I am implementing the model in Matlab R2018a. I have twenty categories. My training accuracy goes to 98% but validation accuracy is 60-66%. If I reduce overfiitting , then both comes to near about 66%.
Try for better accuracy:
Article Parametric Decomposition of Sample Space for Classification
Well that would depend on the data set also. Check if there are any missing values in the data set and also whether the data set is properly balanced.
Try using other Classifiers on the data set.
Use transfer learning mehtod..pretrained models in your CNN network RESNET/ DENSENET /NasNET technique to increase the accuracy.
Well, it is clear that it is not a matter of what algorithm you are using. Let me tell you a trick to improve accuracy when you are having good results during training but not testing.
1) It is due to less amount of data.
2) Data is not versatile
to overcome this you can use python to create more data using keras library (that makes your training data less prone to overfit)
by using these parameters. in the function
apply_transform(x, transform_parameters)
- 'theta': Float. Rotation angle in degrees.
- 'tx': Float. Shift in the x direction.
- 'ty': Float. Shift in the y direction.
- 'shear': Float. Shear angle in degrees.
- 'zx': Float. Zoom in the x direction.
- 'zy': Float. Zoom in the y direction.
- 'flip_horizontal': Boolean. Horizontal flip.
- 'flip_vertical': Boolean. Vertical flip.
- 'channel_shift_intencity': Float. Channel shift intensity.
- 'brightness': Float. Brightness shift intensity.
Note: you can do these transformation in MATLAB itself in no time.
If even after that you are unable to improve your accuracy, I recommend you to post your model architecture (i.e. no. Of cnn layers, max pool layers, dropouts etc.) And also the no. of data points you are using for training.
Make sure you train your model for enough epocs.
Were you able to increase the accuracy rate?
You can check the layers and kernels in your cnn model. You can also change the optimization algorithm used.
Yes, now the Validation Accuracy is increased to 88.40% and training accuracy goes nearly to hundred.If I increase the epochs, validation accuracy also increases, but final validation accuracy suddenly drops to above 88.40%..I am stuck here.
Your model might be overfitting if your model fits too well to the training set.
Deepali Bongulwar, for the fitting of your modal one your images, make sure you choose LR (learning rate) wisely. For example, you can make a Losses vs LR curve and find the values where cure is steepest/max slope as in fig. attached below it is slice(1e-4, 1e-2).
or you can follow Subash Gautam advice and use TF with half of the efforts you are putting right now.
you can implement early stopping to overcome overfitting, and also you can shuffle your data to increase versatility of your dataset.
- Badges
- Science topic
- Similar topics
- Organizational Psychology
- Training