def main():
global num_dense_sample
description = 'This script is for testing posenet'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('input_beacon_setting_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path where beacon setting file is saved.')
parser.add_argument('input_model_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where input model is saved.')
parser.add_argument('output_graph_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path where exported graph def protobuf (.pb) file will be saved.')
parser.add_argument('output_model_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where output model will be saved.')
parser.add_argument('-s', '--use_shrink_model', action='store_true', default=False, \
help='Use shrink model (default: False)')
parser.add_argument('-l', '--lstm_model', action='store_true', default=False, \
help='Export LSTM model (default: False)')
args = parser.parse_args()
input_beacon_setting_file = args.input_beacon_setting_file
input_model_dir = args.input_model_dir
output_graph_file = args.output_graph_file
output_model_dir = args.output_model_dir
output_model_file = os.path.join(output_model_dir, "model.ckpt")
use_shrink_model = args.use_shrink_model
lstm_model = args.lstm_model
print "use shrink model for training : " + str(use_shrink_model)
# parse beacon setting file
beaconmap = IBeaconUtils.parseBeaconSetting(input_beacon_setting_file)
beacon_num = len(beaconmap.keys())
# convert hd5 file to ckpt
# https://github.com/keras-team/keras/issues/9040
K.set_learning_phase(0)
if use_shrink_model:
if lstm_model:
model = posenet_beacon_no_inception_shrink_lstm_keras.create_posenet(beacon_num, trainable=False)
else:
model = posenet_beacon_no_inception_shrink_keras.create_posenet(beacon_num, trainable=False)
else:
print "Do not shrink model is not supported"
sys.exit()
model.load_weights(os.path.join(input_model_dir, 'trained_weights.h5'))
model.summary()
#Save graph and checkpoint
session = keras.backend.get_session()
graph = session.graph
graph_def = graph.as_graph_def()
with gfile.GFile(output_graph_file, 'wb') as f:
f.write(graph_def.SerializeToString())
saver = tf.train.Saver()
saver.save(session, output_model_file)
def main():
description = 'This script is for testing posenet'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('input_txt_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path of input txt file in Cambridge Visual Landmark Dataset format.')
parser.add_argument('input_beacon_setting_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path where beacon setting file is saved.')
parser.add_argument('output_model_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where output models will be saved.')
parser.add_argument('output_log_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where log files will be saved.')
parser.add_argument('-w', '--input_beacon_weight_file', action='store', type=str, default=None, \
help='File path beacon posenet weiht is stored in numpy format.')
parser.add_argument('-s', '--use_shrink_model', action='store_true', default=False, \
help='Use shrink model (default: False)')
parser.add_argument('-f', '--use_fixed_input_mean_std', action='store_true', default=False, \
help='Use fixed input mean and std (default: False)')
parser.add_argument('-a', '--use_augmentation_beacon', action='store_true', default=False, \
help='Use data augmentation for beacon data (default: False)')
parser.add_argument('-e', '--epochs', action='store', type=int, default=posenet_config.epochs, \
help='Epochs (Default : ' + str(posenet_config.epochs))
parser.add_argument('-b', '--batch_size', action='store', type=int, default=posenet_config.lstm_batch_size, \
help='Batch size (Default : ' + str(posenet_config.lstm_batch_size))
args = parser.parse_args()
input_txt_file = args.input_txt_file
input_beacon_setting_file = args.input_beacon_setting_file
output_model_dir = args.output_model_dir
output_log_dir = args.output_log_dir
input_beacon_weight_file = args.input_beacon_weight_file
use_shrink_model = args.use_shrink_model
use_fixed_input_mean_std = args.use_fixed_input_mean_std
use_augmentation_beacon = args.use_augmentation_beacon
posenet_config.epochs = args.epochs
posenet_config.lstm_batch_size = args.batch_size
print "epochs : " + str(posenet_config.epochs)
print "batch size : " + str(posenet_config.lstm_batch_size)
print "use shrink model for training : " + str(use_shrink_model)
print "use fixed input mean and std : " + str(use_fixed_input_mean_std)
print "use beacon data augmentation : " + str(use_augmentation_beacon)
if input_beacon_weight_file is None:
print "please specify one of initial weight or restore directory"
sys.exit()
# parse beacon setting file
beaconmap = IBeaconUtils.parseBeaconSetting(input_beacon_setting_file)
beacon_num = len(beaconmap.keys())
output_numpy_mean_beacon_file = os.path.join(output_model_dir,
"mean_beacon.npy")
output_numpy_model_file = os.path.join(output_model_dir, "model.npy")
output_model_file = os.path.join(output_model_dir, "model.ckpt")
datasource, mean_beacon = posenet_data_utils.get_beacon_data(
input_txt_file, beaconmap, beacon_num, use_fixed_input_mean_std,
use_augmentation_beacon)
if use_fixed_input_mean_std:
print("Skip save mean beacon")
else:
with open(output_numpy_mean_beacon_file, 'wb') as fw:
np.save(fw, mean_beacon)
print("Save mean beacon at: " + output_numpy_mean_beacon_file)
# Set GPU options
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.4)
session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
KTF.set_session(session)
# Train model
s_x = K.variable(value=0.0)
s_q = K.variable(value=-3.0)
if use_shrink_model:
model = posenet_beacon_no_inception_shrink_lstm_keras.create_posenet(
beacon_num, input_beacon_weight_file)
else:
print "Do not shrink model is not supported"
sys.exit()
adam = Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, epsilon=0.00000001)
euc_loss3x_s = posenet_homoscedastic_loss.euc_loss3x_s(s_x=s_x)
euc_loss3q_s = posenet_homoscedastic_loss.euc_loss3q_s(s_q=s_q)
model.compile(optimizer=adam,
loss={
'beacon_lstm_pose_xyz': euc_loss3x_s,
'beacon_lstm_pose_wpqr': euc_loss3q_s
})
model.summary()
# Setup checkpointing
checkpointer = ModelCheckpoint(filepath=os.path.join(
output_model_dir, "checkpoint_weights.h5"),
verbose=1,
save_weights_only=True,
period=1)
# Save Tensorboard log
logger = TensorBoard(log_dir=output_log_dir,
histogram_freq=0,
write_graph=True)
# Adjust Epoch size depending on beacon data augmentation
if use_augmentation_beacon:
posenet_config.epochs = posenet_config.epochs / posenet_config.num_beacon_augmentation
steps_per_epoch = int(
len(datasource.poses_index) / float(posenet_config.lstm_batch_size))
num_iterations = steps_per_epoch * posenet_config.epochs
print("Number of epochs : " + str(posenet_config.epochs))
print("Number of training data : " + str(len(datasource.poses_index)))
print("Number of iterations : " + str(num_iterations))
history = model.fit_generator(
posenet_data_utils.gen_beacon_lstm_data_batch(datasource),
steps_per_epoch=steps_per_epoch,
epochs=posenet_config.epochs,
callbacks=[checkpointer, logger])
model.save_weights(os.path.join(output_model_dir, "trained_weights.h5"))
def main():
global base_model
description = 'This script is for testing posenet'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('input_txt_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path of input txt file in Cambridge Visual Landmark Dataset format.')
