Not getting accuracy more than 12 % on training data

#1

https://colab.research.google.com/drive/1US8ALiYXDmz70SSnY13yfw07YTYZERXW
this is the link to my file

#2

Actually the given dataset is buggy, and in training data only images til 328 are correct after that there are images with random noise only, you can see this by visualizing it using plt.imshow() function.

So just use images till 328 for training, similarly the testing data is also buggy, and contains first 60-70 correct images only.

Backend team is working on it, soon we will upload the cleaned flawless dataset.

Happy Learning :blush:

#3

Also normalize the training data by dividing by 255.0

#4

ok Sir I will try with that too

#5

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.