def predict(model, img):
x = img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
prediction_index = np.argmax(preds[0])
return CATEGORIES[prediction_index]
def read_and_prep_images(img_paths,
img_height=image_size,
img_width=image_size):
imgs = [
load_img(img_path, target_size=(img_height, img_width))
for img_path in img_paths
]
img_array = np.array([img_to_array(img) for img in imgs])
output = preprocess_input(img_array)
return (output)
def preprocess_image(path):
'''Process an image to numpy array.
Args:
path: the path of the image.
Returns:
Numpy array of the image.
'''
img = process_image.load_img(path, target_size=(224, 224))
x = process_image.img_to_array(img)
# x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
return x
def predict(image1):
model = MobileNet()
image = load_img(image1, target_size=(224, 224))
# convert the image pixels to a numpy array
image = img_to_array(image)
# reshape data for the model
image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))
# prepare the image for the VGG model
image = preprocess_input(image)
# predict the probability across all output classes
yhat = model.predict(image)
# convert the probabilities to class labels
label = decode_predictions(yhat)
# retrieve the most likely result, e.g. highest probability
label = label[0][0]
return label
def predict_image(model, path: str, temperature_scaling: float = 1.0) -> str:
source_img = imread(path)
img = preprocess_input(make_image_square(source_img))
logit_model = get_logits_friendly_model(model)
logits = logit_model.predict(img.reshape((1, HEIGHT, WIDTH, 3)))
calibrated_logits = logits / temperature_scaling
prediction = softmax(calibrated_logits).numpy()
prediction_list = prediction.tolist()[0]
max_index = np.argmax(prediction)
second_max_index = prediction_list.index(
max(prediction_list[:max_index] + prediction_list[max_index + 1:]))
trash = return_trash_label(max_index)
print(CLASSES[max_index] + ": " +
str(round(max(prediction_list) * 100, 2)) + "%")
print(CLASSES[second_max_index] + ": " +
str(round(prediction_list[second_max_index] * 100, 2)) + "%")
return WASTE_TYPE[trash]
def preprocess_input(x):
# return imagenet_utils.preprocess_input(x, mode='tf')
return preprocess_input(x)
def prepare_image(file):
img = image.load_img(file, target_size=(224, 224))
img_array = image.img_to_array(img)
img_array_expanded_dims = np.expand_dims(img_array, axis=0)
return mobilenet.preprocess_input(
img_array_expanded_dims) #imagei 0 ile 1 arasında normalize eder
def calibrate_on_validation(model_path: str, val_generator) -> float:
logit_model = get_logits_friendly_model(load_model(model_path))
x_val = val_generator.x
y_val = val_generator.y
x_val_pre = preprocess_input(x_val)
return calibrate(logit_model, x_val_pre, y_val)