parser.add_argument('input_beacon_setting_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path where beacon setting file is saved.')
parser.add_argument('input_model_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where input model is saved.')
parser.add_argument('result_log_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where localization result files are saved.')
parser.add_argument('-s', '--use_shrink_model', action='store_true', default=False, \
help='Use shrink model (default: False)')
parser.add_argument('-f', '--use_fixed_input_mean_std', action='store_true', default=False, \
help='Use fixed input mean and std (default: False)')
parser.add_argument('-m', '--base_model', action='store', type=str, default=base_model, \
help='Base model : inception-v1/inception-v3/mobilenet-v1 (Default : ' + str(base_model))
args = parser.parse_args()
input_txt_file = args.input_txt_file
input_beacon_setting_file = args.input_beacon_setting_file
input_model_dir = args.input_model_dir
result_log_dir = args.result_log_dir
use_shrink_model = args.use_shrink_model
use_fixed_input_mean_std = args.use_fixed_input_mean_std
base_model = args.base_model
print "base model : " + str(base_model)
print "use shrink model for training : " + str(use_shrink_model)
print "use fixed input mean and std : " + str(use_fixed_input_mean_std)
if base_model != "inception-v1" and base_model != "inception-v3" and base_model != "mobilenet-v1":
print "invalid base model : " + base_model
sys.exit()
input_image_dir = os.path.dirname(input_txt_file)
input_numpy_mean_image_file = os.path.join(input_model_dir,
"mean_image.npy")
if use_fixed_input_mean_std:
input_numpy_mean_image = None
else:
input_numpy_mean_image = np.load(input_numpy_mean_image_file)
input_numpy_mean_beacon_file = os.path.join(input_model_dir,
"mean_beacon.npy")
if use_fixed_input_mean_std:
input_numpy_mean_beacon = None
else:
input_numpy_mean_beacon = np.load(input_numpy_mean_beacon_file)
output_localize_txt_file = os.path.join(result_log_dir,
"localize-poses.txt")
output_localize_json_file = os.path.join(result_log_dir,
"localize-poses.json")
output_summary_log_file = os.path.join(result_log_dir, "summary-log.txt")
output_hist_log_file = os.path.join(result_log_dir, "hist-log.txt")
output_detail_log_file = os.path.join(result_log_dir, "detail-log.txt")
# parse beacon setting file
beaconmap = IBeaconUtils.parseBeaconSetting(input_beacon_setting_file)
beacon_num = len(beaconmap.keys())
if base_model == "inception-v1":
image_size = 224
output_auxiliary = True
elif base_model == "inception-v3":
image_size = 299
output_auxiliary = False
elif base_model == "mobilenet-v1":
image_size = 224
output_auxiliary = False
else:
print "invalid base model : " + base_model
sys.exit()
datasource, image_filenames = get_data(input_txt_file, input_image_dir,
input_numpy_mean_image, beaconmap,
input_numpy_mean_beacon,
use_fixed_input_mean_std)
predicted_poses = np.zeros((len(datasource.beacons), 7))
groundtruth_poses = np.zeros((len(datasource.beacons), 7))
results = np.zeros((len(datasource.beacons), 2))
# Set GPU options
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.4)
session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
KTF.set_session(session)
# load model
if use_shrink_model:
if base_model == "inception-v1":
model = posenet_image_beacon_no_inception_shrink_keras.create_posenet_inception_v1(
beacon_num)
elif base_model == "inception-v3":
model = posenet_image_beacon_no_inception_shrink_keras.create_posenet_inception_v3(
beacon_num)
elif base_model == "mobilenet-v1":
model = posenet_image_beacon_no_inception_shrink_keras.create_posenet_mobilenet_v1(
beacon_num)
else:
print "invalid base model : " + base_model
sys.exit()
else:
print "Do not shrink model is not supported"
sys.exit()
model.load_weights(os.path.join(input_model_dir, 'trained_weights.h5'))
model.summary()
time_array = np.array([])
for i in range(len(datasource.image_filenames)):
np_images = posenet_image_utils.preprocess_test_image(
datasource.image_filenames[i],
input_numpy_mean_image,
use_fixed_input_mean_std,
1,
False,
image_size=image_size)
np_beacon = datasource.beacons[i]
pose_q = np.asarray(datasource.poses[i][3:7])
pose_x = np.asarray(datasource.poses[i][0:3])
start_time = time.time()
sample_predicted = model.predict([np_images, np_beacon])
if output_auxiliary:
# 0-3 are results for auxiliary outputs
sample_predicted_x = sample_predicted[4]
sample_predicted_q = sample_predicted[5]
else:
sample_predicted_x = sample_predicted[0]
sample_predicted_q = sample_predicted[1]
elapsed_time = time.time() - start_time
time_array = np.append(time_array, elapsed_time)
pose_q = np.squeeze(pose_q)
pose_x = np.squeeze(pose_x)
predicted_q = np.squeeze(sample_predicted_q)
predicted_x = np.squeeze(sample_predicted_x)
predicted_poses[i, 0] = predicted_x[0]
predicted_poses[i, 1] = predicted_x[1]
predicted_poses[i, 2] = predicted_x[2]
predicted_poses[i, 3] = predicted_q[0]
predicted_poses[i, 4] = predicted_q[1]
predicted_poses[i, 5] = predicted_q[2]
predicted_poses[i, 6] = predicted_q[3]
groundtruth_poses[i, 0] = pose_x[0]
groundtruth_poses[i, 1] = pose_x[1]
groundtruth_poses[i, 2] = pose_x[2]
groundtruth_poses[i, 3] = pose_q[0]
groundtruth_poses[i, 4] = pose_q[1]
groundtruth_poses[i, 5] = pose_q[2]
groundtruth_poses[i, 6] = pose_q[3]
# calculate error
q1 = pose_q / np.linalg.norm(pose_q)
q2 = predicted_q / np.linalg.norm(predicted_q)
d = abs(np.sum(np.multiply(q1, q2)))
# fix floating point inaccuracy
if d < -1.0:
d = -1.0
if d > 1.0:
d = 1.0
theta = 2 * np.arccos(d) * 180 / math.pi
error_x = np.linalg.norm(pose_x - predicted_x)
