sgd_experimental(lr=0.005, lr_decay=1e-6, momentum=0.9, nesterov=True)相当于SGDClassifier()里的什么参数
时间: 2023-05-29 12:04:05 浏览: 130
pytorch_mnist-python源码.zip
5星 · 资源好评率100%
sgd_experimental(lr=0.005, lr_decay=1e-6, momentum=0.9, nesterov=True)相当于SGDClassifier()里的以下参数:
- learning_rate='constant'
- eta0=0.005
- learning_rate_init=0.005
- power_t=0.5
- alpha=0.0001
- l1_ratio=0.15
- fit_intercept=True
- max_iter=None
- tol=0.001
- shuffle=True
- verbose=0
- epsilon=0.1
- n_jobs=None
- random_state=None
- early_stopping=False
- validation_fraction=0.1
- n_iter_no_change=5
- class_weight=None
- warm_start=False
- average=False
- momentum=0.9
- nesterovs_momentum=True
- lr_decay=1e-6
阅读全文