python xgboost 继续对现有模型进行训练 [英] python xgboost continue training on existing model

问题描述

假设我构建了一个 xgboost 模型:

Lets say I build an xgboost model:

bst = xgb.train(param0, dtrain1, num_round, evals=[(dtrain, "training")])

地点:

• param0 是 xgb 的一组参数，
• dtrain1 是一个可以训练的 DMatrix
• num_round 是回合数

然后，我将模型保存到磁盘:

Then, I save the model to disk:

bst.save_model("xgbmodel")

稍后，我想重新加载我保存的模型并继续用 dtrain2 训练它

Later on, I want to reload the model I saved and continue training it with dtrain2

有人知道怎么做吗?

推荐答案

您甚至不必从磁盘加载模型并重新训练.

You don't even have to load the model from the disk and retrain.

您需要做的只是带有附加参数的相同 xgb.train 命令:xgb_model=(您在问题中保存的 xgboost 模型完整路径名或 Booster 对象).

All you need to do is the same xgb.train command with additional parameter: xgb_model= (either xgboost model full path name you've saved like in the question or a Booster object).

示例:

bst = xgb.train(param0, dtrain2, num_round, evals=[(dtrain, "training")], xgb_model='xgbmodel')

祝你好运！

这篇关于python xgboost 继续对现有模型进行训练的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！