def train_autokeras(self):
#Load images
train_data, train_labels = load_image_dataset(csv_file_path=self.TRAIN_CSV_DIR, images_path=self.RESIZE_TRAIN_IMG_DIR)
test_data, test_labels = load_image_dataset(csv_file_path=self.TEST_CSV_DIR, images_path=self.RESIZE_TEST_IMG_DIR)
train_data = train_data.astype('float32') / 255
test_data = test_data.astype('float32') / 255
print("Train data shape:", train_data.shape)
clf = ImageClassifier(verbose=True, path=self.TEMP_DIR, resume=False)
clf.fit(train_data, train_labels, time_limit=self.TIME)
clf.final_fit(train_data, train_labels, test_data, test_labels, retrain=True)
evaluate_value = clf.evaluate(test_data, test_labels)
print("Evaluate:", evaluate_value)
# clf.load_searcher().load_best_model().produce_keras_model().save(MODEL_DIR)
# clf.export_keras_model(MODEL_DIR)
clf.export_autokeras_model(self.MODEL_DIR)
#统计训练信息
dic = {}
ishape = clf.cnn.searcher.input_shape
dic['n_train'] = train_data.shape[0] #训练总共用了多少图
dic['n_classes'] = clf.cnn.searcher.n_classes
dic['input_shape'] = str(ishape[0]) + 'x' + str(ishape[1]) + 'x' + str(ishape[2])
dic['history'] = clf.cnn.searcher.history
dic['model_count'] = clf.cnn.searcher.model_count
dic['best_model'] = clf.cnn.searcher.get_best_model_id()
best_model = [item for item in dic['history'] if item['model_id'] == dic['best_model']]
if len(best_model) > 0:
dic['loss'] = best_model[0]['loss']
dic['metric_value'] = best_model[0]['metric_value']
dic['evaluate_value'] = evaluate_value
self.traininfo = dic
def load_images():
x_train, y_train = load_image_dataset(csv_file_path="train/label.csv",
images_path="train")
print(x_train.shape)
print(y_train.shape)
x_test, y_test = load_image_dataset(csv_file_path="test/label.csv",
images_path="test")
print(x_test.shape)
print(y_test.shape)
return x_train, y_train, x_test, y_test
def load_images():
x_train, y_train = load_image_dataset(csv_file_path="train/label.csv",
images_path="train")
print(x_train.shape)
print(y_train.shape)
x_test, y_test = load_image_dataset(csv_file_path="test/label.csv",
images_path="test")
print(x_test.shape)
print(y_test.shape)
return x_train, y_train, x_test, y_test
def train_model():
clf = ak.ImageClassifier(verbose=True, augment=False)
train_data, train_labels = load_image_dataset(csv_file_path=train_data_dir+"/label.csv",
images_path=train_data_dir)
validation_data, validation_labels = load_image_dataset(csv_file_path=validation_data_dir+"/label.csv",
images_path=validation_data_dir)
clf.fit(train_data, train_labels)
clf.final_fit(train_data, train_labels, validation_data, validation_labels, retrain=True)
y = clf.evaluate(validation_data, validation_labels)
print("auto CNN classifier accuracy: %f" % y)
clf.load_searcher().load_best_model().produce_keras_model().save('shallowCNN_model.h5')
def load_images():
x_train, y_train = load_image_dataset(csv_file_path=data_dir +
"/labels_real.csv",
images_path=data_dir + "/train")
print(x_train.shape)
print(y_train.shape)
x_test = load_image_dataset(csv_file_path=data_dir +
"/sample_submission_real.csv",
images_path=data_dir + "/test")
print(x_test[0].shape)
return x_train, y_train, x_test[0]
def load_invasive_species():
data_dir = "datasets/invasive-species"
x_train, y_train = load_image_dataset(csv_file_path=data_dir +
"/train_labels_real.csv",
images_path=data_dir + "/train")
print(x_train.shape)
print(y_train.shape)
