嗨,在我更改数据集之前,我的代码一直运行良好。现在,我收到一个错误:
model.fit(train,train_df.iloc[:,-1],epochs=30, batch_size=20, verbose=1)
错误是:
ValueError:检查输入时出错:预期的dense_31_input具有形状(1125,)但得到的数组具有形状(103,)
变量是:
scaler = StandardScaler()
train=scaler.fit_transform(train_df.iloc[:,:-1])
test=scaler.fit_transform(test_df.iloc[:,:-1])
# Creating Deep Model
model = Sequential()
# Add an input layer
model.add(Dense(562, activation='relu', input_shape=(1125,)))
# Add one hidden layer
model.add(Dense(562, activation='relu'))
model.add(BatchNormalization())
# Add an output layer
model.add(Dense(1, activation='sigmoid'))
#add improvements
model.add(Dropout(0.3))
#Train the model
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
model.fit(train,train_df.iloc[:,-1],epochs=30, batch_size=20, verbose=1)
#TEst the model
y_pred = model.predict(test_df.iloc[:,:-1])
我假设修复它。我需要更改 batch_size 和 epochs 吗?但是应该使用什么数字?