preprocess_images.py 文件源码

def run(self):

        # Get paths to all images
        im_files = find_images(join(self.input_dir))
        assert (len(im_files) > 0)

        if 'augmentation' in self.pipeline.keys():
            print "Starting preprocessing ({} processes)".format(self.processes)
            optimization_pool = Pool(self.processes)
            subprocess = partial(preprocess, params=self)
            results = optimization_pool.map(subprocess, im_files)
        else:
            print "Using previously augmented data"

        # Create training and validation (imbalanced)
        print "Splitting into training/validation"

        try:
            train_imgs, val_imgs = self.train_val_split(listdir(self.augment_dir))
            self.random_sample(train_imgs, val_imgs, classes=DEFAULT_CLASSES)
        except AssertionError:
            print "No images found in one more classes - unable to split training and validation"
            exit()