如何使用模型（.h5）查看 model 预测答案和真实 output？

Question

I made my simple image classification model(classification.h5) by using CNN and I am hoping to see whether my model is working properly.

My CNN model is:

from tensorflow.keras import layers
from tensorflow.keras.models import Sequential
model = Sequential()

model.add(Conv2D(16, (3, 3), activation='relu', strides=(1, 1), 
    padding='same',input_shape=input_shape))
model.add(MaxPool2D((2, 2)))
model.add(Dropout(0.5))

model.add(Conv2D(32, (3, 3), activation='relu', strides=(1, 1), 
    padding='same'))
model.add(MaxPool2D((2, 2)))
model.add(Dropout(0.5))

model.add(Conv2D(412, (13, 13), strides=(1, 1), padding = 'same', activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Dropout(0.5))

model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(4, activation='softmax'))

model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['acc'])
    

The model worked well. For the next step, I tried to see if this model really works well but I am lost how actually I can see the real result.

What I want to try to see is shown below:

model prediction = 'Model predicted answer'

Real Answer = 'Real answer'

How can I write the code for this output?

Answer 1

1. Upload the saved model:

saved_model = keras.models.load_model("Model_Name.h5")

2. Prepare your data (preprocessing or reshaping)

3. Do your predictions:

saved_model.predict(data)

Note: You can save a model like: model.save("Model_Name.h5")

Answer 2

to see your model really worked or not you have to test out predictions on the data which was not used in training so you have to do something like

predicted_values = model.predict(data_not_used_in_training)

compare these predicted values with the real values of this data and apply metrics
check this out on how to make predictions link