x_test, y_test = load_image_dataset(csv_file_path=data_dir +
"/sample_submission_real.csv",
images_path=data_dir + "/test")
print(x_test.shape)
return x_train, y_train, x_test
def load_plant_seedlings():
data_dir = "datasets/plant-seedlings"
x_train, y_train = load_image_dataset(
csv_file_path=data_dir + "/train.csv",
images_path=data_dir + "/train_files")
print(x_train.shape)
print(y_train.shape)
x_test = load_image_dataset(csv_file_path=data_dir +
"/sample_submission.csv",
images_path=data_dir + "/test")
print(x_test[0].shape)
return x_train, y_train, x_test[0]
def load_aerial_cactus():
data_dir = "datasets/aerial-cactus"
x_train, y_train = load_image_dataset(csv_file_path=data_dir +
"/train.csv",
images_path=data_dir + "/train")
print(x_train.shape)
print(y_train.shape)
x_test = load_image_dataset(csv_file_path=data_dir +
"/sample_submission.csv",
images_path=data_dir + "/test")
print(x_test[0].shape)
return x_train, y_train, x_test[0]
def predict_autokeras(self):
#Load images
test_data, test_labels = load_image_dataset(csv_file_path=self.PREDICT_CSV_DIR, images_path=self.RESIZE_PREDICT_IMG_DIR)
test_data = test_data.astype('float32') / 255
print("Test data shape:", test_data.shape)
autokeras_model = pickle_from_file(self.MODEL_DIR)
autokeras_score = autokeras_model.evaluate(test_data, test_labels)
print(autokeras_score)
def train_autokeras(RESIZE_TRAIN_IMG_DIR, RESIZE_TEST_IMG_DIR, TRAIN_CSV_DIR,
TEST_CSV_DIR, TIME):
# Load images
train_data, train_labels = load_image_dataset(
csv_file_path=TRAIN_CSV_DIR, images_path=RESIZE_TRAIN_IMG_DIR) # 加载数据
test_data, test_labels = load_image_dataset(
csv_file_path=TEST_CSV_DIR, images_path=RESIZE_TEST_IMG_DIR)
train_data = train_data.astype('float32') / 255
test_data = test_data.astype('float32') / 255
clf = ImageClassifier(verbose=True)
clf.fit(train_data, train_labels, time_limit=TIME) # 找最优模型
clf.final_fit(train_data,
train_labels,
test_data,
test_labels,
retrain=True) # 最优模型继续训练
y = clf.evaluate(test_data, test_labels)
print("测试集精确度:", y)
score = clf.evaluate(train_data, train_labels) # score: 0.8139240506329114
print("训练集精确度:", score)
clf.export_keras_model(MODEL_DIR) # 储存
def train_autokeras(RESIZE_TRAIN_IMG_DIR, TRAIN_CSV_DIR, RESIZE_TEST_IMG_DIR,
TEST_CSV_DIR, TIME):
#Load images
train_data, train_labels = load_image_dataset(
csv_file_path=TRAIN_CSV_DIR, images_path=RESIZE_TRAIN_IMG_DIR)
test_data, test_labels = load_image_dataset(
csv_file_path=TEST_CSV_DIR, images_path=RESIZE_TEST_IMG_DIR)
train_data = train_data.astype('float32') / 255
test_data = test_data.astype('float32') / 255
print("Train data shape:", train_data.shape)
clf = ImageClassifier(verbose=True)
clf.fit(train_data, train_labels, time_limit=TIME)
clf.final_fit(train_data,
train_labels,
test_data,
test_labels,
retrain=True)
y = clf.evaluate(test_data, test_labels)
print("Evaluate:", y)
#Predict the category of the test image
img = load_img(PREDICT_IMG_PATH)
x = img_to_array(img)
x = x.astype('float32') / 255
x = np.reshape(x, (1, RESIZE, RESIZE, 3))
print("x shape:", x.shape)
y = clf.predict(x)
print("predict:", y)
clf.load_searcher().load_best_model().produce_keras_model().save(MODEL_DIR)
#Save model architecture diagram
model = load_model(MODEL_DIR)
plot_model(model, to_file=MODEL_PNG)
def train_autokeras(self):
time_limit = self.projectinfo['parameter_time']
#Load images
train_data, train_labels = load_image_dataset(csv_file_path=self.project_train_labels_csv,
