CODEWITHSUNDEEP
pythontensorflowconv-neural-networkprediction
TheHistory
TheHistory

Reputation: 25

3 Classes prediction CNN Deep Learning

I trained my model in three classes and now I want to input one image at a time to see whether it belongs to classes 1,2, or 3.

data = []
img_size = 224

for i in categories:
    path = os.path.join(TRAIN_DIR1, i)   
    class_num = categories.index(i)
    for file in os.listdir(path):
        filepath = os.path.join(path, file)
        img = cv2.imread(filepath, 0)
        img = cv2.resize(img, (img_size, img_size))
        data.append([img, class_num])
random.shuffle(data)
X, y = [], []
for feature, label in data:
    X.append(feature)
    y.append(label)
X = np.array(X).reshape(-1, img_size, img_size, 1)
X = X / 255.0
y = np.array(y)


X_train, X_valid, y_train, y_valid = train_test_split(X, y, random_state=20, stratify=y)


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


model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

I need help writing my prediction code to input one testing image at a time, please.

Upvotes: 0

Views: 284

Answers (1)

Baraa Zaid
Baraa Zaid

Reputation: 424

import cv2

img_directory = input(str("Input directory: ")) # 'C:/dataset/img.png'

img= cv2.imread(img_directory)

img=cv2.resize(img, (180,180))

img = tf.expand_dims(img, 0)

prediction = model.predict(img)

score = tf.nn.softmax(prediction[0])

print(
    "This image most likely belongs to {} with a {:.2f} percent confidence."
    .format(class_names[np.argmax(score)], 100 * np.max(score))
)

You can use a while loop to continuously enter the img directory with break when you input quit.

Upvotes: 2

Related Questions