results[i, :] = [error_x, theta]
print 'Index=', i, ' , Pos Error(m)=', error_x, ', Rot Error(degrees)=', theta
# write localize poses
with open(output_localize_txt_file, "w") as fw:
fw.write("Localization Data V1\n")
fw.write("ImageFile, Camera Position [X Y Z W P Q R]\n")
fw.write("\n")
for idx in range(len(datasource.beacons)):
fw.write(
str(idx) + " " +
' '.join(['%f' % p for p in predicted_poses[idx, :]]) + "\n")
locJsonObj = {}
locJsonObj["locGlobal"] = []
for idx, pose in enumerate(predicted_poses):
Rh = transformations.quaternion_matrix(
[pose[3], pose[4], pose[5], pose[6]])
groundtruth_pose = groundtruth_poses[idx]
groundtruth_Rh = transformations.quaternion_matrix([
groundtruth_pose[3], groundtruth_pose[4], groundtruth_pose[5],
groundtruth_pose[6]
])
jsonLoc = {}
jsonLoc["beacon_idx"] = idx
jsonLoc["t"] = [pose[0], pose[1], pose[2]]
jsonLoc["R"] = Rh[0:3, 0:3].tolist()
jsonLoc["groundtruth"] = [
groundtruth_pose[0], groundtruth_pose[1], groundtruth_pose[2]
]
jsonLoc["groundtruthR"] = groundtruth_Rh[0:3, 0:3].tolist()
locJsonObj["locGlobal"].append(jsonLoc)
with open(output_localize_json_file, "w") as fw:
json.dump(locJsonObj, fw)
# write histgram results
bin_edge = [0.01 * float(x) for x in range(0, 1001)]
dist_errors = results[:, 0]
dist_hist, dist_hist_bins = np.histogram(dist_errors, bins=bin_edge)
dist_hist_cum_ratio = np.cumsum(dist_hist) / float(len(datasource.beacons))
print "Histogram of error: " + str(dist_hist)
print "Cumulative ratio of error: " + str(dist_hist_cum_ratio)
print "Total loc err larger than " + str(
np.max(bin_edge)) + " meters: " + str(
len(datasource.beacons) - np.sum(dist_hist))
# write summary of results
mean_result = np.mean(results, axis=0)
std_result = np.std(results, axis=0)
median_result = np.median(results, axis=0)
max_result = np.max(results, axis=0)
percentile_80_result = np.percentile(results, 80, axis=0)
percentile_90_result = np.percentile(results, 90, axis=0)
percentile_95_result = np.percentile(results, 95, axis=0)
print 'Mean error ', mean_result[0], 'm and ', mean_result[1], 'degrees.'
print 'StdDev error ', std_result[0], 'm and ', std_result[1], 'degrees.'
print 'Median error ', median_result[0], 'm and ', median_result[
1], 'degrees.'
print 'Max error ', max_result[0], 'm and ', max_result[1], 'degrees.'
print '80 percentile error ', percentile_80_result[
0], 'm and ', percentile_80_result[1], 'degrees.'
print '90 percentile error ', percentile_90_result[
0], 'm and ', percentile_90_result[1], 'degrees.'
print '95 percentile error ', percentile_95_result[
0], 'm and ', percentile_95_result[1], 'degrees.'
print 'Mean time ', str(np.average(time_array))
print 'StdDev time ', str(np.std(time_array))
print 'Median time ', str(np.median(time_array))
with open(output_summary_log_file, "w") as fw:
fw.write("Number of test image = " + str(len(datasource.beacons)) +
"\n")
fw.write("Mean error = " + str(mean_result[0]) + " meters." + "\n")
fw.write("StdDev error = " + str(std_result[0]) + " meters." + "\n")
fw.write("Median error = " + str(median_result[0]) + " meters." + "\n")
fw.write("Max error = " + str(max_result[0]) + " meters." + "\n")
fw.write("80 percentile error = " + str(percentile_80_result[0]) +
" meters." + "\n")
fw.write("90 percentile error = " + str(percentile_90_result[0]) +
" meters." + "\n")
fw.write("95 percentile error = " + str(percentile_95_result[0]) +
" meters." + "\n")
fw.write("\n")
fw.write("Mean error = " + str(mean_result[1]) + " degrees." + "\n")
fw.write("StdDev error = " + str(std_result[1]) + " degrees." + "\n")
fw.write("Median error = " + str(median_result[1]) + " degrees." +
"\n")
fw.write("Max error = " + str(max_result[1]) + " degrees." + "\n")
fw.write("80 percentile error = " + str(percentile_80_result[1]) +
" degrees." + "\n")
fw.write("90 percentile error = " + str(percentile_90_result[1]) +
" degrees." + "\n")
fw.write("95 percentile error = " + str(percentile_95_result[1]) +
" degrees." + "\n")
fw.write("\n")
fw.write("Histogram of error: " + str(dist_hist) + "\n")
fw.write("Cumulative ratio: " + str(
np.around(
np.cumsum(dist_hist, dtype=float) /
len(datasource.beacons), 2)) + "\n")
fw.write("Total loc err larger than " + str(np.max(bin_edge)) +
" meters: " +
str(len(datasource.beacons) - np.sum(dist_hist)) + "\n")
fw.write("\n")
fw.write("Mean time = " + str(np.average(time_array)) + "\n")
fw.write("StdDev time = " + str(np.std(time_array)) + "\n")
fw.write("Median time = " + str(np.median(time_array)) + "\n")
# write error histgram
np.savetxt(output_hist_log_file,
zip(dist_hist_bins, dist_hist_cum_ratio),
delimiter=',')
# write error histgram
np.savetxt(output_hist_log_file,
zip(dist_hist_bins, dist_hist_cum_ratio),
delimiter=',')
# write detail results
with open(output_detail_log_file, "w") as fw:
for idx in range(len(datasource.beacons)):
fw.write(
str(idx) + "," + str(results[idx, 0]) + "," +
str(results[idx, 1]) + "\n")
def main():
global output_pos_layer_name
global output_rot_layer_name
description = 'This script is for testing posenet'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('input_txt_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path of input txt file in Cambridge Visual Landmark Dataset format.')
parser.add_argument('input_beacon_setting_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path where beacon setting file is saved.')
parser.add_argument('input_pb_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path of model pb file.')
parser.add_argument('result_log_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where localization result files are saved.')
