Data Science Asked on April 9, 2021
I am working on a project where I have to classify the good and bad packets. I am modelling my data with 1 dimensional CNN u where i have to predict good packet(0) and malicious packets(1,2,3), i have upsample the data with class_weight parameter while training the model. I have reshaped my data(6,1) and i have used a Conv1d layers where the first one has 124,second one has 64 and the third one has 48 layers. In each middle layer I have used a kernel_size = 5, padding =same, and activation function relu. Afterthat I have used a Flatten, with BatchNormalization and I have added a two Dense layers with 128 and 64 respectively with activation function RELU. The output layer has the number of classes(4) and activation function softmax. However the model has a high Bias and the training loss is much higher than the validation loss. I really need help…
Thanks in advance!
My original data has 168000, however i am first trying to get the model working on small data
Get help from others!
Recent Questions
Recent Answers
© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP