[Urgent] I cannot get 0.95 Similarity on C3W4

[tiagoblima]

I have completed all mandatory steps in the code without any errors or warnings. And output seems alright, but I cant get to pass the Assigment.
images.zip (176.0 KB)
The similarity keeps nearly zero, any clue?
I am attaching the generated images in this post.

[Deepti_Prasad]

Hello @tiagoblima

Kindly follow the below post

TF-AT: Using the Fallback Runtime to Avoid Slow Training in Colab

Google Colab updates its runtime periodically to use newer versions of packages like Tensorflow. This can sometimes affect the use of GPUs for notebooks that require older versions. You will notice that when you reach the training part of the exercise. The lack of GPU will result in waiting several minutes per epoch. To get around it, please use the fallback runtime before running any of the code in your notebook. Here are the steps: Make sure that you are already connected to a GPU. You can c…

Make sure you have deleted your browsing and cache history before you try the above step.

In case you still encounter issue, kindly let me know.

Regards
DP

[tiagoblima]

Actually, I tried this step, but I didnt found the version needed. So instead of using the NV_LIBCUBLAS_VERSION=11 I used the NV_LIBCUBLAS_VERSION=12.

[tiagoblima]

I tried it again in a new browser. I get this error

[Deepti_Prasad]

Hi @tiagoblima

Then kindly go through this comment, which tells some of the common mistakes one can do,

Advanced computer vision saliency maps week 4 assignment ssim score

is this the way you recalled the labels or included label with 2? Please give detail about which activation you have used for the last dense layer in your model? The most common mistake by learners in this assignment was related def do salience grader cell where the learner missed converting the image from BGR to RGB, check if you have done this. The next usual mistake one can do in the below statement of def do salience grader cell Define the expected output array by one-hot encodi…

In case you have followed all the steps, and still facing issue, then one needs to look at your codes once.

If all the above steps doesn’t resolve your issue, then you can DM me your download assignment. Click on my name then message.

Regards
DP

[chris.favila]

Hi Tiago (and other learners who might be following this topic). From your screenshot, it seems you’re using a slightly older version of the notebook. If you re-open it from the classroom, you shouldn’t see a “Use the Fallback Runtime” section. You can copy your solutions there. However, I don’t think it will change your output. Please follow Deepti’s advice re: the exercises. You can also check the ungraded labs for reference. Hope this helps.

[Deepti_Prasad]

Hello @tiagoblima,

You haven’t check the comment where I told you to crosscheck the comments with your comments… as I can see your mistakes are similar to the comment I shared.

I want you to open again your notebook and check my previous comment where I have shared a comment stating where all common mistakes can happen. I checked your notebook and you have missed some of the important steps and also recalled labels incorrectly in do salience cells.

Advanced computer vision saliency maps week 4 assignment ssim score

is this the way you recalled the labels or included label with 2? Please give detail about which activation you have used for the last dense layer in your model? The most common mistake by learners in this assignment was related def do salience grader cell where the learner missed converting the image from BGR to RGB, check if you have done this. The next usual mistake one can do in the below statement of def do salience grader cell Define the expected output array by one-hot encodi…

Let me know after correction, what is the progress.

Regards
DP

[tiagoblima]

Thanks a lot for your pacient! I’ve made that work properly seeing the comments. I do apologise for any inconvinience.

[Deepti_Prasad]

Hello @tiagoblima

No problem, nothing to be sorry. I only didn’t give direct answer because you get better at debugging your codes. Can I know if you have passed the assignment? If not please feel free to ask any help!!!

Regards
DP

[tiagoblima]

Yes, I passed the assignment. Thank you so much.