parser.add_argument('-f', '--use_fixed_input_mean_std', action='store_true', default=False, \
help='Use fixed input mean and std (default: False)')
parser.add_argument('-m', '--base_model', action='store', type=str, default=posenet_config.base_model, \
help='Base model : inception-v1/inception-v3/mobilenet-v1 (Default : ' + str(posenet_config.base_model))
args = parser.parse_args()
input_txt_file = args.input_txt_file
input_beacon_setting_file = args.input_beacon_setting_file
input_pb_file = args.input_pb_file
result_log_dir = args.result_log_dir
use_fixed_input_mean_std = args.use_fixed_input_mean_std
posenet_config.base_model = args.base_model
print "base model : " + str(posenet_config.base_model)
# you can check output node name by tensorflow/tools/graph_transforms::summarize_graph
# https://github.com/tensorflow/models/tree/master/research/slim#Export
if posenet_config.base_model=="inception-v1":
output_pos_layer_name = "image_beacon_cls3_fc_pose_xyz/BiasAdd"
output_rot_layer_name = "image_beacon_cls3_fc_pose_wpqr/BiasAdd"
elif posenet_config.base_model=="inception-v3" or posenet_config.base_model=="mobilenet-v1":
output_pos_layer_name = "image_beacon_cls_fc_pose_xyz/BiasAdd"
output_rot_layer_name = "image_beacon_cls_fc_pose_wpqr/BiasAdd"
else:
print "invalid base model : " + posenet_config.base_model
sys.exit()
input_image_dir = os.path.dirname(input_txt_file)
input_model_dir = os.path.dirname(input_pb_file)
input_numpy_mean_image_file = os.path.join(input_model_dir, "mean_image.npy")
if use_fixed_input_mean_std:
input_numpy_mean_image = None
else:
input_numpy_mean_image = np.load(input_numpy_mean_image_file)
input_numpy_mean_beacon_file = os.path.join(input_model_dir, "mean_beacon.npy")
if use_fixed_input_mean_std:
input_numpy_mean_beacon = None
else:
input_numpy_mean_beacon = np.load(input_numpy_mean_beacon_file)
output_localize_txt_file = os.path.join(result_log_dir, "localize-poses.txt")
output_localize_json_file = os.path.join(result_log_dir, "localize-poses.json")
output_summary_log_file = os.path.join(result_log_dir, "summary-log.txt")
output_hist_log_file = os.path.join(result_log_dir, "hist-log.txt")
output_detail_log_file = os.path.join(result_log_dir, "detail-log.txt")
# parse beacon setting file
beaconmap = IBeaconUtils.parseBeaconSetting(input_beacon_setting_file)
beacon_num = len(beaconmap.keys())
image = tf.placeholder(tf.float32, [1, 224, 224, 3])
beacons = tf.placeholder(tf.float32, [1, beacon_num, 1, 1])
datasource, image_filenames = get_data(input_txt_file, input_image_dir, input_numpy_mean_image, beaconmap, input_numpy_mean_beacon, use_fixed_input_mean_std)
predicted_poses = np.zeros((len(datasource.images),7))
groundtruth_poses = np.zeros((len(datasource.images),7))
results = np.zeros((len(datasource.images),2))
# Set GPU options
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.4)
time_array = np.array([])
# Load model
graph = load_graph(input_pb_file)
input_image_name = "import/" + input_image_layer_name
input_beacon_name = "import/" + input_beacon_layer_name
output_pos_name = "import/" + output_pos_layer_name
output_rot_name = "import/" + output_rot_layer_name
input_image_operation = graph.get_operation_by_name(input_image_name)
input_beacon_operation = graph.get_operation_by_name(input_beacon_name)
output_pos_operation = graph.get_operation_by_name(output_pos_name)
output_rot_operation = graph.get_operation_by_name(output_rot_name)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options), graph=graph) as sess:
for i in range(len(datasource.images)):
np_image = datasource.images[i]
np_beacon = datasource.beacons[i]
feed = {input_image_operation.outputs[0]: np_image, input_beacon_operation.outputs[0]: np_beacon}
pose_q= np.asarray(datasource.poses[i][3:7])
pose_x= np.asarray(datasource.poses[i][0:3])
start_time = time.time()
predicted_x, predicted_q = sess.run([output_pos_operation.outputs[0],
output_rot_operation.outputs[0]], feed_dict=feed)
elapsed_time = time.time() - start_time
time_array = np.append(time_array, elapsed_time)
pose_q = np.squeeze(pose_q)
pose_x = np.squeeze(pose_x)
predicted_q = np.squeeze(predicted_q)
predicted_x = np.squeeze(predicted_x)
predicted_poses[i,0] = predicted_x[0]
predicted_poses[i,1] = predicted_x[1]
predicted_poses[i,2] = predicted_x[2]
predicted_poses[i,3] = predicted_q[0]
predicted_poses[i,4] = predicted_q[1]
predicted_poses[i,5] = predicted_q[2]
predicted_poses[i,6] = predicted_q[3]
groundtruth_poses[i,0] = pose_x[0]
groundtruth_poses[i,1] = pose_x[1]
groundtruth_poses[i,2] = pose_x[2]
groundtruth_poses[i,3] = pose_q[0]
groundtruth_poses[i,4] = pose_q[1]
groundtruth_poses[i,5] = pose_q[2]
groundtruth_poses[i,6] = pose_q[3]
# calculate error
q1 = pose_q / np.linalg.norm(pose_q)
q2 = predicted_q / np.linalg.norm(predicted_q)
d = abs(np.sum(np.multiply(q1,q2)))
# fix floating point inaccuracy
if d<-1.0:
d = -1.0
if d>1.0:
d = 1.0
theta = 2 * np.arccos(d) * 180/math.pi
error_x = np.linalg.norm(pose_x-predicted_x)
results[i,:] = [error_x,theta]
print 'Index=', i, ' , Pos Error(m)=', error_x, ', Rot Error(degrees)=', theta
# write localize poses
with open(output_localize_txt_file, "w") as fw:
fw.write("Localization Data V1\n")
fw.write("ImageFile, Camera Position [X Y Z W P Q R]\n")
fw.write("\n")
for idx, filename in enumerate(image_filenames):
fw.write(os.path.basename(filename) + " " + ' '.join(['%f' % p for p in predicted_poses[idx,:]]) + "\n")
locJsonObj = {}
locJsonObj["locGlobal"] = []
for idx, pose in enumerate(predicted_poses):
Rh = transformations.quaternion_matrix([pose[3], pose[4], pose[5], pose[6]])
groundtruth_pose = groundtruth_poses[idx]
groundtruth_Rh = transformations.quaternion_matrix([groundtruth_pose[3], groundtruth_pose[4], groundtruth_pose[5], groundtruth_pose[6]])
jsonLoc = {}
jsonLoc["filename"] = os.path.basename(image_filenames[idx])
jsonLoc["t"] = [pose[0], pose[1], pose[2]]
jsonLoc["R"] = Rh[0:3,0:3].tolist()
jsonLoc["groundtruth"] = [groundtruth_pose[0], groundtruth_pose[1], groundtruth_pose[2]]
jsonLoc["groundtruthR"] = groundtruth_Rh[0:3,0:3].tolist()
locJsonObj["locGlobal"].append(jsonLoc)
with open(output_localize_json_file, "w") as fw:
json.dump(locJsonObj, fw)
# write histgram results
bin_edge = [0.01*float(x) for x in range(0,1001)]
dist_errors = results[:,0]
dist_hist, dist_hist_bins = np.histogram(dist_errors, bins=bin_edge)
dist_hist_cum_ratio = np.cumsum(dist_hist) / float(len(datasource.images))
print "Histogram of error: " + str(dist_hist)
print "Cumulative ratio of error: " + str(dist_hist_cum_ratio)
print "Total loc err larger than " + str(np.max(bin_edge)) + " meters: " + str(len(datasource.images)-np.sum(dist_hist))
# write summary of results
mean_result = np.mean(results,axis=0)
std_result = np.std(results,axis=0)
median_result = np.median(results,axis=0)
max_result = np.max(results,axis=0)
percentile_80_result = np.percentile(results,80,axis=0)
percentile_90_result = np.percentile(results,90,axis=0)
percentile_95_result = np.percentile(results,95,axis=0)
print 'Mean error ', mean_result[0], 'm and ', mean_result[1], 'degrees.'
print 'StdDev error ', std_result[0], 'm and ', std_result[1], 'degrees.'
print 'Median error ', median_result[0], 'm and ', median_result[1], 'degrees.'
print 'Max error ', max_result[0], 'm and ', max_result[1], 'degrees.'
print '80 percentile error ', percentile_80_result[0], 'm and ', percentile_80_result[1], 'degrees.'
print '90 percentile error ', percentile_90_result[0], 'm and ', percentile_90_result[1], 'degrees.'
print '95 percentile error ', percentile_95_result[0], 'm and ', percentile_95_result[1], 'degrees.'
print 'Mean time ', str(np.average(time_array))
print 'StdDev time ', str(np.std(time_array))
print 'Median time ', str(np.median(time_array))
with open(output_summary_log_file, "w") as fw:
fw.write("Number of test image = " + str(len(datasource.images)) + "\n")
fw.write("Mean error = " + str(mean_result[0]) + " meters." + "\n")
fw.write("StdDev error = " + str(std_result[0]) + " meters." + "\n")
fw.write("Median error = " + str(median_result[0]) + " meters." + "\n")
fw.write("Max error = " + str(max_result[0]) + " meters." + "\n")
fw.write("80 percentile error = " + str(percentile_80_result[0]) + " meters." + "\n")
fw.write("90 percentile error = " + str(percentile_90_result[0]) + " meters." + "\n")
fw.write("95 percentile error = " + str(percentile_95_result[0]) + " meters." + "\n")
fw.write("\n")
fw.write("Mean error = " + str(mean_result[1]) + " degrees." + "\n")
fw.write("StdDev error = " + str(std_result[1]) + " degrees." + "\n")
fw.write("Median error = " + str(median_result[1]) + " degrees." + "\n")
fw.write("Max error = " + str(max_result[1]) + " degrees." + "\n")
fw.write("80 percentile error = " + str(percentile_80_result[1]) + " degrees." + "\n")
fw.write("90 percentile error = " + str(percentile_90_result[1]) + " degrees." + "\n")
fw.write("95 percentile error = " + str(percentile_95_result[1]) + " degrees." + "\n")
fw.write("\n")
fw.write("Histogram of error: " + str(dist_hist) + "\n")
fw.write("Cumulative ratio: " + str(np.around(np.cumsum(dist_hist,dtype=float)/len(datasource.images),2)) + "\n")
fw.write("Total loc err larger than " + str(np.max(bin_edge)) + " meters: " + str(len(datasource.images)-np.sum(dist_hist)) + "\n")
fw.write("\n")
fw.write("Mean time = " + str(np.average(time_array)) + "\n")
fw.write("StdDev time = " + str(np.std(time_array)) + "\n")
fw.write("Median time = " + str(np.median(time_array)) + "\n")
# write error histgram
np.savetxt(output_hist_log_file, zip(dist_hist_bins, dist_hist_cum_ratio), delimiter=',')
# write error histgram
np.savetxt(output_hist_log_file, zip(dist_hist_bins, dist_hist_cum_ratio), delimiter=',')
# write detail results
with open(output_detail_log_file, "w") as fw:
for idx, filename in enumerate(image_filenames):
fw.write(os.path.basename(filename) + "," + str(results[idx,0]) + "," + str(results[idx,1]) + "\n")
def main():
description = 'This script is for merging multiple SfM output models to one SfM model.' + \
'Please prepare multiple OpenMVG projects which have output SfM models, and matrix to convert to global coordinate.'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('input_csv', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Input CSV file which lists OpenMVG projects which will be merged.')
parser.add_argument('output_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Output directory path where merged model will be saved.')
args = parser.parse_args()
input_csv = args.input_csv
output_dir = args.output_dir
# load reconstruct parameters
reconstructParam = ReconstructParam.ReconstructParam
reconstructIBeaconParam = ReconstructIBeaconParam.ReconstructIBeaconParam
# read projects list
projectList = []
with open(input_csv, "r") as f:
reader = csv.reader(f)
for row in reader:
project = {}
project["dir"] = row[0]
project["sfm_data"] = row[1]
project["A"] = row[2]
projectList.append(project)
# copy source files to output directory
for project in projectList:
copyOriginalFiles(project["dir"], output_dir)
# load beacon settings
mergeBeaconmap = None
for project in projectList:
beacon_file = os.path.join(project["dir"], "Input", "listbeacon.txt")
if os.path.exists(beacon_file):
beaconmap = iBeaconUtils.parseBeaconSetting(beacon_file)
if mergeBeaconmap is None:
mergeBeaconmap = beaconmap
else:
if mergeBeaconmap!=beaconmap:
print "invalid find listbeacon.txt for project data : " + project["dir"]
print "listbeacon.txt should be same for all project data"
sys.exit()
else:
print "valid listbeacon.txt for project data : " + project["dir"]
# prepare output directory
if not os.path.isdir(os.path.join(output_dir,"Ref")):
FileUtils.makedir(os.path.join(output_dir,"Ref"))
if not os.path.isdir(os.path.join(output_dir,"Ref","loc")):
FileUtils.makedir(os.path.join(output_dir,"Ref","loc"))
if not os.path.isdir(os.path.join(output_dir,"Output","SfM")):
FileUtils.makedir(os.path.join(output_dir,"Output","SfM"))
