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()
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')
# (Version 0.2.13 as of 9/8/18)
from autokeras.image_supervised import ImageClassifier, load_image_dataset
train_path = 'datasets/dogsCats/dogCat128rgb_train'
train_labels = 'datasets/dogsCats/dogsCats_train.csv'
validation_path = 'datasets/dogsCats/dogCat128rgb_val'
validation_labels = 'datasets/dogsCats/dogsCats_val.csv'
from os import listdir
from os.path import isfile, join
files = [f for f in listdir(train_path) if isfile(join(train_path, f))]
print(files)
x_train, y_train = load_image_dataset(csv_file_path=train_labels,
images_path=train_path)
print(x_train.shape)
print(y_train.shape)
x_val, y_val = load_image_dataset(csv_file_path=validation_labels,
images_path=validation_path)
print(x_val.shape)
print(y_val.shape)
# Searching for the Best Model
clf = ImageClassifier(verbose=True,
searcher_args={'trainer_args': {
'max_iter_num': 25
}})
clf.fit(x_train, y_train,
elif action_value_list[2].replace('\t', '') == 'false':
rule_value_list.append(0.0)
else:
sys.exit("Invalid rule!!")
rule_list.append(rule_value_list)
line = fp.readline()
my_file = Path(output_keras_mode)
if agent_skip_autokeras is True and my_file.is_file() is True:
print('Skip running AutoKeras ...\n')
else:
if test_csv_file_path is not None and test_images_path is not None:
x_train, y_train = load_image_dataset(
csv_file_path=train_csv_file_path,
images_path=train_images_path)
else:
sys.exit("No train data input!!")
if test_csv_file_path is not None and test_images_path is not None:
x_test, y_test = load_image_dataset(
csv_file_path=test_csv_file_path, images_path=test_images_path)
do_evaluate = True
else:
do_evaluate = False
if agent_percept == 'image' and agent_func_interpert_input == 'autokeras':
clf = ImageClassifier(verbose=True)
clf.fit(x_train, y_train, time_limit=autokeras_timeout)
clf.final_fit(x_train, y_train, x_test, y_test, retrain=True)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Sep 27 16:46:35 2018
@author: Mohamed Laradji
"""
from autokeras.image_supervised import ImageClassifier, load_image_dataset
x_train, y_train = load_image_dataset(csv_file_path="data/train/labels.csv",
images_path="data/train")
x_val, y_val = load_image_dataset(csv_file_path="data/val/labels.csv",
images_path="data/val")
if __name__ == '__main__':
clf = ImageClassifier(verbose=True)
clf.fit(x_train, y_train,
time_limit=12 * 60 * 60) # Currently results in errors.
clf.final_fit(x_train, y_train, x_val, y_val, retrain=True)
y = clf.evaluate(x_val, y_val)
# (x_train, y_train), (x_test, y_test) = mnist.load_data()
# print(x_train.shape, x_train[0].shape, x_train.reshape(x_train.shape + (1,)).shape)
NB_EPOCH = 200
BATCH_SIZE = 128
VERBOSE = 1
NB_CLASSES = 3
OPTIMIZER = RMSprop() # optimizer, explainedin this chapter
N_HIDDEN = 128
VALIDATION_SPLIT = 0.2 # how much TRAIN is reserved for VALIDATION
DROPOUT = 0.3
RESHAPED = 7575
x_train, y_train = load_image_dataset(csv_file_path="train.csv",
images_path="images")
# print('x_train', x_train[0].shape, type(x_train))
# x_train = x_train.reshape(x_train.shape[0], 396, 532, 4)
print('x_train', x_train.shape)
# print('y_train', y_train.shape)
x_test, y_test = load_image_dataset(csv_file_path="test.csv",
images_path="images")
# print(x_test.shape)
# print(y_test.shape)
x_train = x_train.reshape(3077, RESHAPED)
x_test = x_test.reshape(1025, RESHAPED)