def main():
pre_processing(['./train/','./val/'])
x,y = load_data('./train/')
k = NN(x,y,20)
x = k.normalize(x)
k.add_layer(50,tf.nn.relu)
k.add_layer(50,tf.nn.relu)
k.add_layer(10,tf.nn.softmax)
h = k.train()
x_val,y_val = load_data('./val/')
predictions = [ np.argmax(yi) for yi in np.array(k.predict(x_val))]
print(k.confusion_matrix(y_val,predictions))
loss, acc = k.evaluate(x_val,y_val)
print('loss: ',loss)
print('acc: ',acc*100,'%')
# Plot training & validation accuracy values
plt.plot(h.history['acc'])
# plt.plot(h2.history['acc'])
plt.title('Model accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()
def __call__(self):
images = load_hdf5(self.images_path)
labels = load_hdf5(self.labels_path)
masks = load_hdf5(self.mask_path)
images = pre_processing(images)
if np.max(labels) > 1:
labels = labels / 255.
masks = masks / 255.
if self.train_test == 'train':
return self.extract_ordered(images, labels)
if self.train_test == 'test':
sub_images, sub_labels = self.extract_ordered(images, labels)
return (sub_images, images, labels, masks)
def __call__(self):
images = load_hdf5(self.images_path)
labels = load_hdf5(self.labels_path)
masks = load_hdf5(self.mask_path)
assert(images.shape[1]==self.height and images.shape[2]==self.width)
assert(labels.shape[1]==self.height and labels.shape[2]==self.width)
assert(masks.shape[1]==self.height and masks.shape[2]==self.width)
images = pre_processing(images)
if np.max(labels) > 1:
labels = labels / 255.
masks = masks / 255.
images, labels, masks = self.padding(images, labels, masks)
print('images:', images.shape, images.dtype, np.min(images), np.max(images))
print('labels:', labels.shape, labels.dtype, np.min(labels), np.max(labels))
print('masks:', masks.shape, masks.dtype, np.min(masks), np.max(masks))
return images, labels, masks
def __call__(self):
images = load_hdf5(self.images_path)
labels = load_hdf5(self.labels_path)
masks = load_hdf5(self.mask_path)
images = pre_processing(images)
if np.max(labels) > 1:
labels = labels / 255.
masks = masks / 255.
#visualize(group_images(images, 4)).show()
#visualize(group_images(labels, 4)).show()
#visualize(group_images(masks, 4)).show()
#print(images.shape, images.dtype, np.min(images), np.max(images))
#print(labels.shape, labels.dtype, np.min(labels), np.max(labels))
#print(masks.shape, masks.dtype, np.min(masks), np.max(masks))
if self.train_test == 'train':
return self.extract_ordered(images, labels)
if self.train_test == 'test':
sub_images, sub_labels = self.extract_ordered(images, labels)
return (sub_images, images, labels, masks)
import pre_process
import logistic_reg
import svm
import random_forest
output_file = "D:/data/output_1.csv"
pre_process.pre_processing("D:/data/Epi.pkl")
# Modoule selection
choice = input(
"choose your modoule : 1.Logistic Regression 2.SVM 3.Random Forest :")
if choice == '1':
logistic_reg.logistic_reg("D:/data/output_3.pkl")
elif choice == '2':
svm.svm("D:/data/output_3.pkl")
elif choice == '3':
random_forest.random_forest("D:/data/output_3.pkl")