if not os.path.isdir(os.path.join(output_dir,"Output","SfM","reconstruction")):
FileUtils.makedir(os.path.join(output_dir,"Output","SfM","reconstruction"))
if not os.path.isdir(os.path.join(output_dir,"Output","SfM","reconstruction","global")):
FileUtils.makedir(os.path.join(output_dir,"Output","SfM","reconstruction","global"))
sfmDataList = []
for project in projectList:
if not os.path.exists(project["sfm_data"]):
print "cannot find sfm data : " + project["sfm_data"]
sys.exit()
with open(project["sfm_data"]) as jsonFile:
sfmDataList.append(json.load(jsonFile))
AList = []
for project in projectList:
AList.append(np.loadtxt(project["A"]))
print "load mat : " + project["A"]
print (np.loadtxt(project["A"]))
print "Load 3D points"
pointIdList = []
pointList = []
for sfmData in sfmDataList:
pointId, point = mergeSfM.getAll3DPointloc(sfmData)
pointn = np.asarray(point, dtype=np.float).T
pointIdList.append(pointId)
pointList.append(pointn)
# merge models
mergeSfmData = None
mergePointId = None
mergePointn = None
for idx in range(0, len(sfmDataList)):
if idx==0:
mergeSfmData = sfmDataList[0]
mergeSfM.transform_sfm_data(mergeSfmData, AList[0])
else:
mergePointThres = mergeSfM.findMedianStructurePointsThres(mergeSfmData, reconstructParam.mergePointThresMul)
print "thres to merge 3D points : " + str(mergePointThres)
inlierMap = findInliersByKnownTransform(mergePointId, pointIdList[idx], mergePointn, pointList[idx], AList[idx], mergePointThres)
print "number of points in base model : " + str(len(mergePointn[0]))
print "number of points in model " + str(idx) + " : " + str(len(pointList[idx]))
print "number of inliers : " + str(len(inlierMap))
mergeSfM.merge_sfm_data(mergeSfmData, sfmDataList[idx], AList[idx], {x[0]: x[1] for x in inlierMap})
mergePointId, mergePoint = mergeSfM.getAll3DPointloc(mergeSfmData)
mergePointn = np.asarray(mergePoint, dtype=np.float).T
# go back to coordinate of the first model
_invA = np.linalg.inv(AList[0][0:3,0:3])
invA = np.c_[_invA, -np.dot(_invA,AList[0][:,3])]
mergeSfM.transform_sfm_data(mergeSfmData, invA)
mergeSfmData["root_path"] = os.path.join(output_dir,"Input","inputImg")
resultSfMDataFile = os.path.join(output_dir,"Output","SfM","reconstruction","global","sfm_data.json")
with open(resultSfMDataFile,"w") as jsonfile:
json.dump(mergeSfmData, jsonfile)
# write new beacon file
if mergeBeaconmap is not None:
iBeaconUtils.exportBeaconDataForSfmImageFrames(os.path.join(output_dir,"Input","csv"), resultSfMDataFile,
os.path.join(output_dir,"Input","listbeacon.txt"),
os.path.join(output_dir,"Output","SfM","reconstruction","global","beacon.txt"),
reconstructIBeaconParam.normApproach)
'''
os.system(reconstructParam.BUNDLE_ADJUSTMENT_PROJECT_PATH + " " + resultSfMDataFile + " " + resultSfMDataFile)
'''
os.system(reconstructParam.BUNDLE_ADJUSTMENT_PROJECT_PATH + " " + resultSfMDataFile + " " + resultSfMDataFile + \
" -c=" + "rst,rsti" + " -r=" + "1")
Amat = AList[0]
with open(os.path.join(output_dir,"Ref","Amat.txt"),"w") as AmatFile:
np.savetxt(AmatFile,Amat)
FileUtils.convertNumpyMatTxt2OpenCvMatYml(os.path.join(output_dir,"Ref","Amat.txt"), os.path.join(output_dir,"Ref","Amat.yml"), "A")
# To create same directory structure before merging, create sfm_data.json without structure information in matches directory
with open(resultSfMDataFile) as fpr:
sfmData = json.load(fpr)
sfmData["extrinsics"] = []
sfmData["control_points"] = []
sfmData["structure"] = []
with open(os.path.join(output_dir,"Output","matches","sfm_data.json"),"w") as fpw:
json.dump(sfmData, fpw)
print "Execute : " + reconstructParam.WORKSPACE_DIR + "/TrainBoW/Release/TrainBoW " + os.path.join(output_dir,"Output") + " " + \
os.path.join(output_dir,"Output", "matches", "BOWfile.yml") + " -p=" + os.path.join(output_dir,"Output", "matches", "PCAfile.yml")
os.system(reconstructParam.WORKSPACE_DIR + "/TrainBoW/Release/TrainBoW " + os.path.join(output_dir,"Output") + " " + \
os.path.join(output_dir,"Output", "matches", "BOWfile.yml") + " -p=" + os.path.join(output_dir,"Output", "matches", "PCAfile.yml"))
os.system("openMVG_main_ComputeSfM_DataColor -i " + resultSfMDataFile + \
" -o " + os.path.join(output_dir,"Output","SfM","reconstruction","global","colorized.ply"))
def main():
description = 'This script is for testing posenet'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('input_txt_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path of input txt file in Cambridge Visual Landmark Dataset format.')
parser.add_argument('input_beacon_setting_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path where beacon setting file is saved.')
parser.add_argument('input_pb_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path of model pb file.')
parser.add_argument('result_log_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where localization result files are saved.')
