This repository provide modified SCINet model to predict stock price and implement based on PyTorch Framework.
python main.py
The term seq_len
refers to the number of inputs used for forecasting the output.
pred_len
denotes the size or number of steps used to forecast the output at each step.
in_dim
represents the number of dimensions in the input, which corresponds to the number of features used as inputs.
The kernel
is the 1D convolution kernel, and it should have an odd value (e.g., 3, 5, 7, etc.).