i am not getting the correct value, please help
You shared no week and assignment number, so, how could mentors know which specific assignment you’re referring to? Though I know correctly, I request that you provide these details before I assist you.
PS: When I face any issue while doing any course, my procedure for asking help is: respect mentors’ time and make their job easy by giving them complete and accurate information.
knowing the topic in the header I assume that the mentors know what i am asking, this is the last assignment of week 4, neural style transfer. you should also respect learners
It is very helpful to the mentors if you give the week number and assignment number. This lets us go directly to the appropriate course notebook, without having to research the names of every assignment in every week of every course.
Next time I will comply
Franklin Viloria
It looks like you instrumented your gram_matrix function to print GA, so I added that along with some other instrumentation in compute_style_layer_cost and here’s what I see:
type(a_G) <class 'tensorflow.python.framework.ops.EagerTensor'>
m is 1
shape(a_S) [1 4 4 3]
shape(a_G) [1 4 4 3]
after reshape+T: shape(a_S) [ 3 16]
after reshape+T: shape(a_G) [ 3 16]
a_S [[ 2.6123514 6.3462267 -2.0568852 1.0848972 -0.34144378 5.9450154
-0.68249106 6.6380787 4.405425 3.2136106 -0.88850987 8.216282
1.1940846 -3.8442307 4.486284 -3.2315984 ]
[-3.3520837 3.8470404 -3.1489944 -1.2055032 -3.17067 -1.7347562
-3.1652112 -0.90944517 0.31713337 0.23800504 -0.10706711 0.6901974
1.7071393 6.2297974 -2.2124014 -5.5964684 ]
[ 0.74761856 -0.95714605 -4.0077353 -5.972679 5.036553 3.6944358
-1.7189786 9.18924 2.566379 1.4399388 -1.7099016 3.6196625
-0.9568796 2.8206615 -4.4811783 3.4338741 ]]
GA =
[[277.3386 1.9207706 84.06223 ]
[ 1.9207706 139.91864 -1.1867776]
[ 84.06223 -1.1867776 244.99716 ]]
GA =
[[277.3386 1.9207706 84.06223 ]
[ 1.9207706 139.91864 -1.1867776]
[ 84.06223 -1.1867776 244.99716 ]]
J_style_layer 0.0
type(a_G) <class 'tensorflow.python.framework.ops.EagerTensor'>
m is 1
shape(a_S) [1 4 4 3]
shape(a_G) [1 4 4 3]
after reshape+T: shape(a_S) [ 3 16]
after reshape+T: shape(a_G) [ 3 16]
a_S [[-3.404881 -2.5186315 1.3512313 -1.8821764 -0.39341784 5.434381
-0.2787553 3.5750656 -2.616547 1.2345984 0.25895953 -2.933355
-5.2402277 0.19823879 1.3253293 -0.41526246]
[ 7.183007 -3.8986888 0.18695849 -1.5039697 -0.34587932 6.118635
2.493302 9.585233 6.579515 -0.9685255 -0.5711074 2.555351
0.36834985 7.452428 6.3523054 0.583993 ]
[ 2.534576 -2.9244845 -1.2326248 -1.8601038 1.730303 0.91409665
2.0111642 -2.3005989 5.8995004 -2.2799122 -1.6340904 -3.1489797
-0.42677724 3.718691 5.739221 -2.0045857 ]]
GA =
[[112.29061 37.05909 -1.9554844]
[ 37.05909 352.1803 116.86712 ]
[ -1.9554844 116.86712 136.64961 ]]
GA =
[[277.3386 1.9207706 84.06223 ]
[ 1.9207706 139.91864 -1.1867776]
[ 84.06223 -1.1867776 244.99716 ]]
J_style_layer 14.01648998260498
J_style_layer = tf.Tensor(14.01649, shape=(), dtype=float32)
All tests passed
You can see that the GA values I get are significantly different than yours. One possible mistake is to directly reshape to the final shape you want for a_S and a_G instead of including a transpose to preserve the channels dimension.
Here’s an earlier thread about this issue. And that thread points to this one, which demonstrates why just the direct reshape doesn’t work.
Indeed, I tried making the mistake I described above and I get answers for GA that are close to yours, but differ in the second or third decimal places. So I think you probably made that mistake and are also seeing the differences caused by running locally on your own computer.
Note that it is a slightly risky method to work on the notebooks in a different environment and then upload them back to the Coursera website to be graded. We have seen cases, e.g. using Google Colab, where the external tools can rewrite the JSON “metadata” in the notebooks in a way that confuses the Coursera graders.
Paul,
I am very grateful for your advise of using google colab notebook, I just used it with the art generation using my own content and style images while my computer made epoch 250 google GPU T4 finished all 2500 epochs, that was great, by the way i have to load the files to google drive and change paths.
thank you
It’s great that you were able to get that to work and figure out the other changes you needed to make in terms of adapting to the way Colab handles files. Sorry, I should have mentioned that we have a guide for how to adapt to Colab by mentor Saif, but you’ve already figured it out.