images_path=self.project_resize_train_dir)
test_data, test_labels = load_image_dataset(csv_file_path=self.project_test_labels_csv,
images_path=self.project_resize_test_dir)
train_data = train_data.astype('float32') / 255
test_data = test_data.astype('float32') / 255
self.log.info("Train data shape: %d" % train_data.shape[0])
clf = ImageClassifier(verbose=True, path=self.project_tmp_dir, resume=False)
clf.fit(train_data, train_labels, time_limit=time_limit)
clf.final_fit(train_data, train_labels, test_data, test_labels, retrain=True)
evaluate_value = clf.evaluate(test_data, test_labels)
self.log.info("Evaluate: %f" % evaluate_value)
clf.export_autokeras_model(self.project_mod_path)
#统计训练信息
dic = {}
ishape = clf.cnn.searcher.input_shape
dic['n_train'] = train_data.shape[0] #训练总共用了多少图
dic['n_classes'] = clf.cnn.searcher.n_classes
dic['input_shape'] = str(ishape[0]) + 'x' + str(ishape[1]) + 'x' + str(ishape[2])
dic['history'] = clf.cnn.searcher.history
dic['model_count'] = clf.cnn.searcher.model_count
dic['best_model'] = clf.cnn.searcher.get_best_model_id()
best_model = [item for item in dic['history'] if item['model_id'] == dic['best_model']]
if len(best_model) > 0:
dic['loss'] = best_model[0]['loss']
dic['metric_value'] = best_model[0]['metric_value']
dic['evaluate_value'] = evaluate_value
return dic
from autokeras.image.image_supervised import load_image_dataset
# clf = ak.ImageClassifier(verbose=True, augment=False)
clf = ak.ImageClassifier(
path=
"/home/mayank_sati/pycharm_projects/tensorflow/traffic_light_detection_classification-master/traffic_light_classification/autokeras/visualise",
verbose=True,
augment=False)
# clf = ImageClassifier(path="~/automodels/",verbose=True, augment=False)
train_image_path = "/home/mayank_sati/Desktop/sorting_light/all_train_images"
test_image_path = "/home/mayank_sati/Desktop/sorting_light/all_train_images"
train_csv = "/home/mayank_sati/Desktop/sorting_light/train_color_autokeras.csv"
test_csv = "/home/mayank_sati/Desktop/sorting_light/test_color_autokeras.csv"
x_train, y_train = load_image_dataset(csv_file_path=train_csv,
images_path=train_image_path)
print(x_train.shape)
print(y_train.shape)
x_test, y_test = load_image_dataset(csv_file_path=test_csv,
images_path=train_image_path)
print(x_test.shape)
print(y_test.shape)
# clf = ImageClassifier(verbose=True)
clf.fit(x_train, y_train, time_limit=10 * 60)
clf.final_fit(x_train, y_train, x_test, y_test, retrain=True)
y = clf.evaluate(x_test, y_test)
print(y)
from autokeras.image.image_supervised import ImageClassifier, load_image_dataset
# we created ./all path where we copied all the images
train_path = '../data/all'
train_labels = '../data/labels_train.csv'
x_train, y_train = load_image_dataset(csv_file_path=train_labels,
images_path=train_path)
#x_val, y_val = load_image_dataset(csv_file_path=validation_labels,images_path=validation_path)
clf = ImageClassifier(verbose=True)
# 4 hours search
clf.fit(x_train, y_train, time_limit=4 * 60 * 60)
best_model = clf.export_keras_model()
keras_model = best_model.produce_keras_model('asdf')
keras_model.summary()
# save it
keras_model.save('best.hdf5')
#clf.final_fit(x_train,y_train,x_val,y_val,retrain = True, trainer_args={'max_iter_num':10})
#print(clf.evaluate(x_val,y_val))
# In[ ]:
size_of_image = 1024
# In[ ]:
hours_for_training = float(input("How many hours to train (in decimals)?"))
