I am creating this post for my learning and putting my training a deep neural network into practice. the task I use is the cat classification from Course 1. I’ve just made a n-layer neural network to test it out. here is the result: Accuracy of Train logistic regression: 100 % (percentage of cor…

Note that data augmentation is not a way of doing regularization. It’s not correct to list it as a similar technique like dropout and L2. Augmentation is a way of increasing the size and variance of the data set.

some update: I did add a few more layers a. [12288, 512, 256, 128, 64, 1] Accuracy of Train logistic regression: 100 % (percentage of correctly labelled datapoints) Accuracy of Test logistic regression: 68 % (percentage of correctly labelled datapoints) train_X's shape: (418, 12288) train_Y's sha…

Notice that on the last few training runs you show, you have train accuracy 100% the whole time. So as Tom suggested earlier, this really looks like a serious overfitting problem. Maybe “early stopping” would be helpful. One way to get a better picture of what is happening would be to print the test…

[image] ph.ai: I did add a few more layers As I said before, I expect this will only make the problem worse.

I’ve added the testing loss and testing accuracy on every 100 epochs and here it is: Accuracy of Train logistic regression: 100 % (percentage of correctly labelled datapoints) Accuracy of Test logistic regression: 68 % (percentage of correctly labelled datapoints) train_X's shape: (418, 12288) trai…

[image] ph.ai: Epoch 600 - Train Loss: 0.0000969937, Accuracy: 100.0000%, Test Loss: 1.1407402754, Test Accuracy: 82.0000% The evidence suggests that “early stopping” after Epoch 600 would be your best solution at least with your other current hyperparameter choices. All the …

I think maybe you don’t understand what regularization (which Dropout is a form of) does. It increases the cost on the training set, to the benefit of getting lower cost on the test set. Every result you’ve shown shows that you’re still getting 100% accuracy on the training set. So you’re still o…

It’s great that you are trying all these experiments. We always learn something when we try to take the course material and apply or extend it. My interpretation of your results is that dropout = 0.05 gave the best performance. You got to 80% test accuracy on Epoch 400 there. Also notice that what …

As you proceed with DLS Course 2 and Course 3, you’ll hear a lot more about strategies for dealing with cases in which the performance does not achieve your requirements. And in the case of overfitting, the number one choice to pursue for that is “get more training data”. :laughing: Of course in “re…

Course 3 Week1: put it into practice, cat classification

Course Q&A Deep Learning Specialization Structuring Machine Learning Projects

paulinpaloalto January 23, 2024, 12:32am 9

The evidence suggests that “early stopping” after Epoch 600 would be your best solution at least with your other current hyperparameter choices. All the training after that is just a waste of time: it does not improve the training accuracy and the test accuracy only gets worse after that point.

Topic		Replies	Views
Help Me With NN Model Accuracy AI Discussions ai-discussions , project	33	420	January 3, 2025
Stuck at 0.5000 validation accuarcy in course 2 week 2 cats vs dogs data augmentation Improving Deep Neural Networks: Hyperparameter tun coursera-platform	3	561	February 16, 2022
Relation between Accuracy and Cost in Week 4 Assigment Neural Networks and Deep Learning coursera-platform	7	762	August 31, 2022
No cat at all, but predicting a cat Neural Networks and Deep Learning coursera-platform	4	737	January 13, 2023
No overfitting issue without dropout layers on "Predicting Sunspots with Neural Networks" Sequences, Time Series and Prediction week-module-4	19	519	September 28, 2023

Course 3 Week1: put it into practice, cat classification

Related topics