i have trained a model using fer2013 dataset using CNN for Emotion detection. Now i want to use it in a image

I have a trained model and saved the weights in fer.h5. Now i want to use the pre trained model in another set of images and save it to a excel file

import sys, os
import pandas as pd
import numpy as np

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D, 
BatchNormalization,AveragePooling2D
from keras.losses import categorical_crossentropy
from keras.optimizers import Adam 
from keras.regularizers import l2
from keras.utils import np_utils
# pd.set_option('display.max_rows', 500)
# pd.set_option('display.max_columns', 500)
# pd.set_option('display.width', 1000)

df=pd.read_csv('fer2013/fer2013.csv')

# print(df.info())
# print(df["Usage"].value_counts())

# print(df.head())
X_train,train_y,X_test,test_y=[],[],[],[]

for index, row in df.iterrows():
    val=row['pixels'].split(" ")
    try:
    if 'Training' in row['Usage']:
        X_train.append(np.array(val,'float32'))
        train_y.append(row['emotion'])
    elif 'PublicTest' in row['Usage']:
           X_test.append(np.array(val,'float32'))
           test_y.append(row['emotion'])
except:
    print(f"error occured at index :{index} and row:{row}")


num_features = 64
num_labels = 7
batch_size = 64
epochs = 40
width, height = 48, 48


X_train = np.array(X_train,'float32')
train_y = np.array(train_y,'float32')
X_test = np.array(X_test,'float32')
test_y = np.array(test_y,'float32')

train_y=np_utils.to_categorical(train_y, num_classes=num_labels)
test_y=np_utils.to_categorical(test_y, num_classes=num_labels)

#cannot produce
#normalizing data between oand 1
X_train -= np.mean(X_train, axis=0)
X_train /= np.std(X_train, axis=0)

X_test -= np.mean(X_test, axis=0)
X_test /= np.std(X_test, axis=0)

X_train = X_train.reshape(X_train.shape[0], 48, 48, 1)

X_test = X_test.reshape(X_test.shape[0], 48, 48, 1)

# print(f"shape:{X_train.shape}")
##designing the cnn
#1st convolution layer
model = Sequential()

model.add(Conv2D(64, kernel_size=(3, 3), activation='relu', input_shape= 
(X_train.shape[1:])))
model.add(Conv2D(64,kernel_size= (3, 3), activation='relu'))
# model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2,2), strides=(2, 2)))
model.add(Dropout(0.5))

#2nd convolution layer
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
# model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2,2), strides=(2, 2)))
model.add(Dropout(0.5))

#3rd convolution layer
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(Conv2D(128, (3, 3), activation='relu'))
# model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2,2), strides=(2, 2)))

model.add(Flatten())

#fully connected neural networks
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.2))

model.add(Dense(num_labels, activation='softmax'))

# model.summary()

#Compliling the model
model.compile(loss=categorical_crossentropy,
              optimizer=Adam(),
              metrics=['accuracy'])

    #Training the model
    model.fit(X_train, train_y,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(X_test, test_y),
          shuffle=True)


#Saving the  model to  use it later on
fer_json = model.to_json()
with open("fer.json", "w") as json_file:
    json_file.write(fer_json)
model.save_weights("fer.h5")