pm

The error indicates that the np.dot operation fails because the inputs to that function are not compatible with the matrix multiplication operation, therefore something must be wrong with the shape of the inputs.

For matrix multiplication, the number of columns in the first matrix must be equal to the number of rows in the second matrix. The result matrix has the number of rows of the first and the number of columns of the second matrix. - Wikipedia

Sandeep_Kumar_Kalva · May 30, 2021, 7:52am

Dear Albertovilla,

Thank you for your response. The function ‘propagate’ (where ‘A’ is defined) was written correctly before implementing the function ‘optimize’. When I run the following code that is given after defining ‘propagate’ function, the test is passed as shown below:
w = np.array([[1.], [2.]])
b = 2.
X =np.array([[1., 2., -1.], [3., 4., -3.2]])
Y = np.array([[1, 0, 1]])
grads, cost = propagate(w, b, X, Y)

assert type(grads[“dw”]) == np.ndarray
assert grads[“dw”].shape == (2, 1)
assert type(grads[“db”]) == np.float64

print ("dw = " + str(grads[“dw”]))
print ("db = " + str(grads[“db”]))
print ("cost = " + str(cost))

propagate_test(propagate)

dw = [[0.99845601]

[2.39507239]]*
db = 0.001455578136784208
cost = 5.801545319394553
All tests passed!

However, After defining the function ‘optimise’, when test function by running the below lines
params, grads, costs = optimize(w, b, X, Y, num_iterations=100, learning_rate=0.009, print_cost=False)

print ("w = " + str(params[“w”]))
print ("b = " + str(params[“b”]))
print ("dw = " + str(grads[“dw”]))
print ("db = " + str(grads[“db”]))
print("Costs = " + str(costs))

optimize_test(optimize)

I get this error which is weird b/c it ‘np.dot’ worked before and now its giving the error:

ValueError Traceback (most recent call last)
in
----> 1 params, grads, costs = optimize(w, b, X, Y, num_iterations=100, learning_rate=0.009, print_cost=False)
2
3 print ("w = " + str(params[“w”]))
4 print ("b = " + str(params[“b”]))
5 print ("dw = " + str(grads[“dw”]))

in optimize(w, b, X, Y, num_iterations, learning_rate, print_cost)
36 # YOUR CODE STARTS HERE
37
—> 38 grads, cost = propagate(w, b, X, Y)
39 # YOUR CODE ENDS HERE
40

in propagate(w, b, X, Y)
29 # cost = …
30 # YOUR CODE STARTS HERE
—> 31 A = sigmoid(np.dot(w.T, X) + b)
32 cost = -1./mnp.sum(Ynp.log(A)+(1-Y)*np.log(1-A))
33 # YOUR CODE ENDS HERE

ValueError: operands could not be broadcast together with shapes (2,3) (2,2)

Please do suggest where am I doing it wrong. Thank you.

albertovilla · May 30, 2021, 1:36pm

I guess somehow you are modifying some of the parameters, for example, w.

In the propagate test case you have assert grads[“dw”].shape == (2, 1), so w.T cannot be (2,3), it should be (1, 2). What’s the print out of w in optimize?

Sandeep_Kumar_Kalva · May 30, 2021, 3:22pm

I have printed out the values of w, dw, X, b in optimise.
w = [[1.]
[2.]]
dw =[[0.99845601]
[2.39507239]]
X =[[ 1. 2. -1. ]
[ 3. 4. -3.2]]
b = 2.0
so w is of size(2,1) and w.T should be (1,2) and X is of (2,3). So np.dot(w.T,X) should be of shape (1,3). But not sure why it is showing as (2,3).

