Hi @youshui_miao, Generally to overcome overfitting There are few techniques to overcome this problem
- Data augmentation: If the training set has less number of images you use data augmentation to improve the samples of the dataset.
- Using DropOut Layer: When you apply dropout to a layer, it randomly drops out a number of output units from the layer during the training process.
- Adding L1 / L2 regularization to the model.
- Early stopping: Once the validation loss stops decreasing but rather begins increasing, we stop the training and save the current model.
Please try these techniques to overcome over fitting. Thank You!