def __init__(self,
input_file_path,
images_per_batch=50,
train_percentage=0.8,
max_sample_records=1000):
self.input_file_path = input_file_path
folders = os.listdir(self.input_file_path)
folders = sanitize_data_folders(folders)
self.train_folders, self.test_folders = Dataset.train_test_split(
folders)
self.train_percentage = train_percentage
self.max_sample_records = max_sample_records
self.train_metadata_summaries, self.train_metadata = summarize_metadata(
self.input_file_path, self.train_folders)
self.train_folder_weights = self.get_folder_weights(self.train_folders)
self.test_metadata_summaries, self.test_metadata = summarize_metadata(
self.input_file_path, self.test_folders)
self.test_folder_weights = self.get_folder_weights(self.test_folders)
self.images_per_batch = images_per_batch
self.images_per_epoch = int(
self.train_metadata_summaries['image_count'] *
self.train_percentage)
self.batches_per_epoch = int(self.images_per_epoch /
self.images_per_batch)
self.samples_per_epoch = int(self.images_per_epoch /
self.max_sample_records)
def __init__(self,input_file_path,images_per_batch=50,train_percentage=0.8, max_sample_records=1000):
self.input_file_path = input_file_path
folders = os.listdir(self.input_file_path)
folders = sanitize_data_folders(folders)
self.train_percentage = train_percentage
self.train_folders, self.test_folders = self.train_test_split(folders)
self.max_sample_records = max_sample_records
self.train_metadata_summaries, self.train_metadata = summarize_metadata(self.input_file_path,self.train_folders)
self.train_folder_weights = self.get_folder_weights(self.train_folders)
self.test_metadata_summaries, self.test_metadata = summarize_metadata(self.input_file_path, self.test_folders)
self.test_folder_weights = self.get_folder_weights(self.test_folders)
self.images_per_batch = images_per_batch
self.images_per_epoch = self.train_metadata_summaries['image_count']
self.batches_per_epoch = int(self.images_per_epoch / self.images_per_batch)
self.samples_per_epoch = int(self.images_per_epoch / self.max_sample_records)
def __init__(self,input_file_path,images_per_batch=50,images_per_sample=3000,train_percentage=0.8):
self.input_file_path = input_file_path
folders = os.listdir(input_file_path)
self.train_folders, self.test_folders = self.train_test_split(folders)
metadata_summaries = summarize_metadata(input_file_path)
self.train_percentage = train_percentage
self.images_per_batch = images_per_batch
self.images_per_sample = images_per_sample
self.images_per_epoch = int(metadata_summaries['image_count'] * self.train_percentage)
self.samples_per_epoch = int(self.images_per_epoch / self.images_per_sample)
def get_folder_weights(self,folders):
folder_weights = {}
metadata_summaries, folder_metadata = summarize_metadata(self.input_file_path, include_folders=folders)
images_processed = 0
for folder, metadata in folder_metadata.items():
upper_bound = images_processed + metadata['image_count']
folder_weights[folder] = {'lower_bound': images_processed,
'upper_bound': upper_bound,
'weight': metadata['image_count'] / metadata_summaries['image_count']}
images_processed = upper_bound
return folder_weights
def get_folder_weights(self, folders):
folder_weights = {}
metadata_summaries, folder_metadata = summarize_metadata(
self.input_file_path, include_folders=folders)
images_processed = 0
for folder, metadata in folder_metadata.items():
upper_bound = images_processed + metadata['image_count']
folder_weights[folder] = {
'lower_bound':
images_processed,
'upper_bound':
upper_bound,
'weight':
metadata['image_count'] / metadata_summaries['image_count']
}
images_processed = upper_bound
return folder_weights