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 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
if __name__ == '__main__':
# 需要把数据放到 ~/.keras/dataset 中，不然下载会报错
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print(x_train.shape)
# (60000, 28, 28)
print('增加一个维度，以符合格式要求')
x_train = x_train.reshape(x_train.shape + (1, ))
print(x_train.shape)
# (60000, 28, 28, 1)
x_test = x_test.reshape(x_test.shape + (1, ))
# 指定模型更新路径
clf = ImageClassifier(path="automodels/", verbose=True)
# 限制为 4 个小时
# 搜索部分
gap = 6
clf.fit(x_train[::gap], y_train[::gap], time_limit=4 * 60 * 60)
# 用表现最好的再训练一次
clf.final_fit(x_train[::gap],
y_train[::gap],
x_test,
y_train,
retrain=True)
y = clf.evaluate(x_test, y_test)
print(y)
print("导出训练好的模型")
clf.export_autokeras_model("automodels/auto_mnist_model")
print("可视化模型")
visualize("automodels/")
x_train.append(img)
# x_train.reshape(256,256,3)
y_train.append(0)
x_train = np.array(x_train)
y_train = np.array(y_train)
for file_name in os.listdir("test/normal"):
img = cv2.imread("test/normal/" + file_name)
x_test.append(img)
# x_train.reshape(256,256,3)
y_test.append(0)
for file_name in os.listdir("test/anomaly"):
img = cv2.imread("test/anomaly/" + file_name)
x_test.append(img)
# x_train.reshape(256,256,3)
y_test.append(0)
x_test = np.array(x_test)
y_test = np.array(y_test)
print(x_train.shape)
print(y_train.shape)
clf = ImageClassifier(verbose=True)
clf.fit(x_train, y_train, time_limit=12 * 60 * 60)
clf.final_fit(x_train, y_train, x_test, y_test, retrain=True)
clf.export_autokeras_model("./autokeras_model.bin") # Auto-Kerasで読み込めるモデルを保存
clf.export_keras_model("./keras_model.bin") # Kerasで読み込めるモデルを保存
acc = clf.evaluate(x_test, y_test)
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)
# x_test = x_test.reshape(x_test.shape + (1,))
# clf = ImageClassifier(path='output/', verbose=True, searcher_args={
# 'trainer_args': {'max_iter_num': 1,
# 'max_no_improvement_num': 1}})
# clf.fit(x_train, y_train, time_limit=1 * 60 * 30)
# clf.final_fit(x_train, y_train, x_test, y_test, retrain=True)
# y = clf.evaluate(x_test, y_test)
# print(y)
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(x_train.shape + (1,))
x_test = x_test.reshape(x_test.shape + (1,))
clf = ImageClassifier(verbose=True, searcher_args={'trainer_args':{'max_iter_num':7}})
clf.fit(x_train, y_train, time_limit=12 * 60 * 60)
clf.final_fit(x_train, y_train, x_test, y_test, retrain=True)
y = clf.evaluate(x_test, y_test)
print(y)
clf.export_autokeras_model('output/auto_mnist_model')
# alternative
best_model = clf.cnn.best_model.produce_model()
pickle_to_file(best_model, 'output/auto_mnist_best_model')
print(best_model)
# Step 2 : After the model training is complete, run examples/visualize.py, whilst passing the same path as parameter
# if __name__ == '__main__':
# visualize('~/automodels/')
y_test = []
base_path = "../data-deep-fashion-women/img/"
#Load the data from local file into a dataframe
df = pd.read_csv('../data-deep-fashion-women/img/WOMEN/labels_test.csv')
print(len(df))
for index, row in df.iterrows():
#print(row[0], row[1])
ss = base_path + row[0]
#print(ss)
img = image.load_img(ss, target_size=(224, 224))
img_data = image.img_to_array(img)
image_data_np = np.array(img_data)
x_test.append(image_data_np)
y_test.append(row[1])
from autokeras.image.image_supervised import load_image_dataset
from autokeras.image.image_supervised import ImageClassifier
clf = ImageClassifier(verbose=True)
clf.fit(x_train, y_train, time_limit=10 * 60 * 60) # 10 hours
clf.final_fit(x_train, y_train, x_test, y_test, retrain=True)
y = clf.evaluate(x_test, y_test)
print(y)
clf.export_autokeras_model('./_models/nas_1.h5')
clf.export_keras_model('./_models/nas_2.h5')
clf.load_searcher().load_best_model().produce_keras_model().save(
'./_models/nas_3.h5')