# In[ ]:
from autokeras.image.image_supervised import load_image_dataset
# In[ ]:
x_train, y_train = load_image_dataset(
csv_file_path="split_data/train/label.csv",
images_path="split_data/resized-train/")
print(x_train.shape)
print(y_train.shape)
# In[ ]:
from autokeras.image.image_supervised import ImageClassifier
# In[ ]:
get_ipython().system(u'mkdir models')
clf = ImageClassifier(path="models/", verbose=True)
clf.fit(x_train, y_train, time_limit=hours_for_training * 60 * 60)
# In[ ]:
from keras.utils import plot_model
from keras.models import load_model
from keras.models import Sequential
from autokeras.utils import pickle_from_file
import sys
import numpy as np
sys.path.append("/home/deep/PycharmProjects/autokeras")
from autokeras.image.image_supervised import load_image_dataset
x_test_keyhole, y_test_keyhole = load_image_dataset(
csv_file_path="data_by_liuyang/test/test_keyhole.csv",
images_path="data_by_liuyang/test/the_keyhole")
print("the key hole:", x_test_keyhole.shape)
print(y_test_keyhole.shape)
x_test_no_keyhole, y_test_no_keyhole = load_image_dataset(
csv_file_path="data_by_liuyang/test/test_no_keyhole.csv",
images_path="data_by_liuyang/test/no_keyhole")
print(x_test_no_keyhole.shape)
print(y_test_no_keyhole.shape)
x_test, y_test = np.vstack((x_test_keyhole, x_test_no_keyhole)), np.hstack(
(y_test_keyhole, y_test_no_keyhole))
model_file_name = 'data_by_liuyang/model/autokeras.h5' #加载模型
#model = load_model('data_by_liuyang/model/autokeras.h5')
model = pickle_from_file(model_file_name)
#model = Sequential(model)
#plot_model(model, to_file='my_model.png')
results = model.evaluate(x_test, y_test) #用测试数据测试
print(results) #打印结果
from autokeras.image.image_supervised import load_image_dataset
RESIZE_TRAIN_IMG_DIR = './data/resize/train'
RESIZE_TEST_IMG_DIR = './data/resize/test'
# Path to generate csv file
TRAIN_CSV_DIR = './train_labels.csv'
TEST_CSV_DIR = './test_labels.csv'
train_data, train_labels = load_image_dataset(csv_file_path=TRAIN_CSV_DIR,
images_path=RESIZE_TRAIN_IMG_DIR)
test_data, test_labels = load_image_dataset(csv_file_path=TEST_CSV_DIR,
images_path=RESIZE_TEST_IMG_DIR)
train_data = train_data.astype('float32') / 255
print('111' * 100)
from keras.datasets import fashion_mnist
(X_train, y_train), (X_test, y_test) = fashion_mnist.load_data()
# each image has to 3D: 2 coordinates, 1 value (gray scale)
X_train = X_train.reshape(X_train.shape + (1, ))
X_test = X_test.reshape(X_test.shape + (1, ))
# initialize the list of trianing times that we'll allow
# Auto-Keras to train for
TRAINING_TIMES = [
# 60 * 60, # 1 hour
# 60 * 60 * 2, # 2 hours
# 60 * 60 * 4, # 4 hours
# 60 * 60 * 8, # 8 hours
60 * 60 * 12, # 12 hours
# 60 * 60 * 24, # 24 hours
]
# load the training and testing data, then scale it into the
# range [0, 1]
print("[INFO] loading 101_ObjectCategories data...")
