Question

我开始研究深度学习。编写一些代码时出现问题。请让我知道解决问题。我不知道要解决它。我安装了tensorflow-cpu。这是个问题吗？我需要图形卡吗？

-我的错误-

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int).

-代码`-

import numpy as np
import pandas as pd

samsung=pd.read_csv(r"C:\Users\XNOTE\Desktop\Deepstudy\pred 
test\samsung.csv", index_col=0, header=0, encoding='cp949', sep=',')

for i in range(len(samsung.index)):
    for j in range(len(samsung.iloc[i])):
        samsung.iloc[i,j] = int(samsung.iloc[i,j].replace(',',''))

samsung=samsung.sort_values(['일자'], ascending=[True])

samsung=samsung.values


# code split 
def split_xy5(dataset, time_steps, y_column):
    x,y=list(), list()
    for i in range(len(dataset)):
        x_end_number=i+time_steps
        y_end_number=x_end_number + y_column

        if y_end_number > len(dataset):
            break
        tmp_x = dataset[i:x_end_number, :]
        tmp_y = dataset[x_end_number : y_end_number, 3]
        x.append(tmp_x)
        y.append(tmp_y)
    return np.array(x), np.array(y)
    
x,y = split_xy5(samsung, 5, 1)


from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, test_size = 0.3)

x_train = np.reshape(x_train,(x_train.shape[0], x_train.shape[1] * x_train.shape[2]))
x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1]*x_test.shape[2]))
print(x_train.shape)
print(x_test.shape)

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
scaler.fit(x_train)
x_train_scaled = scaler.transform(x_train)
x_test_scaled = scaler.transform(x_test)
print(x_train_scaled[0,:])

from keras.models import Sequential
from keras.layers import Dense

model = Sequential()
model.add(Dense(64, input_shape = (25, )))
model.add(Dense(32, activation = 'relu'))
model.add(Dense(32, activation = 'relu'))
model.add(Dense(32, activation = 'relu'))
model.add(Dense(32, activation = 'relu'))
model.add(Dense(1))

model.compile(loss='mse', optimizer='adam', metrics=['mse'])

from keras.callbacks import EarlyStopping
early_stopping = EarlyStopping(patience=20)
model.fit(x_train_scaled, y_train, validation_split=0.2, 
verbose=1, batch_size=1, epochs=100, callbacks=[early_stopping])

loss, mse = model.evaluate(x_test_scaled, y_test, batch_size=1)
print('loss : ', loss)
print('mse : ', mse)

y_pred = model.predict(x_test_scaled)

for i in range(5):
    print('종가 : "', y_test[i], '/ 예측가 : ', y_pred[i])

加载文件并使数组使用numpy。制作模型，但不起作用引用

Answer 1

假设x_train_scaled的类型为int，而您在model.fit上遇到错误，则可以尝试以下操作：

tf.cast(x_train_scaled, tf.int32)

您可以对y_train和其他测试数组执行相同的操作，并将其转换为所需的tensorflow dtype。

tensorflow-cpu-ValueError：无法将NumPy数组转换为张量（不支持的对象类型int）

1 个答案: