# To view graph: tensorboard --logdir=/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/tf_visual_data/runs/1/
tf.scalar_summary('accuracy', accuracy)
merged = tf.merge_all_summaries()
train_dir = mkdir(tfboard_run_dir+"/trn/convnet/")
train_activation_layer_1 = mkdir(tfboard_run_dir+"/trn_actvtn_lyr1")
train_activation_layer_2 = mkdir(tfboard_run_dir+"/trn_actvtn_lyr2")
train_activation_layer_3 = mkdir(tfboard_run_dir+"/trn_actvtn_lyr3")
train_activation_layer_4 = mkdir(tfboard_run_dir+"/trn_actvtn_lyr4")
validation_dir = mkdir(tfboard_run_dir+"/vld/convnet/")
# Archive this script to document model design in event of good results that need to be replicated
model_file_path = os.path.dirname(os.path.realpath(__file__))+'/'+os.path.basename(__file__)
shell_command('cp {model_file} {archive_path}'.format(model_file=model_file_path,archive_path=tfboard_run_dir+'/'))
train_writer = tf.train.SummaryWriter(train_dir,sess.graph)
validation_writer = tf.train.SummaryWriter(validation_dir,sess.graph)
validation_predictors[:1000] = validation_predictors[:1000] / 255
sess.run(tf.initialize_all_variables())
batch_index = 0
batches_per_epoch = (train_predictors.shape[0] - train_predictors.shape[0] % 50)/50
for i in range(batch_iterations):
# Shuffle in the very beginning and after each epoch
if batch_index % batches_per_epoch == 0:
train_predictors, train_targets = shuffle_dataset(train_predictors, train_targets)
batch_index = 0
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# To view graph: tensorboard --logdir=/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/tf_visual_data/runs
tf.scalar_summary('accuracy', accuracy)
merged = tf.merge_all_summaries()
tfboard_basedir = '/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/tf_visual_data/runs/'
tfboard_run_dir = mkdir_tfboard_run_dir(tfboard_basedir)
train_dir = mkdir(tfboard_run_dir + "/trn/mlp/")
validation_dir = mkdir(tfboard_run_dir + "/vld/mlp/")
# Archive this script to document model design in event of good results that need to be replicated
model_file_path = os.path.dirname(
os.path.realpath(__file__)) + '/' + os.path.basename(__file__)
shell_command('cp {model_file} {archive_path}'.format(
model_file=model_file_path, archive_path=tfboard_run_dir + '/'))
train_writer = tf.train.SummaryWriter(train_dir, sess.graph)
validation_writer = tf.train.SummaryWriter(validation_dir, sess.graph)
sess.run(tf.initialize_all_variables())
batch_index = 0
batches_per_epoch = (train_predictors.shape[0] -
train_predictors.shape[0] % 50) / 50
for i in range(batch_iterations):
# Shuffle in the very beginning and after each epoch
if batch_index % batches_per_epoch == 0:
train_predictors, train_targets = shuffle_dataset(
train_predictors, train_targets)
batch_index = 0
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:
write_metadata(input_dir_path)
print("Added only metadata file for: " + str(folder) + ".")
else:
print("Completed work on "+str(dir)+". File already exists. No processing necessary.")
print("Finished.")
import numpy as np
import argparse
from util import shell_command, remove_file_if_exists
'''
python frame_count.py \
-i /Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/final_processed_data_3_channels.npz \
-o /Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/
'''
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--input", required = True, help = "path to input numpy dataset")
ap.add_argument("-o", "--output", required = True, help = "path to shape output")
args = vars(ap.parse_args())
input_path = args["input"]
output_path = args["output"]
npzfile = np.load(input_path)
train_predictors = npzfile['train_predictors']
train_targets = npzfile['train_targets']
shape = train_predictors.shape
shape = shape[0]
remove_file_if_exists(output_path+'/shape')
shell_command('echo "{shape}" >> {output}/shape'.format(shape=str(shape),output=output_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:
write_metadata(input_dir_path)
print("Added only metadata file for: " + str(folder) + ".")
else:
print("Completed work on "+str(dir)+". File already exists. No processing necessary.")
print("Finished.")
sys.exit(1)
processed_images = np.array(processed_images)
return processed_images
# Generates negative images from previous driving session.
def random_negative_images():
pass
pixel_size = 24
# Assumes positive images are each separate files
positive_image_dir = "/Users/ryanzotti/Dropbox/StopSigns"
shell_cmd = 'ls {dir}'.format(dir=positive_image_dir)
dir_contents = str(shell_command(shell_cmd)).replace("b\'", "").split("\\n")
file_names = [file_name for file_name in dir_contents if "JPG" in file_name]
positive_images = process_image_set(positive_image_dir, pixel_size)
# Assumes negative images are taken from existing numpy zip file.
# I used my training data. This is ideal because it is
# representive of backgrounds that I would realistically see in a
# production setting
negative_image_file_path = "/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/final_processed_data_3_channels.npz"
npzfile = np.load(negative_image_file_path)
train_predictors = npzfile['train_predictors']
shape = train_predictors.shape
total_frames = shape[0]
height, width = shape[1], shape[2]
negative_images = []
negative_images_count = 3000
else:
print(file_name + " is not a square! It has dimensions " + str(image.shape))
sys.exit(1)
processed_images = np.array(processed_images)
return processed_images
# Generates negative images from previous driving session.
def random_negative_images():
pass
pixel_size = 24
# Assumes positive images are each separate files
positive_image_dir = "/Users/ryanzotti/Dropbox/StopSigns"
shell_cmd = 'ls {dir}'.format(dir=positive_image_dir)
dir_contents = str(shell_command(shell_cmd)).replace("b\'","").split("\\n")
file_names = [file_name for file_name in dir_contents if "JPG" in file_name]
positive_images = process_image_set(positive_image_dir,pixel_size)
# Assumes negative images are taken from existing numpy zip file.
# I used my training data. This is ideal because it is
# representive of backgrounds that I would realistically see in a
# production setting
negative_image_file_path = "/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/final_processed_data_3_channels.npz"
npzfile = np.load(negative_image_file_path)
train_predictors = npzfile['train_predictors']
shape = train_predictors.shape
total_frames = shape[0]
height, width = shape[1], shape[2]
negative_images = []
negative_images_count = 3000
def train(self, sess, x, y_, accuracy, train_step, train_feed_dict,
test_feed_dict):
# To view graph: tensorboard --logdir=/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/tf_visual_data/runs
tf.summary.scalar('accuracy_summary', accuracy)
merged = tf.summary.merge_all()
# Archive the model script in case of good results that need to be replicated
# If model is being restored, then assume model file has already been saved somewhere
# and that self.model_file is None
if self.model_file is not None:
cmd = 'cp {model_file} {archive_path}'
shell_command(
cmd.format(model_file=self.model_file,
archive_path=self.model_dir + '/'))
if not self.restored_model: # Don't want to erase restored model weights
sess.run(tf.global_variables_initializer())
dataset = Dataset(input_file_path=self.data_path,
max_sample_records=self.max_sample_records)
# TODO: Document and understand what RunOptions does
run_opts = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_opts_metadata = tf.RunMetadata()
train_images, train_labels = process_data(
dataset.get_sample(train=True))
train_feed_dict[x] = train_images
train_feed_dict[y_] = train_labels
train_summary, train_accuracy = sess.run(
[merged, accuracy],
feed_dict=train_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
test_images, test_labels = process_data(
dataset.get_sample(train=False))
test_feed_dict[x] = test_images
test_feed_dict[y_] = test_labels
test_summary, test_accuracy = sess.run([merged, accuracy],
feed_dict=test_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
# Always worth printing accuracy, even for a restored model, since it provides an early sanity check
message = "epoch: {0}, training accuracy: {1}, validation accuracy: {2}"
print(message.format(self.start_epoch, train_accuracy, test_accuracy))
if self.tf_timeline: # Used for debugging slow Tensorflow code
create_tf_timeline(self.model_dir, run_opts_metadata)
# Don't double-count. A restored model already has its last checkpoint and results.txt entry available
if not self.restored_model:
with open(self.results_file, 'a') as f:
f.write(
message.format(self.start_epoch, train_accuracy,
test_accuracy) + '\n')
self.save_model(sess, epoch=self.start_epoch)
sync_to_aws(s3_path=self.s3_data_dir,
local_path=self.data_path) # Save to AWS
for epoch in range(self.start_epoch + 1,
self.start_epoch + self.n_epochs):
prev_time = datetime.now()
train_batches = dataset.get_batches(train=True)
for batch_id, batch in enumerate(train_batches):
images, labels = process_data(batch)
train_feed_dict[x] = images
train_feed_dict[y_] = labels
sess.run(train_step, feed_dict=train_feed_dict)
# Track speed to better compare GPUs and CPUs
now = datetime.now()
diff_seconds = (now - prev_time).total_seconds()
if self.show_speed:
speed_results = 'batch {batch_id} of {total_batches}, {seconds} seconds'
speed_results = speed_results.format(
batch_id=batch_id,
seconds=diff_seconds,
total_batches=dataset.batches_per_epoch)
with open(self.speed_file, 'a') as f:
f.write(speed_results + '\n')
print(speed_results)
prev_time = datetime.now()
# TODO: Document and understand what RunOptions does
run_opts = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_opts_metadata = tf.RunMetadata()
train_images, train_labels = process_data(
dataset.get_sample(train=True))
train_feed_dict[x] = train_images
train_feed_dict[y_] = train_labels
train_summary, train_accuracy = sess.run(
[merged, accuracy],
feed_dict=train_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
test_images, test_labels = process_data(
dataset.get_sample(train=False))
test_feed_dict[x] = test_images
test_feed_dict[y_] = test_labels
test_summary, test_accuracy = sess.run(
[merged, accuracy],
feed_dict=test_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
print(message.format(epoch, train_accuracy, test_accuracy))
with open(self.results_file, 'a') as f:
f.write(
message.format(epoch, train_accuracy, test_accuracy) +
'\n')
# Save a model checkpoint after every epoch
self.save_model(sess, epoch=epoch)
sync_to_aws(s3_path=self.s3_data_dir,
local_path=self.data_path) # Save to AWS
# Marks unambiguous successful completion to prevent deletion by cleanup script
shell_command('touch ' + self.model_dir + '/SUCCESS')
def train(self, sess, x, y_, accuracy, train_step, train_feed_dict,
test_feed_dict):
# To view graph: tensorboard --logdir=/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/tf_visual_data/runs
tf.scalar_summary('accuracy', accuracy)
merged = tf.merge_all_summaries()
# Archive this script to document model design in event of good results that need to be replicated
model_file_path = os.path.dirname(
os.path.realpath(__file__)) + '/' + os.path.basename(__file__)
cmd = 'cp {model_file} {archive_path}'
shell_command(
cmd.format(model_file=self.model_file,
archive_path=self.tfboard_run_dir + '/'))
sess.run(tf.initialize_all_variables())
dataset = Dataset(input_file_path=self.data_path,
max_sample_records=self.max_sample_records)
# Not sure what these two lines do
run_opts = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_opts_metadata = tf.RunMetadata()
train_images, train_labels = process_data(
dataset.get_sample(train=True))
train_feed_dict[x] = train_images
train_feed_dict[y_] = train_labels
train_summary, train_accuracy = sess.run(
[merged, accuracy],
feed_dict=train_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
test_images, test_labels = process_data(
dataset.get_sample(train=False))
test_feed_dict[x] = test_images
test_feed_dict[y_] = test_labels
test_summary, test_accuracy = sess.run([merged, accuracy],
feed_dict=test_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
message = "epoch: {0}, training accuracy: {1}, validation accuracy: {2}"
print(message.format(-1, train_accuracy, test_accuracy))
with open(self.results_file, 'a') as f:
f.write(message.format(-1, train_accuracy, test_accuracy) + '\n')
for epoch in range(self.epochs):
train_batches = dataset.get_batches(train=True)
for batch in train_batches:
images, labels = process_data(batch)
train_feed_dict[x] = images
train_feed_dict[y_] = labels
train_step.run(feed_dict=train_feed_dict)
# TODO: remove all this hideous boilerplate
run_opts = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_opts_metadata = tf.RunMetadata()
train_images, train_labels = process_data(
dataset.get_sample(train=True))
train_feed_dict[x] = train_images
train_feed_dict[y_] = train_labels
train_summary, train_accuracy = sess.run(
[merged, accuracy],
feed_dict=train_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
test_images, test_labels = process_data(
dataset.get_sample(train=False))
test_feed_dict[x] = test_images
test_feed_dict[y_] = test_labels
test_summary, test_accuracy = sess.run(
[merged, accuracy],
feed_dict=test_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
print(message.format(epoch, train_accuracy, test_accuracy))
with open(self.results_file, 'a') as f:
f.write(
message.format(epoch, train_accuracy, test_accuracy) +
'\n')
# Save the trained model to a file
saver = tf.train.Saver()
save_path = saver.save(sess, self.tfboard_run_dir + "/model.ckpt")
# Marks unambiguous successful completion to prevent deletion by cleanup script
shell_command('touch ' + self.tfboard_run_dir + '/SUCCESS')
def train(self, sess, x, y_, accuracy, train_step, train_feed_dict,
test_feed_dict):
# To view graph: tensorboard --logdir=/Users/ryanzotti/Documents/repos/Self_Driving_RC_Car/tf_visual_data/runs
tf.summary.scalar('accuracy', accuracy)
merged = tf.summary.merge_all()
# Archive the model script in case of good results that need to be replicated
# If model is being restored, then assume model file has already been saved somewhere
# and that self.model_file is None
if self.model_file is not None:
cmd = 'cp {model_file} {archive_path}'
shell_command(
cmd.format(model_file=self.model_file,
archive_path=self.tfboard_run_dir + '/'))
sess.run(tf.global_variables_initializer())
dataset = Dataset(input_file_path=self.data_path,
max_sample_records=self.max_sample_records)
# TODO: Document and understand what RunOptions does
run_opts = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_opts_metadata = tf.RunMetadata()
train_images, train_labels = process_data(
dataset.get_sample(train=True))
train_feed_dict[x] = train_images
train_feed_dict[y_] = train_labels
train_summary, train_accuracy = sess.run(
[merged, accuracy],
feed_dict=train_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
test_images, test_labels = process_data(
dataset.get_sample(train=False))
test_feed_dict[x] = test_images
test_feed_dict[y_] = test_labels
test_summary, test_accuracy = sess.run([merged, accuracy],
feed_dict=test_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
message = "epoch: {0}, training accuracy: {1}, validation accuracy: {2}"
print(message.format(self.start_epoch, train_accuracy, test_accuracy))
with open(self.results_file, 'a') as f:
f.write(
message.format(self.start_epoch, train_accuracy, test_accuracy)
+ '\n')
# Save a model checkpoint after every epoch
self.save_model(sess, epoch=self.start_epoch)
for epoch in range(self.start_epoch + 1,
self.start_epoch + self.n_epochs):
train_batches = dataset.get_batches(train=True)
for batch in train_batches:
images, labels = process_data(batch)
train_feed_dict[x] = images
train_feed_dict[y_] = labels
sess.run(train_step, feed_dict=train_feed_dict)
# TODO: Document and understand what RunOptions does
run_opts = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_opts_metadata = tf.RunMetadata()
train_images, train_labels = process_data(
dataset.get_sample(train=True))
train_feed_dict[x] = train_images
train_feed_dict[y_] = train_labels
train_summary, train_accuracy = sess.run(
[merged, accuracy],
feed_dict=train_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
test_images, test_labels = process_data(
dataset.get_sample(train=False))
test_feed_dict[x] = test_images
test_feed_dict[y_] = test_labels
test_summary, test_accuracy = sess.run(
[merged, accuracy],
feed_dict=test_feed_dict,
options=run_opts,
run_metadata=run_opts_metadata)
print(message.format(epoch, train_accuracy, test_accuracy))
with open(self.results_file, 'a') as f:
f.write(
message.format(epoch, train_accuracy, test_accuracy) +
'\n')
# Save a model checkpoint after every epoch
self.save_model(sess, epoch=epoch)
# Marks unambiguous successful completion to prevent deletion by cleanup script
shell_command('touch ' + self.tfboard_run_dir + '/SUCCESS')