parser.add_argument('-f', '--use_fixed_input_mean_std', action='store_true', default=False, \
help='Use fixed input mean and std (default: False)')
args = parser.parse_args()
input_txt_file = args.input_txt_file
input_beacon_setting_file = args.input_beacon_setting_file
input_pb_file = args.input_pb_file
result_log_dir = args.result_log_dir
use_fixed_input_mean_std = args.use_fixed_input_mean_std
input_model_dir = os.path.dirname(input_pb_file)
input_numpy_mean_beacon_file = os.path.join(input_model_dir,
"mean_beacon.npy")
if use_fixed_input_mean_std:
input_numpy_mean_beacon = None
else:
input_numpy_mean_beacon = np.load(input_numpy_mean_beacon_file)
output_summary_log_file = os.path.join(result_log_dir, "summary-log.txt")
output_hist_log_file = os.path.join(result_log_dir, "hist-log.txt")
# parse beacon setting file
beaconmap = IBeaconUtils.parseBeaconSetting(input_beacon_setting_file)
beacon_num = len(beaconmap.keys())
beacons = tf.placeholder(tf.float32, [1, beacon_num, 1, 1])
datasource = get_data(input_txt_file, beaconmap, input_numpy_mean_beacon,
use_fixed_input_mean_std)
results = np.zeros((len(datasource.beacons), 2))
# Set GPU options
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.4)
time_array = np.array([])
# Load model
graph = load_graph(input_pb_file)
input_beacon_name = "import/" + input_beacon_layer_name
output_pos_name = "import/" + output_pos_layer_name
output_rot_name = "import/" + output_rot_layer_name
input_operation = graph.get_operation_by_name(input_beacon_name)
output_pos_operation = graph.get_operation_by_name(output_pos_name)
output_rot_operation = graph.get_operation_by_name(output_rot_name)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options),
graph=graph) as sess:
for i in range(len(datasource.beacons)):
np_beacon = datasource.beacons[i]
feed = {input_operation.outputs[0]: np_beacon}
pose_q = np.asarray(datasource.poses[i][3:7])
pose_x = np.asarray(datasource.poses[i][0:3])
start_time = time.time()
predicted_x, predicted_q = sess.run([
output_pos_operation.outputs[0],
output_rot_operation.outputs[0]
],
feed_dict=feed)
elapsed_time = time.time() - start_time
time_array = np.append(time_array, elapsed_time)
pose_q = np.squeeze(pose_q)
pose_x = np.squeeze(pose_x)
predicted_q = np.squeeze(predicted_q)
predicted_x = np.squeeze(predicted_x)
# calculate error
q1 = pose_q / np.linalg.norm(pose_q)
q2 = predicted_q / np.linalg.norm(predicted_q)
d = abs(np.sum(np.multiply(q1, q2)))
# fix floating point inaccuracy
if d < -1.0:
d = -1.0
if d > 1.0:
d = 1.0
theta = 2 * np.arccos(d) * 180 / math.pi
error_x = np.linalg.norm(pose_x - predicted_x)
results[i, :] = [error_x, theta]
print 'Index=', i, ' , Pos Error(m)=', error_x, ', Rot Error(degrees)=', theta
# write histgram results
bin_edge = [0.01 * float(x) for x in range(0, 1001)]
dist_errors = results[:, 0]
dist_hist, dist_hist_bins = np.histogram(dist_errors, bins=bin_edge)
dist_hist_cum_ratio = np.cumsum(dist_hist) / float(len(datasource.beacons))
print "Histogram of error: " + str(dist_hist)
print "Cumulative ratio of error: " + str(dist_hist_cum_ratio)
print "Total loc err larger than " + str(
np.max(bin_edge)) + " meters: " + str(
len(datasource.beacons) - np.sum(dist_hist))
# write summary of results
mean_result = np.mean(results, axis=0)
std_result = np.std(results, axis=0)
median_result = np.median(results, axis=0)
max_result = np.max(results, axis=0)
percentile_80_result = np.percentile(results, 80, axis=0)
percentile_90_result = np.percentile(results, 90, axis=0)
percentile_95_result = np.percentile(results, 95, axis=0)
print 'Mean error ', mean_result[0], 'm and ', mean_result[1], 'degrees.'
print 'StdDev error ', std_result[0], 'm and ', std_result[1], 'degrees.'
print 'Median error ', median_result[0], 'm and ', median_result[
1], 'degrees.'
print 'Max error ', max_result[0], 'm and ', max_result[1], 'degrees.'
print '80 percentile error ', percentile_80_result[
0], 'm and ', percentile_80_result[1], 'degrees.'
print '90 percentile error ', percentile_90_result[
0], 'm and ', percentile_90_result[1], 'degrees.'
print '95 percentile error ', percentile_95_result[
0], 'm and ', percentile_95_result[1], 'degrees.'
print 'Mean time ', str(np.average(time_array))
print 'StdDev time ', str(np.std(time_array))
print 'Median time ', str(np.median(time_array))
with open(output_summary_log_file, "w") as fw:
fw.write("Number of test image = " + str(len(datasource.beacons)) +
"\n")
fw.write("Mean error = " + str(mean_result[0]) + " meters." + "\n")
fw.write("StdDev error = " + str(std_result[0]) + " meters." + "\n")
fw.write("Median error = " + str(median_result[0]) + " meters." + "\n")
fw.write("Max error = " + str(max_result[0]) + " meters." + "\n")
fw.write("80 percentile error = " + str(percentile_80_result[0]) +
" meters." + "\n")
fw.write("90 percentile error = " + str(percentile_90_result[0]) +
" meters." + "\n")
fw.write("95 percentile error = " + str(percentile_95_result[0]) +
" meters." + "\n")
fw.write("\n")
fw.write("Mean error = " + str(mean_result[1]) + " degrees." + "\n")
fw.write("StdDev error = " + str(std_result[1]) + " degrees." + "\n")
fw.write("Median error = " + str(median_result[1]) + " degrees." +
"\n")
fw.write("Max error = " + str(max_result[1]) + " degrees." + "\n")
fw.write("80 percentile error = " + str(percentile_80_result[1]) +
" degrees." + "\n")
fw.write("90 percentile error = " + str(percentile_90_result[1]) +
" degrees." + "\n")
fw.write("95 percentile error = " + str(percentile_95_result[1]) +
" degrees." + "\n")
fw.write("\n")
fw.write("Histogram of error: " + str(dist_hist) + "\n")
fw.write("Cumulative ratio: " + str(
np.around(
np.cumsum(dist_hist, dtype=float) /
len(datasource.beacons), 2)) + "\n")
fw.write("Total loc err larger than " + str(np.max(bin_edge)) +
" meters: " +
str(len(datasource.beacons) - np.sum(dist_hist)) + "\n")
fw.write("\n")
fw.write("Mean time = " + str(np.average(time_array)) + "\n")
fw.write("StdDev time = " + str(np.std(time_array)) + "\n")
fw.write("Median time = " + str(np.median(time_array)) + "\n")
# write error histgram
np.savetxt(output_hist_log_file,
zip(dist_hist_bins, dist_hist_cum_ratio),
delimiter=',')
# write error histgram
np.savetxt(output_hist_log_file,
zip(dist_hist_bins, dist_hist_cum_ratio),
delimiter=',')
def main():
description = 'This script is for testing posenet'
parser = argparse.ArgumentParser(description=description)
parser.add_argument('input_txt_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path of input txt file in Cambridge Visual Landmark Dataset format.')
parser.add_argument('input_beacon_setting_file', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='File path where beacon setting file is saved.')
parser.add_argument('output_model_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where output models will be saved.')
parser.add_argument('output_log_dir', action='store', nargs=None, const=None, \
default=None, type=str, choices=None, metavar=None, \
help='Directory path where log files will be saved.')
parser.add_argument('-i', '--input_image_weight_file', action='store', type=str, default=None, \
help='File path image posenet weiht is stored in numpy format.')
parser.add_argument('-w', '--input_beacon_weight_file', action='store', type=str, default=None, \
help='File path beacon posenet weiht is stored in numpy format.')
