test_labels = np.argmax(dataset.test_labels, axis=1)
test_features = dataset.test_features
csv_writer.append_to_file(
['#', 'Paveikslėlis', 'Nuspėta klasė', 'Tikroji klasė'])
for index in range(30):
csv_writer.append_to_file([
index + 1, '', LABELS[prediction_labels[index]],
LABELS[test_labels[index]]
])
image_saver.plt.imshow(test_features[index])
image_saver.save_image(index)
if __name__ == '__main__':
dataset = Dataset(data_folder='./data')
dataset.load_data(data_parts=[0.7, 0.2, 0.1])
print(dataset.get_data_summary())
l_rate, momentum, n_epoch, batch_size, verbose, optimizer, loss_func = load_P1_options(
)
model = Model(l_rate=l_rate,
momentum=momentum,
optimizer=optimizer,
loss=loss_func)
# train_scenario()
load_from_file_scenario()
loss, accuracy, predictions = model.evaluate(
test_data=dataset.test_features,
plt.ylabel('True label')
plt.xlabel('Predicted label')
ap = argparse.ArgumentParser()
ap.add_argument("-m",
"--model",
default="svm.pickle",
help="path to where the model will be stored")
args = vars(ap.parse_args())
print("Collecting annotations ...")
#CHANGE 'inflammed aorta' to the disease which you are working to diagnose
d = Dataset(myDirectory, myDirectory, ['inflamed aorta'])
labels, images = d.load_data()
print("Gathered {} image slices".format(len(images)))
data = []
labels_new = []
hog = HOG(orientations=19,
pixelsPerCell=(8, 8),
cellsPerBlock=(3, 3),
transform=True)
for i, image in enumerate(images):
if i % 100 == 0:
print("Gathering features, {} of {}".format(i, len(images)))
if 0 not in image.shape:
image_resized = resize(image, (291, 218), anti_aliasing=True)
hist = hog.describe(rgb2gray(image_resized))
