every time i do a prediction,the predicted emotion is neutral. i tried with lstm and cnn

[mark233456]

could you help me for a bit ? this is what i did to run the prediction.

import pandas as pd
import numpy as np
import tensorflow as tf
import tensorflow.keras as keras

text preprocessing

from nltk.tokenize import word_tokenize
import re

plots and metrics

import matplotlib.pyplot as plt
from sklearn.metrics import accuracy_score, f1_score, confusion_matrix

preparing input to our model

from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.utils import to_categorical

keras layers

from keras.models import Sequential
from tensorflow.keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense
from keras.models import load_model

import time

max_seq_len = 500

tokenizer = Tokenizer()

message = ['i am so sad!']

class_names = ['joy', 'fear', 'anger', 'sadness', 'neutral']

model= load_model('models/cnn_w2v.h5')

seq = tokenizer.texts_to_sequences(message)
padded = pad_sequences(seq, maxlen=max_seq_len)

start_time = time.time()
pred = model.predict(padded)

print('Message: ' + str(message))
print('predicted: {} ({:.2f} seconds)'.format(class_names[np.argmax(pred)], (time.time() - start_time)))

[kishan2k2]

Yes getting the same error