Mastering Computer Vision with TensorFlow 2.x

Inputting a test image and converting it into a tensor

So far, we've developed an image directory and prepared and trained the model. In this section, we'll convert the image into a tensor. We develop a tensor from an image by converting the image into an array and then use NumPy's expand_dims() function to expand the shape of the array. Subsequently, we preprocess the input to prepare the image so that it's in the format the model requires:

img_path = 'furniture_images/test/chair/testchair.jpg'img = image.load_img(img_path, target_size=(150, 150))img_tensor = image.img_to_array(img)img_tensor = np.expand_dims(img_tensor, axis=0)img_tensor = preprocess_input(img_tensor)featuremap = model.predict(img_tensor)

Finally, we use the Keras model.predict() ...