Assignment file format

[Jenna]

I am wondering if there is instructions on how to submit the assignment. What type of file should we submit? What format should it be? Thank you.

[chris.favila]

Hi Jenna. There are instructions toward the end of the notebook:

Coursera Labs will automatically convert your notebook to the format that the grader will accept. I recommend saving your work first though before pressing the Submit Assignment button. Sometimes Coursera gets a blank version of the notebook if that’s not done. We’ll modify the instructions in the notebook to make that clearer.

Hope this helps!

[Jenna]

Thank you so much Chris.

I submitted the notebook in ipynb format, and wasn’t able to pass the grader, with “Function “model.fit” not found in Code Cell 11. Please make sure you have not altered the cell positions from the original exercise question.”.

So not 100% about why. Thank you.
T

[chris.favila]

Hi Jenna. You might have introduced a new cell while debugging your solution. You can delete that and resubmit. If it doesn’t work, please see this post for instructions on how to get a new notebook. Once you have the blank notebook, you can copy your old solutions there, and then resubmit. Hope it works!

[Jenna]

Thank you @chris.favila.

Fixed it but now it’s saying that “Sorry, your submission was incorrect. Please try again. ‘image’ must be at least three-dimensional.”.

Here is my code:

def format_example(image, label):
# Cast image to float32
image = tf.cast(image, tf.float32)

# Normalize the image in the range [0, 1]
image = tf.image.per_image_standardization(image)

return image, label

Not sure where it went wrong. Thank you.

[chris.favila]

Hi Jenna! Sorry just saw this. You may want to check this post because the solution is similar (but your initial solutions are different). Just let me know if you need more hints. Thanks!

[Jenna]

Hi Chris,

I probably still need more hint. The model is fine, but the grader wouldn’t pass me for some reason. Thank you.

[Jenna]

Actually I tried again with 2nd line of the code within “format_example” - divided the pixels directly and it worked! Thank you!