Even following the instructions of the last cell it was not possible to obtain a 99.5% precision in the model,
Somebody made it ?
This is my code and my output
code erased
Posting code in a public topic is discouraged and can get your account suspended. It’s okay to share stacktrace on a public post and send code to a mentor via direct message. Please clean up the post.
Your topic is filed under TF1 week 2 but your subject says that the problem is associated with week 3. Do fix this. Here’s the community user guide to get started.
The problem with your code isn’t reaching the desired accuracy since the message Reached 99% accuracy so cancelling training! is getting printed. Please refer to the link in the notebook for writing custom callbacks to fix your code on why the model training doesn’t stop after meeting the stopping criteria.
1 Like
You are right. @balaji.ambresh , I updated the post and I have shared the code with you.
Softmax is an effective activation function for the output layer. For all hidden layers, relu is preferred as the activation function. Please make this change to the dense layer with 128 units and try again.
1 Like