trainX, trainY = load_image_dataset(csv_file_path='./101_ObjectCategories/train/label.csv',
images_path='./101_ObjectCategories/train')
# testX, testY = load_image_dataset(csv_file_path='./101_ObjectCategories/test/label.csv',
# images_path='./101_ObjectCategories/test')
# trainX = trainX.astype("float") / 255.0
# testX = testX.astype("float") / 255.0
# initialize the label names for the CIFAR-10 dataset
# labelNames = ['scorpion', 'hedgehog', 'anchor', 'joshua_tree', 'lobster', 'pyramid', 'ant',
# 'dollar_bill', 'gerenuk', 'bass', 'trilobite', 'chandelier', 'dolphin', 'panda',
# 'inline_skate', 'gramophone', 'camera', 'pizza', 'kangaroo', 'crocodile_head',
# 'flamingo', 'hawksbill', 'ceiling_fan', 'lamp', 'lotus', 'ketch', 'cannon', 'stapler',
# 'crocodile', 'wrench', 'scissors', 'umbrella', 'BACKGROUND_Google', 'minaret', 'crayfish',
# 'ewer', 'cougar_body', 'okapi', 'Motorbikes', 'accordion', 'sunflower', 'headphone', 'bonsai',
# 'mayfly', 'elephant', 'airplanes', 'cup', 'garfield', 'platypus', 'brontosaurus', 'butterfly',
# 'euphonium', 'grand_piano', 'stegosaurus', 'nautilus', 'helicopter', 'rhino', 'wheelchair',
# 'pagoda', 'laptop', 'tick', 'schooner', 'yin_yang', 'beaver', 'snoopy', 'watch', 'emu', 'dragonfly',
import sys
sys.path.append("/home/deep/PycharmProjects/autokeras")
from autokeras.image.image_supervised import load_image_dataset
import numpy as np
x_train_keyhole, y_train_keyhole = load_image_dataset(
csv_file_path="deal-data/train/train_keyhole.csv",
images_path="deal-data/train/the_keyhole")
print(x_train_keyhole.shape)
print(y_train_keyhole.shape)
x_train_no_keyhole, y_train_no_keyhole = load_image_dataset(
csv_file_path="deal-data/train/train_no_keyhole.csv",
images_path="deal-data/train/no_keyhole")
print(x_train_no_keyhole.shape)
print(y_train_no_keyhole.shape)
#将训练数据加起来
x_train, y_train = np.vstack([x_train_keyhole, x_train_no_keyhole]), np.hstack(
[y_train_keyhole, y_train_no_keyhole])
print("x_train:", x_train.shape)
print("y_train", y_train.shape)
x_test_keyhole, y_test_keyhole = load_image_dataset(
csv_file_path="deal-data/test/test_keyhole.csv",
images_path="deal-data/test/the_keyhole")
print("the key hole:", x_test_keyhole.shape)
print(y_test_keyhole.shape)
x_test_no_keyhole, y_test_no_keyhole = load_image_dataset(
csv_file_path="deal-data/test/test_no_keyhole.csv",
images_path="deal-data/test/no_keyhole")
print(x_test_no_keyhole.shape)
from autokeras.utils import pickle_from_file
from autokeras.image.image_supervised import load_image_dataset
model_file_name = "mnist_1_hour"
model = pickle_from_file(model_file_name)
x_test, y_test = load_image_dataset(
csv_file_path="./../data-mnist/test_label.csv",
images_path="./../data-mnist/test")
results = model.evaluate(x_test, y_test)
print(results)
from autokeras.image.image_supervised import load_image_dataset from autokeras.image.image_supervised import ImageClassifier x_train, y_train = load_image_dataset(csv_file_path="../data-mnist/train_label.csv", images_path="../data-mnist/train") print(len(x_train)) # print(x_train.shape) # print(y_train.shape) x_test, y_test = load_image_dataset(csv_file_path="../data-mnist/test_label.csv", images_path="../data-mnist/test") # print(x_test.shape) # print(y_test.shape) clf = ImageClassifier(verbose=True) clf.fit(x_train, y_train, time_limit= 14 * 60 * 60) # 14 hours clf.final_fit(x_train, y_train, x_test, y_test, retrain=True) y = clf.evaluate(x_test, y_test) print(y) model_file_name = "mnist_1_hour" clf.export_autokeras_model(model_file_name)
