Train error model
train_dreams_model(
training_data,
layers,
model_features,
lr,
batch_size,
epochs,
model_file_path = NULL,
log_file_path = NULL,
min_delta = 0,
patience = 0,
l2_reg = 0,
validation_split = 0,
ctx3_embed_dim = 3
)
data.frame
Input training data (Generated from get_training_data()
)
Numeric vector. Number of nodes in each layer.
Vector of feature names. Selected features for model training.
Numeric value between 0 and 1. Learning rate.
Integer. Batch size.
Integer. Number of training epochs.
String. Model output file path. Default is NULL
.
String. Path to model output log file. Default is NULL
.
Numeric value between 0 and 1. Minimum delta for early stopping. Default is 0.
Integer. Patience when reaching minimum delta. Default is 0.
Numeric value between 0 and 1. Level of L2 regularization per layer. Default is 0.
Numeric value between 0 and 1. Validation split ratio. Default is 0.
Integer. Number of dimensions to embed trinucleotide context to. Default is 3.
Trained model in hdf5 format.
get_training_data()
Function for getting training data
Other Train model:
train_dreams_model_indels()