-
Notifications
You must be signed in to change notification settings - Fork 19
Open
Description
I train the model with num_round=2000, but the train process was early stop in round 782.
trainGSmodel <- train_deepGSModel(trainMat = trainMat,trainPheno = trainPheno,
validMat = validMat,validPheno = validPheno, markerImage = markerImage,
cnnFrame = cnnFrame,device_type = "cpu",gpuNum = 1, eval_metric = "rmse",
num_round = 2000,array_batch_size= 30,learning_rate = 0.01,
momentum = 0.5,wd = 0.00001, randomseeds = 0,initializer_idx = 0.01,
verbose = TRUE)
when i predict test data using trained model "trainGSmodel", the value is same, and I check my test data, it is correct.

how does it happend?
thank you very much.
Metadata
Metadata
Assignees
Labels
No labels