Hello, I am trying to train deep learning model using Tensorflow.
The objective is :
1. Train the model with given data
2. Estimate future data --> Check if it works
The data I am using now is difficult to train.
It's graph is Rising Sine Curve, and I don't know much about how to set up my model.
Basically there is data scaling, learning model(Dense, LSTM, etc.), activation functions(ReLU, tanh, etc.), and more.
I would appreciate any help for this problem.
Thank you very much :)
The below link might be useful
https://stackoverflow.com/questions/63479179/estimate-variables-of-a-sine-wave-using-tensorflow
Hello Kim,
you can find the below link for your reference
https://towardsdatascience.com/build-your-first-machine-learning-model-using-tensorflow-d61b9b2b7d5e
https://towardsdatascience.com/how-to-build-a-machine-learning-model-439ab8fb3fb1
1)Use the pretrained networks like Lenet, ImageNet); and then fine-tuning, where the pretrained network is further trained on the specific target task of interest, which may have fewer labeled examples than the pretraining dataset.(training Data set=70% of total data set, testing-10% of total and Validation-20% of total)
2)standard architectures for medical imaging (ResNet50, Inception-v3) as well as a family of simple, lightweight CCN with 4 -5 layers , batchnorm-ReLU progression.
https://www.codecademy.com/articles/setup-deep-learning-environment
- Badges
- Science topic