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

Question

I have written the following code for a neural network to perform regression on a dataset, but I am getting a ValueError. I have looked up to different answers and they suggested to use df = df.values to get a numpy array. I tried it but it still produced the same error. How to fix this?

CODE

from keras import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.optimizers import Adam
from sklearn.model_selection import train_test_split

#Define Features and Label
features = ['posted_by', 'under_construction', 'rera', 'bhk_no.', 'bhk_or_rk',
            'square_ft', 'ready_to_move', 'resale', 'longitude',
            'latitude'] 

X=train[features].values
y=train['target(price_in_lacs)'].values

#Train Test Split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state = 23, shuffle = True)

#Model
model = Sequential()
model.add(Dense(10, activation='relu', kernel_initializer='random_normal', input_dim = 10))
model.add(Dense(1, activation = 'relu', kernel_initializer='random_normal'))

#Compiling the neural network
model.compile(optimizer = Adam(learning_rate=0.1) ,loss='mean_squared_logarithmic_error', metrics =['mse'])

#Fitting the data to the training dataset  
model.fit(X_train,y_train, batch_size=256, epochs=100, verbose=0)

ERROR

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

Answer 1

As X_train and y_train are pandas.core.series.Series they can't be parsed.

Try converting them to list as below:

X=train[features].to_list()

y=train['target(price_in_lacs)'].to_list()

Answer 2

Before fitting the model the training data write the below 2 lines:

X_train=np.asarray(X_train).astype(np.int)

y_train=np.asarray(y_train).astype(np.int)

Answer 3

To convert numpy array to tensor,

import tensor as tf
#Considering y variable holds numpy array
y_tensor = tf.convert_to_tensor(y, dtype=tf.int64) 

#You can use any of the available datatypes that suits best - https://www.tensorflow.org/api_docs/python/tf/dtypes/DType

Answer 4

It maybe due to the fact that some of your columns may not have complete integer values, before fitting you should convert it

X = np.asarray(X).astype(np.int_)
Y = np.array(Y).astype(np.int_)