I have successfuly completed the week 3, programming assignment. this was the output of the driver training:
Cost after iteration 0: 0.693086
Cost after iteration 1000: 0.000220
Cost after iteration 2000: 0.000108
Cost after iteration 3000: 0.000072
Cost after iteration 4000: 0.000054
Cost after iteration 5000: 0.000043
Cost after iteration 6000: 0.000036
Cost after iteration 7000: 0.000030
Cost after iteration 8000: 0.000027
Cost after iteration 9000: 0.000024
W1 = [[ 0.71392202 1.31281102]
[-0.76411243 -1.41967065]
[-0.75040545 -1.38857337]
[ 0.56495575 1.04857776]]
b1 = [[-0.0073536 ]
[ 0.01534663]
[ 0.01262938]
[ 0.00218135]]
W2 = [[ 2.82545815 -3.3063945 -3.16116615 1.8549574 ]]
b2 = [[0.00393452]]
All tests passed!
But, when I explicity train the model using:
nn_model(X,Y,4,print_cost=True)
the output is:
Cost after iteration 0: 0.693116
Cost after iteration 1000: 0.282991
Cost after iteration 2000: 0.266770
Cost after iteration 3000: 0.259013
Cost after iteration 4000: 0.256956
Cost after iteration 5000: 0.253551
Cost after iteration 6000: 0.250299
Cost after iteration 7000: 0.247534
Cost after iteration 8000: 0.245734
Cost after iteration 9000: 0.244419
{‘W1’: array([[ -0.10976777, -11.04379218],
[-10.32466393, -10.50524738],
[ -2.98252288, -1.45933805],
[ 0.53725833, 0.24953177],
[ -4.59181086, -8.69485444],
[ -9.972046 , 12.69249904],
[ -1.8753276 , 4.98785028]]),
‘b1’: array([[-0.15050221],
[ 0.0648266 ],
[ 0.26964829],
[-0.06060059],
[-0.59661557],
[-0.18946601],
[-0.68132552]]),
‘W2’: array([[-10.3176535 , 6.82734816, -4.83699664, -3.24364976,
2.57823027, -6.39279918, 1.40952222]]),
‘b2’: array([[0.04254188]])}
The cost is not decreasing, and the output does not seem right. What is wrong?
