'ValueError: cannot reshape array of size 1502 into shape (48,48)

I have been stuck with this problem for a very long time and I could not find the solution.

ValueError: cannot reshape array of size 1502 into shape (48,48)
#converting dtype of pixels to string
df['pixels'] = df['pixels'].astype("string")

pixels = df['pixels'].tolist() #Making list of pixels

width, height = 48, 48 # initializing image shape

# Converting to array and dimension for transfer Learning
faces = []
faces = np.asarray(faces)
faces = np.expand_dims(faces, -1)
faces /= 127.5 # normalizing the data
faces -= 1.

# Converting Emotions to NumPy array
emotions = pd.get_dummies(df['emotion']).to_numpy()

1



Solution 1:[1]

face has 1502 elements. and what you are doing is, you want to change face shape to 48x48 since 48x48=2304. you need the same total value from before to after

Sources

This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.

Source: Stack Overflow

Solution Source
Solution 1 dimas krisrianto