parser.add_argument('-l', '--loss_beta', action='store', type=float, default=posenet_config.loss_beta, \
help='Beta for loss function (Default : ' + str(posenet_config.loss_beta))
parser.add_argument('-s', '--use_shrink_model', action='store_true', default=False, \
help='Use shrink model (default: False)')
parser.add_argument('-f', '--use_fixed_input_mean_std', action='store_true', default=False, \
help='Use fixed image mean and std (default: False)')
parser.add_argument('-a', '--use_augmentation_beacon', action='store_true', default=False, \
help='Use data augmentation for beacon data (default: False)')
parser.add_argument('-m', '--base_model', action='store', type=str, default=posenet_config.base_model, \
help='Base model : inception-v1/inception-v3/mobilenet-v1 (Default : ' + str(posenet_config.base_model))
parser.add_argument('-e', '--epochs', action='store', type=int, default=posenet_config.epochs, \
help='Epochs (Default : ' + str(posenet_config.epochs))
parser.add_argument('-b', '--batch_size', action='store', type=int, default=posenet_config.batch_size, \
help='Batch size (Default : ' + str(posenet_config.batch_size))
args = parser.parse_args()
input_txt_file = args.input_txt_file
input_beacon_setting_file = args.input_beacon_setting_file
output_model_dir = args.output_model_dir
output_log_dir = args.output_log_dir
input_image_weight_file = args.input_image_weight_file
input_beacon_weight_file = args.input_beacon_weight_file
posenet_config.loss_beta = args.loss_beta
use_shrink_model = args.use_shrink_model
use_fixed_input_mean_std = args.use_fixed_input_mean_std
use_augmentation_beacon = args.use_augmentation_beacon
posenet_config.base_model = args.base_model
posenet_config.epochs = args.epochs
posenet_config.batch_size = args.batch_size
print "base model : " + str(posenet_config.base_model)
print "epochs : " + str(posenet_config.epochs)
print "batch size : " + str(posenet_config.batch_size)
print "loss weight value beta : " + str(posenet_config.loss_beta)
print "use shrink model for training : " + str(use_shrink_model)
print "use fixed input mean and std : " + str(use_fixed_input_mean_std)
print "use beacon data augmentation : " + str(use_augmentation_beacon)
if posenet_config.base_model != "inception-v1" and posenet_config.base_model != "inception-v3" and posenet_config.base_model != "mobilenet-v1":
print "invalid base model : " + posenet_config.base_model
sys.exit()
if input_image_weight_file is None or input_beacon_weight_file is None:
print "please specify initial weight for image and beacon"
sys.exit()
# parse beacon setting file
beaconmap = IBeaconUtils.parseBeaconSetting(input_beacon_setting_file)
beacon_num = len(beaconmap.keys())
input_image_dir = os.path.dirname(input_txt_file)
output_numpy_mean_image_file = os.path.join(output_model_dir,
"mean_image.npy")
output_numpy_mean_beacon_file = os.path.join(output_model_dir,
"mean_beacon.npy")
output_numpy_model_file = os.path.join(output_model_dir, "model.npy")
output_model_file = os.path.join(output_model_dir, "model.ckpt")
if posenet_config.base_model == "inception-v1":
image_size = 224
output_auxiliary = True
elif posenet_config.base_model == "inception-v3":
image_size = 299
output_auxiliary = False
elif posenet_config.base_model == "mobilenet-v1":
image_size = 224
output_auxiliary = False
else:
print "invalid base model : " + posenet_config.base_model
sys.exit()
datasource, mean_image, mean_beacon = posenet_data_utils.get_image_beacon_data(
input_txt_file,
input_image_dir,
beaconmap,
beacon_num,
use_fixed_input_mean_std,
use_augmentation_beacon,
image_size=image_size)
if use_fixed_input_mean_std:
print("Skip save mean image and beacon")
else:
with open(output_numpy_mean_image_file, 'wb') as fw:
np.save(fw, mean_image)
print("Save mean image at: " + output_numpy_mean_image_file)
with open(output_numpy_mean_beacon_file, 'wb') as fw:
np.save(fw, mean_beacon)
print("Save mean beacon at: " + output_numpy_mean_beacon_file)
# Set GPU options
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.4)
session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
KTF.set_session(session)
# Train model
adam = Adam(lr=0.0001, beta_1=0.9, beta_2=0.999, epsilon=0.00000001)
if use_shrink_model:
if posenet_config.base_model == "inception-v1":
model = posenet_image_beacon_no_inception_shrink_keras.create_posenet_inception_v1(
beacon_num, input_image_weight_file, input_beacon_weight_file)
model.compile(optimizer=adam,
loss={
'image_beacon_cls1_fc_pose_xyz':
posenet_loss.euc_loss1x,
'image_beacon_cls1_fc_pose_wpqr':
posenet_loss.euc_loss1q,
'image_beacon_cls2_fc_pose_xyz':
posenet_loss.euc_loss2x,
'image_beacon_cls2_fc_pose_wpqr':
posenet_loss.euc_loss2q,
'image_beacon_cls3_fc_pose_xyz':
posenet_loss.euc_loss3x,
'image_beacon_cls3_fc_pose_wpqr':
posenet_loss.euc_loss3q
})
elif posenet_config.base_model == "inception-v3":
model = posenet_image_beacon_no_inception_shrink_keras.create_posenet_inception_v3(
beacon_num, input_image_weight_file, input_beacon_weight_file)
model.compile(optimizer=adam,
loss={
'image_beacon_cls3_fc_pose_xyz':
posenet_loss.euc_loss3x,
'image_beacon_cls3_fc_pose_wpqr':
posenet_loss.euc_loss3q
})
elif posenet_config.base_model == "mobilenet-v1":
model = posenet_image_beacon_no_inception_shrink_keras.create_posenet_mobilenet_v1(
beacon_num, input_image_weight_file, input_beacon_weight_file)
model.compile(optimizer=adam,
loss={
'image_beacon_cls_fc_pose_xyz':
posenet_loss.euc_loss3x,
'image_beacon_cls_fc_pose_wpqr':
posenet_loss.euc_loss3q
})
else:
print "invalid base model : " + posenet_config.base_model
sys.exit()
else:
print "Do not shrink model is not supported"
sys.exit()
model.summary()
# Setup checkpointing
checkpointer = ModelCheckpoint(filepath=os.path.join(
output_model_dir, "checkpoint_weights.h5"),
verbose=1,
save_weights_only=True,
period=1)
# Save Tensorboard log
logger = TensorBoard(log_dir=output_log_dir,
histogram_freq=0,
write_graph=True)
# Adjust Epoch size depending on beacon data augmentation
if use_augmentation_beacon:
posenet_config.epochs = posenet_config.epochs / posenet_config.num_beacon_augmentation
steps_per_epoch = int(
len(datasource.poses_index) / float(posenet_config.batch_size))
num_iterations = steps_per_epoch * posenet_config.epochs
print("Number of epochs : " + str(posenet_config.epochs))
print("Number of training data : " + str(len(datasource.poses_index)))
print("Number of iterations : " + str(num_iterations))
history = model.fit_generator(
posenet_data_utils.gen_image_beacon_data_batch(
datasource, output_auxiliary=output_auxiliary),
steps_per_epoch=steps_per_epoch,
epochs=posenet_config.epochs,
callbacks=[checkpointer, logger])
model.save_weights(os.path.join(output_model_dir, "trained_weights.h5"))