Joda · May 30, 2021, 4:51pm

I am also having the exact same error as Sandeep, which I posted below:

ValueError Traceback (most recent call last)
in
----> 1 params, grads, costs = optimize(w, b, X, Y, num_iterations=100, learning_rate=0.009, print_cost=False)
2
3 print ("w = " + str(params[“w”]))
4 print ("b = " + str(params[“b”]))
5 print ("dw = " + str(grads[“dw”]))

in optimize(w, b, X, Y, num_iterations, learning_rate, print_cost)
35 # grads, cost = …
36 # YOUR CODE STARTS HERE
—> 37 grads, cost = propagate(w, b, X, Y)
38
39 # YOUR CODE ENDS HERE

in propagate(w, b, X, Y)
29 # cost = …
30 # YOUR CODE STARTS HERE
—> 31 A = sigmoid(np.dot(w.T, X) + b)
32 cost = (-1/m)*(np.dot(Y, np.log(A).T) + np.dot(1 - Y, np.log(1 - A).T))
33

ValueError: operands could not be broadcast together with shapes (2,3) (2,2)

I have not made any hard coded size assertions in my own code and haven’t changed and of the assert statements in the assignment. I am not sure how else I can approach fixing the issue.

Sandeep_Kumar_Kalva · May 31, 2021, 5:37am

I have solved this problem. I was writing wrongly the equation for updating the term b in optimize function. After correcting it worked. There were no errors. Please do check your code carefully.

jimmyhe · June 7, 2021, 1:59pm

First time I look into this comment, I didn’t get it. But actually when I look more carefully, that’s it!

harrisonliang · July 1, 2021, 9:00am

I really like your answer, I made a silly mistake on the interation b, now the problem was solved

Prashanth_Kamath · October 23, 2021, 9:40pm

Hi @albertovilla,

I fixed this issue however I get a test error stating,

"AssertionError Traceback (most recent call last)
in
1 from public_tests import *
2
----> 3 model_test(model)

~/work/release/W2A2/public_tests.py in model_test(target)
117 assert type(d[‘costs’]) == list, f"Wrong type for d[‘costs’]. {type(d[‘costs’])} != list"
118 assert len(d[‘costs’]) == 1, f"Wrong length for d[‘costs’]. {len(d[‘costs’])} != 1"
→ 119 assert np.allclose(d[‘costs’], expected_output[‘costs’]), f"Wrong values for d[‘costs’]. {d[‘costs’]} != {expected_output[‘costs’]}"
120
121 assert type(d[‘w’]) == np.ndarray, f"Wrong type for d[‘w’]. {type(d[‘w’])} != np.ndarray"

AssertionError: Wrong values for d[‘costs’]. [array(0.15900538)] != [array(0.69314718)]
".

For the code written as follows

(≈ 1 line of code)

# initialize parameters with zeros 
# w, b = ...
w, b = initialize_with_zeros(X_train.shape[0])

#(≈ 1 line of code)
# Gradient descent 
# params, grads, costs = ...
params, grads, cost = optimize(w, b, X_train, Y_train, num_iterations, learning_rate, print_cost = False)

The cost function passes all the tests. I am not able to resolve this and move forward at all. Any suggestions to improve the code? Kindly advise.

Purvaja_Soochit · February 14, 2022, 2:28am

I used function propagate instead of optimize

mrqasimasif · May 25, 2023, 11:51am

Hi, I am facing the same problem, did you happen to find the solution?

saifkhanengr · May 25, 2023, 11:56am

Please post your full error.

Faisal_Bin_Basha · August 2, 2023, 2:43pm

Hi, even I have this exact same issue I am not sure where my mistake is ?

saifkhanengr · August 2, 2023, 3:50pm

I’ve replied to your original post here.

Topic		Replies	Views
Programming Assignment: Logistic Regression with a Neural week1 Neural Networks and Deep Learning week-2	4	138	April 24, 2024
Week 2 Exercise 6 optimize Neural Networks and Deep Learning	3	574	September 28, 2021
Week 2 Exercise 6 - Propagate passes all tests but raises errors in Optimize Neural Networks and Deep Learning	3	526	January 24, 2022
Week 2 exercise 5 (propagate) Neural Networks and Deep Learning	6	598	September 19, 2022
C1 W2 A2 propagate Neural Networks and Deep Learning	3	577	January 9, 2023

Week 2 assignment

(≈ 1 line of code)

Related topics