简体繁体中英

Keras CNN training accuracy is good but test accuracy is very low

原文 2017-03-01 10:01:34 8 1 python/ deep-learning/ keras

Please give me any comment for these CNN results. I have used 2000 training images and 400 test images. Training accuracy is perfect but test accuracy is very low. I think it because there is much variation between training and test images. Anyone have a good idea for this case?

[ 精度图 ]

1 answers

This is clear case of over-fitting. How many learneable parameters you have? For example VGGnet has 138M parameters and in this case its not very hard to see some neuron in the network must have sort of memorized a training image as it is and thus your network is not generalizing well.

~~To fix that, first of all you can try a simpler model if task is simple like discriminating between shapes~~ . Also you can increase training data via transformations like swapping color channels (if it doesnt impact the output class), flipping or rotating image to make your net generalize better. Include L1/L2 regularization in your loss function and try dropouts.

High training accuracy, low validation accuracy CNN binary classification keras

Very low accuracy cnn

Very low accuracy on CNN

Deploying a CNN: High training and test accuracy but low prediction accuracy

Low accuracy after training a CNN

Accuracy too low with very simple CNN model using Keras in Tensorflow

Very low validation accuracy but high training accuracy

LSTM CNN training and test accuracy are same with low prediction probability

High accuracy training but low accuracy test/prediction

High accuracy on both training and validation but very low on test set

暂无

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

Related Question High training accuracy, low validation accuracy CNN binary classification keras Very low accuracy cnn Very low accuracy on CNN Deploying a CNN: High training and test accuracy but low prediction accuracy Low accuracy after training a CNN Accuracy too low with very simple CNN model using Keras in Tensorflow Very low validation accuracy but high training accuracy LSTM CNN training and test accuracy are same with low prediction probability High accuracy training but low accuracy test/prediction High accuracy on both training and validation but very low on test set

Related Tags

Keras CNN training accuracy is good but test accuracy is very low

Question

1 answers

solution1 5 2017-03-01 10:10:49

solution1
5 2017-03-01 10:10:49