# C2\_W4 Assignment: I've read most of the forum posts about low accuracy issues, but none of the solutions are working **URL:** \ **Category:** Convolutional Neural Networks in TensorFlow\ **Tags:** week-module-4\ **Created:** [August 15, 2023, 12:18am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850 "2023-08-15T00:18:05Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![Nick\_VN](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/nick_vn/32/14021_2.png) [@Nick\_VN](https://community.deeplearning.ai/u/Nick_VN)\ **Post date:** [August 15, 2023, 12:18am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/1 "2023-08-15T00:18:05Z")
I have read the various forum posts about the C2\_W4 assignment, but none of them have helped. I am achieving a ~4% accuracy and can’t fix this issue. 1. My expected outputs all look correct. 2. I am not one-hot encoding, so I am using: `loss = 'sparse_categorical_crossentropy'` with `softmax` 3. I have set my last layer to 24 nodes: `dense_35 (Dense) (None, 24)` 4. I have already tried `optimizer='adam'` and `optimizer='rmsprop'` without luck 5. I’ve already removed `horizontal_flip`, `shear_range`, and `rotation_range` from my `train_datagen` generator 6. I’ve already experimented with different batch sizes, trying both the initial value of `32` and going all the way up to `1830` **Current training output:** > Epoch 1/15 > 858/858 [==============================] - 15s 16ms/step - loss: nan - accuracy: 0.0410 - val\_loss: nan - val\_accuracy: 0.0462 > Epoch 2/15 > 858/858 [==============================] - 13s 16ms/step - loss: nan - accuracy: 0.0410 - val\_loss: nan - val\_accuracy: 0.0462 > Epoch 3/15 > 858/858 [==============================] - 14s 16ms/step - loss: nan - accuracy: 0.0410 - val\_loss: nan - val\_accuracy: 0.0462 > … > Epoch 14/15 > 858/858 [==============================] - 15s 18ms/step - loss: nan - accuracy: 0.0410 - val\_loss: nan - val\_accuracy: 0.0462 > Epoch 15/15 > 858/858 [==============================] - 19s 22ms/step - loss: nan - accuracy: 0.0410 - val\_loss: nan - val\_accuracy: 0.0462 ---
**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:** [August 15, 2023, 3:12am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/2 "2023-08-15T03:12:35Z")
I saw that you’ve posted several different versions of this question today. I’m not a mentor for that course, but I will observe that your accuracy is just about what you’d expect if you were making random predictions among 24 labels - or if you were always making the same prediction (i.e always predict 0 from a range of 0 to 23, regardless of the data). 1/24 is just about exactly 0.041. In my experience, this sort of issue is a huge clue. Also observe that in “loss: nan”, that means Not a Number. So the loss values are not valid. Loss should always be a positive real value. Putting these together, I’d guess that your training method is not working. ---
**Author:** ![Deepti\_Prasad](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/deepti_prasad/32/165831_2.png) [@Deepti\_Prasad](https://community.deeplearning.ai/u/Deepti_Prasad)\ **Post date:** [August 15, 2023, 3:15am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/3 "2023-08-15T03:15:01Z")
Have you tried this post, read all the comments, this should give you the solution > [@Training accuracy 86% validation 94%, required training accuracy 99% validation accuracy 95%](https://community.deeplearning.ai/t/training-accuracy-86-validation-94-required-training-accuracy-99-validation-accuracy-95/356763/3): > > hey I referred the same post to clear assignment in the week 3, but I have doubt for this section. other than 2 conv2d and 2 maxpooling2d, I have used 2 dense layer. I didn’t include dropout. So in my last dense layer I used 26 units that’s where in one of the post you replied not to use, so I tried using 3, that when I get value error. I also did optimiser Adam first which still gave the same result. then I used rms-prop, which reduced the accuracy. Regards DP ---
**Author:** ![Nick\_VN](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/nick_vn/32/14021_2.png) [@Nick\_VN](https://community.deeplearning.ai/u/Nick_VN)\ **Post date:** [August 15, 2023, 3:40am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/4 "2023-08-15T03:40:16Z")
Hi @TMosh thank you for your feedback. I suspected that my training method is not working, but I don’t know why it isn’t working or what I can do to fix it, which is why I am reaching out to ask for help. Do you have any ideas what might be going wrong? All of the “Expected output” fields are correct and I have followed the examples from the teachings this week, so I’m not sure where to go from here. ---
**Author:** ![Nick\_VN](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/nick_vn/32/14021_2.png) [@Nick\_VN](https://community.deeplearning.ai/u/Nick_VN)\ **Post date:** [August 15, 2023, 3:46am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/5 "2023-08-15T03:46:11Z")
Hi Deepti, The post that you referenced was someone trying to further optimize their model from 86%, and I have reviewed the responses for this post. My model is leveling out at 4% so I think there’s something much different that is wrong with the model. I have been reviewing these posts but nothing is standing out to me as a reason why the accuracy would be so low. Would you be willing to take a look at my notebook? ---
**Author:** ![Deepti\_Prasad](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/deepti_prasad/32/165831_2.png) [@Deepti\_Prasad](https://community.deeplearning.ai/u/Deepti_Prasad)\ **Post date:** [August 15, 2023, 4:10am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/6 "2023-08-15T04:10:02Z")
Hi Nick, can you share your notebook in personal DM, click on my name and then message. Regards DP ---
**Author:** ![Deepti\_Prasad](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/deepti_prasad/32/165831_2.png) [@Deepti\_Prasad](https://community.deeplearning.ai/u/Deepti_Prasad)\ **Post date:** [August 15, 2023, 4:17am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/7 "2023-08-15T04:17:08Z")
Honestly Nick, When I did this notebook assignment, what I remember I was following the course weeks’ video, and included every image augmentation parameter but one need to understand, the train model requires it do be as simple as possible. the emphasis on batch\_size, dense layer and optimiser also is important. You can share your notebook, will have a look. Regards DP ---
**Author:** ![Deepti\_Prasad](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/deepti_prasad/32/165831_2.png) [@Deepti\_Prasad](https://community.deeplearning.ai/u/Deepti_Prasad)\ **Post date:** [August 15, 2023, 5:01am UTC](https://community.deeplearning.ai/t/c2-w4-assignment-ive-read-most-of-the-forum-posts-about-low-accuracy-issues-but-none-of-the-solutions-are-working/417850/8 "2023-08-15T05:01:57Z")
HELLO NICK, ERRORS IN YOUR NOTEBOOK 1. you need to append your file in row and not in line. 2. Your reshape code for labels and images is incorrect. 3. As explained in the previous comment, your Image augmentation for train\_datagen need to be as simple as possible. I know we get confused here and include everything what course instructor mentions in the weeks video, but the lesser things you add, the better accuracy. 4. Your last layers dense need to be 26, as the number of categories is 26 alphabets. Your dense layer model compile needed changes. 5. You do not need dropout layer always. 6. Use Adam optimiser as it gives better performance with little hyperparameter tuning. Please check the notebook thoroughly, let me know once you have cleared the model training with achieved accuracy. Keep Learning!!! Regards DP