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 data_prep(data_path, rgb=True):
#gamma_map = make_gamma_tables(np.arange(1.0,3.0,0.5))
gamma_map = make_gamma_tables([1])
data_folders = os.listdir(data_path)
data_folders = sanitize_data_folders(data_folders)
shuffle(data_folders)
#data_folders = data_folders[:10]
train_folder_size = int(len(data_folders) * 0.8)
train_predictors = []
train_targets = []
for folder in data_folders[:train_folder_size]:
print("Started session: " + str(folder))
predictors, targets = process_session(data_path + '/' + folder,
gamma_map, rgb)
train_predictors.extend(predictors)
train_targets.extend(targets)
print("Completed session: " + str(folder))
train_predictors_np = np.array(train_predictors)
train_targets_np = np.array(train_targets)
validation_predictors = []
validation_targets = []
for folder in data_folders[train_folder_size:]:
print("Started session: " + str(folder))
predictors, targets = process_session(data_path + '/' + folder,
gamma_map, rgb)
validation_predictors.extend(predictors)
validation_targets.extend(targets)
print("Completed session: " + str(folder))
validation_predictors_np = np.array(validation_predictors)
validation_targets_np = np.array(validation_targets)
max_folder = max([int(folder) for folder in data_folders])
new_file_name = None
if rgb:
new_file_name = '/data_rgb_' + str(max_folder)
else:
new_file_name = '/data_bw_' + str(max_folder)
np.savez(data_path + new_file_name,
train_predictors=train_predictors_np,
train_targets=train_targets_np,
validation_predictors=validation_predictors_np,
validation_targets=validation_targets_np)
def data_prep(data_path,rgb=True):
#gamma_map = make_gamma_tables(np.arange(1.0,3.0,0.5))
gamma_map = make_gamma_tables([1])
data_folders = os.listdir(data_path)
data_folders = sanitize_data_folders(data_folders)
shuffle(data_folders)
#data_folders = data_folders[:10]
train_folder_size = int(len(data_folders) * 0.8)
train_predictors = []
train_targets = []
for folder in data_folders[:train_folder_size]:
print("Started session: " + str(folder))
predictors, targets = process_session(data_path+'/'+folder,gamma_map,rgb)
train_predictors.extend(predictors)
train_targets.extend(targets)
print("Completed session: "+str(folder))
train_predictors_np = np.array(train_predictors)
train_targets_np = np.array(train_targets)
validation_predictors = []
validation_targets = []
for folder in data_folders[train_folder_size:]:
print("Started session: " + str(folder))
predictors, targets = process_session(data_path + '/' + folder,gamma_map,rgb)
validation_predictors.extend(predictors)
validation_targets.extend(targets)
print("Completed session: " + str(folder))
validation_predictors_np = np.array(validation_predictors)
validation_targets_np = np.array(validation_targets)
max_folder = max([int(folder) for folder in data_folders])
new_file_name = None
if rgb:
new_file_name = '/data_rgb_'+str(max_folder)
else:
new_file_name = '/data_bw_'+str(max_folder)
np.savez(data_path+new_file_name, train_predictors=train_predictors_np,
train_targets=train_targets_np,validation_predictors = validation_predictors_np,
validation_targets = validation_targets_np)
import os
from util import shell_command, sanitize_data_folders
def write_metadata(input_dir_path):
input_file_path = input_dir_path + '/predictors_and_targets.npz'
npzfile = np.load(input_file_path)
image_count = len(npzfile['predictors'])
metadata_file_path = input_dir_path + '/metadata.txt'
with open(metadata_file_path, 'w') as writer:
writer.write('image_count:' + str(image_count) + '\n')
data_path = 'C:\\Users\\Zak\\Self-Driving-Car\\data'
data_folders = os.listdir(data_path)
data_folders = sanitize_data_folders(data_folders)
gamma_map = make_gamma_tables([1]) # I should refactor-out the gamma at some point. It's not needed here
rgb = True
for folder in data_folders:
cmd = 'dir '+data_path + '\\' + folder
dir_contents = str(shell_command(cmd))
print("Started work on "+str(folder))
print(dir_contents)
input_dir_path = data_path + '/' + folder
if 'predictors_and_targets.npz' not in dir_contents:
predictors, targets = process_session(data_path + '/' + folder, gamma_map, rgb)
video_to_rgb_npz(input_dir_path,predictors,targets)
print("Completed work on: "+str(folder)+". Created new npz and metadata files.")
write_metadata(input_dir_path)
elif 'metadata.csv' not in dir_contents:
import os
from util import shell_command, sanitize_data_folders
def write_metadata(input_dir_path):
input_file_path = input_dir_path + '/predictors_and_targets.npz'
npzfile = np.load(input_file_path)
image_count = len(npzfile['predictors'])
metadata_file_path = input_dir_path + '/metadata.txt'
with open(metadata_file_path, 'w') as writer:
writer.write('image_count:' + str(image_count) + '\n')
data_path = '/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/data'
data_folders = os.listdir(data_path)
data_folders = sanitize_data_folders(data_folders)
gamma_map = make_gamma_tables([1]) # I should refactor-out the gamma at some point. It's not needed here
rgb = True
for folder in data_folders:
cmd = 'ls '+data_path + '/' + folder
dir_contents = str(shell_command(cmd))
print("Started work on "+str(folder))
print(dir_contents)
input_dir_path = data_path + '/' + folder
if 'predictors_and_targets.npz' not in dir_contents:
predictors, targets = process_session(data_path + '/' + folder, gamma_map, rgb)
video_to_rgb_npz(input_dir_path,predictors,targets)
print("Completed work on: "+str(folder)+". Created new npz and metadata files.")
write_metadata(input_dir_path)
elif 'metadata.csv' not in dir_contents:
