# C2W4 Assignment accuracy **URL:** \ **Category:** Convolutional Neural Networks in TensorFlow\ **Tags:** week-module-4\ **Created:** [March 25, 2022, 9:00am UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000 "2022-03-25T09:00:12Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Taras\_Buha](https://avatars.discourse-cdn.com/v4/letter/t/f19dbf/32.png) [@Taras\_Buha](https://community.deeplearning.ai/u/Taras_Buha)\ **Post date:** [March 25, 2022, 9:00am UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000/1 "2022-03-25T09:00:12Z")
Hi, I was trying different things to achieve accuracy more than 99%. One more conv layer, different optimizers with different learning rate accuracy was between 70-80%. Just ImageDataGenerator with rescale, rotation and fill mode helped to achieve accuracy more than 99%. Do we have any others approaches? Best regards, Taras ---
**Author:** ![kalavaladeekshithala](https://avatars.discourse-cdn.com/v4/letter/k/848f3c/32.png) [@kalavaladeekshithala](https://community.deeplearning.ai/u/kalavaladeekshithala)\ **Post date:** [April 7, 2022, 3:01am UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000/2 "2022-04-07T03:01:38Z")
can you pleasee send your code? ---
**Author:** ![shiro](https://avatars.discourse-cdn.com/v4/letter/s/7bcc69/32.png) [@shiro](https://community.deeplearning.ai/u/shiro)\ **Post date:** [September 9, 2022, 7:47am UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000/3 "2022-09-09T07:47:01Z")
Hi, Taras. “A reasonable benchmark is to achieve over 99% accuracy for training and over 95% accuracy for validation within 15 epochs.” This seems too high for me because the task is 26 class classification. I checked more sample images than 100. I think shear and rotation are useless or limited gain since all images I checked are upright. And horizontal flips will be harmful because they are all right hand. I reflect those findings on the settings of ImageDataGenerator but my result was far beyond “A reasonable benchmark” Any tips on how to achieve 99% accuracy in 15 epochs? Did you use transfer learning? ---
**Author:** ![shiro](https://avatars.discourse-cdn.com/v4/letter/s/7bcc69/32.png) [@shiro](https://community.deeplearning.ai/u/shiro)\ **Post date:** [September 9, 2022, 8:10am UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000/4 "2022-09-09T08:10:24Z")
I was running the calculations as I wrote my earlier post, and soon after that, I went to 99% in 15 epochs. It seemed better to be conservative with augmentation. Thanks. ---
**Author:** ![Gregory\_Chagas](https://avatars.discourse-cdn.com/v4/letter/g/c6cbf5/32.png) [@Gregory\_Chagas](https://community.deeplearning.ai/u/Gregory_Chagas)\ **Post date:** [September 23, 2022, 10:11pm UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000/5 "2022-09-23T22:11:25Z")
“It seemed better to be conservative with augmentation.” Of Course!!! This kind of data must not have too many variations. ---
**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:** [June 17, 2023, 4:36am UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000/6 "2023-06-17T04:36:10Z")
hello shiro, your post helped me understand and cleared week 4 assignment. thank you. I understood one think the more number of classes, the lesser complicated should be one’s model. ---
**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, 12:06am UTC](https://community.deeplearning.ai/t/c2w4-assignment-accuracy/112000/7 "2023-08-15T00:06:21Z")
I can’t even get higher than 4% accuracy and I’ve been following the advice listed here. I don’t know what to do at this point.