如何解决，ValueError: setting an array element with a sequence？

Question

这是我的代码，即使我进行了one-hot encoding也会出错，但这对我不起作用。然后我自己将序列转换为数字但是在编译错误时发生“ValueError：设置带有序列的数组元素”

请指导我如何将数据拟合到神经网络中，我在 csv 文件的一列中有蛋白质序列列表，在第二列中它们的结构名为a, ab, b

df= pd.read_csv('/home/alpha/mk fyp/whole/DATASET2.csv',names=('X1','Y'),delimiter=',')
X1=df.iloc[:,0].values
Y=df.iloc[:,1:2].values
def convert(sequence):
for item in sequence:
    try:
        yield float(item)
    except ValueError as e:
        yield item

a = [[item for item in convert(sublist)] for sublist in X1]
X = np.array(a)
X_train, X_test, y_train, y_test = train_test_split(X,Y, test_size=0.20)
# define a simple CNN model
def baseline_model():
# create model
model = Sequential()
model.add(Dense(input_dim = 1, units = 10, activation='relu', kernel_initializer='uniform'))

model.add(Dense(1, activation='relu'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
return model 
# build the model
model = baseline_model()
# Fit the model
model.fit(X, Y, validation_data=(X1, Y), epochs=10, batch_size=200)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("CNN Error: %.2f%%" % (100-scores[1]*100))