关于4_2_AutoEncoer.py的疑问
请问为什么函数standard_scale是这样:def standard_scale(X_train, X_test):....preprocessor = prep.StandardScaler().fit(X_train)....X_train = preprocessor.transform(X_train)....X_test = preprocessor.transform(X_test)....return X_train, X_test而不是这样:def standard_scale(X_train, X_test):....preprocessor = prep.StandardScaler()....X_train = preprocessor.fit_transform(X_train)....X_test = preprocessor.fit_transform(X_test)....return X_train, X_test
def standard_scale(X_train, X_test):
....preprocessor = prep.StandardScaler().fit(X_train)
....X_train = preprocessor.transform(X_train)
....X_test = preprocessor.transform(X_test)
....return X_train, X_test
....preprocessor = prep.StandardScaler()
....X_train = preprocessor.fit_transform(X_train)
....X_test = preprocessor.fit_transform(X_test)
明白了,还是看书没有仔细
老师好,我就一个问题,5.2的模型怎么保存?谢谢
您好,请问书上4.2节计算一个batch的平均损失时用到了:**g_cost += cost / n_samples * batch_sizecost已经是从对应的那个batch中计算出来的了,为什么还要乘以batch_size,或者说这里的平均损失**g_cost指的是平均到一个样本上的损失还是别的意义的平均损失呢
第八章策略网络207页,tvars没有定义??/
买了书,下载代码看看
关于4_2_AutoEncoer.py的疑问
请问为什么函数standard_scale是这样:
def standard_scale(X_train, X_test):
....preprocessor = prep.StandardScaler().fit(X_train)
....X_train = preprocessor.transform(X_train)
....X_test = preprocessor.transform(X_test)
....return X_train, X_test
而不是这样:
def standard_scale(X_train, X_test):
....preprocessor = prep.StandardScaler()
....X_train = preprocessor.fit_transform(X_train)
....X_test = preprocessor.fit_transform(X_test)
....return X_train, X_test
老师好,我就一个问题,5.2的模型怎么保存?谢谢
您好,请问书上4.2节计算一个batch的平均损失时用到了:**g_cost += cost / n_samples * batch_size
cost已经是从对应的那个batch中计算出来的了,为什么还要乘以batch_size,或者说这里的平均损失**g_cost指的是平均到一个样本上的损失还是别的意义的平均损失呢
第八章策略网络207页,tvars没有定义??/
买了书,下载代码看看