# Week2 Emoji\_v3a low test accuracy but passed the grader **URL:** \ **Category:** Sequence Models\ **Tags:** coursera-platform\ **Created:** [February 26, 2022, 2:27pm UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405 "2022-02-26T14:27:37Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![gbdantoni](https://avatars.discourse-cdn.com/v4/letter/g/e495f1/32.png) [@gbdantoni](https://community.deeplearning.ai/u/gbdantoni)\ **Post date:** [February 26, 2022, 2:27pm UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/1 "2022-02-26T14:27:38Z")
My code for Emoji\_v3a passes all of the internal tests and shows high accuracy and low loss values when training the Emojify\_V2 model but consistently gets a test accuracy value around 0.5. I carefully went through my code to compare my outputs against the expected outputs but couldn’t find any problems so I submitted the assignment, hoping the grader would identify which section of my code was incorrect, but the grader gave me 100/100 and said all functions are correct. Should I really expect the test accuracy to be between 80% and 95% and if so, where should I look to see what’s wrong? ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [February 27, 2022, 12:10am UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/2 "2022-02-27T00:10:58Z")
I get 80% on the test set when I run my noteboook. What loss and accuracy do you get from cell with the model.fit() results? Please post the values from the last few iterations. ---
**Author:** ![gbdantoni](https://avatars.discourse-cdn.com/v4/letter/g/e495f1/32.png) [@gbdantoni](https://community.deeplearning.ai/u/gbdantoni)\ **Post date:** [February 27, 2022, 12:27am UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/3 "2022-02-27T00:27:20Z")
The final loss and accuracy are: 0.0644 and 0.9848. ![image](https://global.discourse-cdn.com/dlai/original/2X/f/f8deadf64b0f4a3f907c6ddeed07872ee66b60a1.png) ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [February 27, 2022, 12:35am UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/4 "2022-02-27T00:35:32Z")
Those are the training set results, they look fine. I’m not sure why you’d have that much lower accuracy on the test set. I’ll think about it for a bit, and reply again if I have any ideas. ---
**Author:** ![Jiachen\_Sun](https://avatars.discourse-cdn.com/v4/letter/j/87869e/32.png) [@Jiachen\_Sun](https://community.deeplearning.ai/u/Jiachen_Sun)\ **Post date:** [July 7, 2022, 8:09pm UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/5 "2022-07-07T20:09:33Z")
I got a 0.625 test accuracy, but training accuracy also looks totally fine. ---
**Author:** ![xl0](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/xl0/32/21037_2.png) [@xl0](https://community.deeplearning.ai/u/xl0)\ **Post date:** [July 15, 2022, 12:40pm UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/6 "2022-07-15T12:40:18Z")
Same issue here, test accuracy between 65% and 75%: ```auto 2/2 [==============================] - 0s 3ms/step - loss: 1.4789 - accuracy: 0.6607 Test accuracy = 0.6607142686843872 ``` Train accuracy gets up to 100%. The model passes both the test and the autograder, so I can assume it’s correct. I did set the embedding layer as non-trainable. Any ideas on what could be wrong? ---
**Author:** ![xl0](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/xl0/32/21037_2.png) [@xl0](https://community.deeplearning.ai/u/xl0)\ **Post date:** [July 15, 2022, 2:23pm UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/7 "2022-07-15T14:23:29Z")
Found the issue - the test dataset CSV file has been mishandled in the past, and the strings contain \t (TAB character) at the end. The training set does not suffer from this issue. I used .split(’ ') to separate the words, which meant the last word of the sentence had a \t stuck to it and was not in the dictionary. The solution is to always use .split() without argument, which strips whitespace by default. With correctly split words, I’m getting 82% accuracy, which is within the expected range, but surprisingly, still below the much simpler average vector model. ---
**Author:** ![anon76241992](https://avatars.discourse-cdn.com/v4/letter/a/3d9bf3/32.png) [@anon76241992](https://community.deeplearning.ai/u/anon76241992)\ **Post date:** [October 14, 2023, 9:12am UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/8 "2023-10-14T09:12:55Z")
I come here for the same problem. I got 78% for test accuracy. Maybe this is because overfitting due to the use of embeddings?? ---
**Author:** ![anon76241992](https://avatars.discourse-cdn.com/v4/letter/a/3d9bf3/32.png) [@anon76241992](https://community.deeplearning.ai/u/anon76241992)\ **Post date:** [October 14, 2023, 9:20am UTC](https://community.deeplearning.ai/t/week2-emoji-v3a-low-test-accuracy-but-passed-the-grader/103405/9 "2023-10-14T09:20:48Z")
Okay, I just ran the notebook again and now I got 85% acc at test set. Maybe the model is facing a very high variance problem. ![image](https://global.discourse-cdn.com/dlai/original/3X/0/1/01ee4b412d4ec3852fef20f72a2f91d779503c01.png)