# Wrong Grader output

**URL:** <https://community.deeplearning.ai/t/wrong-grader-output/77857>\
**Category:** Convolutional Neural Networks\
**Tags:** coursera-platform\
**Created:** [December 22, 2021, 4:50pm UTC](https://community.deeplearning.ai/t/wrong-grader-output/77857 "2021-12-22T16:50:21Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![user344](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/user344/32/10803_2.png) [@user344](https://community.deeplearning.ai/u/user344)\
**Post date:** [December 22, 2021, 4:50pm UTC](https://community.deeplearning.ai/t/wrong-grader-output/77857/1 "2021-12-22T16:50:21Z")

</div>

Even though I am passing all the tests , I am getting score of only 50.  
Grader shows output that - these tests could be hidden . Please check your submission.

---

<div class="post-metadata">

**Author:** ![paulinpaloalto](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/paulinpaloalto/32/187_2.png) [@paulinpaloalto](https://community.deeplearning.ai/u/paulinpaloalto)\
**Post date:** [December 22, 2021, 7:50pm UTC](https://community.deeplearning.ai/t/wrong-grader-output/77857/2 "2021-12-22T19:50:57Z")

</div>

You don’t tell us which assignment you are talking about. If it is the first assignment in C4 Week 1, then there is a known bug in the unit tests: they do not catch the error of not including the stride in your logic for _conv\_forward_ and _pool\_forward_.

---

<div class="post-metadata">

**Author:** ![user344](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/user344/32/10803_2.png) [@user344](https://community.deeplearning.ai/u/user344)\
**Post date:** [December 23, 2021, 11:12am UTC](https://community.deeplearning.ai/t/wrong-grader-output/77857/3 "2021-12-23T11:12:31Z")

</div>

Its error in W4 assignment 1  
And i have included stride

---

<div class="post-metadata">

**Author:** ![paulinpaloalto](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/paulinpaloalto/32/187_2.png) [@paulinpaloalto](https://community.deeplearning.ai/u/paulinpaloalto)\
**Post date:** [December 23, 2021, 4:58pm UTC](https://community.deeplearning.ai/t/wrong-grader-output/77857/4 "2021-12-23T16:58:00Z")

</div>

There are also right and wrong ways to include the stride. Are you sure that you checked all the outputs of _pool\_forward_ in the _stride = 2_ case. They all need to match, not just most of them. And the problem is that the test case doesn’t throw an error if they don’t match. One other thing to check is that the type of your output for _conv\_single\_step_ is not being coerced to _float32_. That will pass the unit test for that function, but fail the grader.

---

<div class="post-metadata">

**Author:** ![paulinpaloalto](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/paulinpaloalto/32/187_2.png) [@paulinpaloalto](https://community.deeplearning.ai/u/paulinpaloalto)\
**Post date:** [December 23, 2021, 5:02pm UTC](https://community.deeplearning.ai/t/wrong-grader-output/77857/5 "2021-12-23T17:02:52Z")

</div>

Oh, sorry, do you mean Week 4 Assignment 1? That’s Face Recognition, which is a whole different case, then.

---

<div class="post-metadata">

**Author:** ![user344](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/user344/32/10803_2.png) [@user344](https://community.deeplearning.ai/u/user344)\
**Post date:** [December 23, 2021, 5:07pm UTC](https://community.deeplearning.ai/t/wrong-grader-output/77857/6 "2021-12-23T17:07:24Z")

</div>

Oh sorry my typing mistake.  
I was talking about same as yours C4 W1 Assignment