Stderr despite changing tf version an passing all tests

Course Q&A TensorFlow: Advanced Techniques Specialization Advanced Computer Vision with TensorFlow
1

*https://www.coursera.org/learn/advanced-computer-vision-with-tensorflow/programming/Z96hp/image-segmentation-of-handwritten-digits/submission

  • I get the problem: There was a problem grading your submission. Check stderr for more details.

Despite having completed all tests, all gradings except the hand-in and changing tf version. Where are the so called “stderr” mentioned? I’m happy to share the notebook if someone got a solution idea.

2

@Axel_Carlsson, unfortunately, that error is not an especially helpful one. There was a problem in the past with this assignment that gave this error for iou score. The problem turned out to be due to a tensorflow and keras version mismatch between the autograder and the lab.

The “Save Model” portion of the assignment has been updated to include steps to help you work around the issue with the version mismatch with the grader.

I’m guessing you’re using this version of the assignment since it was updated back in January. One way to recognize that you have this version is that it downloads the model using the file name, final_model.h5

A couple more things to check:

  1. Make sure you have followed the instruction in the assignment to go to Runtime > Restart Session and wait for the kernel to reconnect after you have pip installed tensorflow and keras version 2.8.0, and before you load temp_model.h5 and save final_model.h5
  2. Make sure when you submit the assignment, you choose the “Replace file” link and select the downloaded file named final_model.h5
1 Like