TypeError：图像数据无法转换为float

Question

我在python中使用pandas导入了一个csv文件。它在单个列中包含字符串中的所有像素值，因此我使用dataframe将其拆分。但现在当我试图从数据集中绘制图像时，我收到此错误

raise TypeError("Image data cannot be converted to float")

TypeError: Image data cannot be converted to 

代码：

import numpy as np # linear algebra
import pandas as pd 

df_train = pd.read_csv('/root/Downloads/Deep-Learning/Projects/train.csv')
df_test = pd.read_csv('/root/Downloads/Deep-Learning/Projects/test.csv')

from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras.optimizers import RMSprop
from keras.callbacks import ReduceLROnPlateau
from keras.preprocessing.image import ImageDataGenerator
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

df_train.head()

#every columns but the first
df_train_x = df_train.iloc[:,1:]
#only the first column
df_train_y = df_train.iloc[:,:1]

df_train_x = pd.DataFrame(df_train_x.Pixels.str.split(' ',2303).tolist())

ax = plt.subplots(1,5)
for i in range(0,5):   #validate the first 5 records
    ax[1][i].imshow(df_train_x.values[i].reshape(48,48), cmap='gray')
    ax[1][i].set_title(df_train_y.values[i])

我该怎么办？