def test_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV1
config.DATASET_CLASS = LmThingsOnATable
config.IS_DEBUG = False
config.IMAGE_SIZE = [70, 70]
config.BATCH_SIZE = 4
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.OBJECT_DETECTION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
environment.init("test_yolov_1")
prepare_dirs(recreate=True)
start_training(config)
def test_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV2
config.DATASET_CLASS = Pascalvoc2007
config.IS_DEBUG = False
config.IMAGE_SIZE = [128, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.OBJECT_DETECTION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.DATA_FORMAT = "NHWC"
# dataset config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
config.DATASET.DATA_FORMAT = "NHWC"
environment.init("test_yolo_v2")
prepare_dirs(recreate=True)
start_training(config)
def run(experiment_id,
restore_path=None,
image_size=(None, None),
image=DEFAULT_INFERENCE_TEST_DATA_IMAGE,
config_file=None):
environment.init(experiment_id)
config = config_util.load_from_experiment()
if config_file:
config = config_util.merge(config, config_util.load(config_file))
config.BATCH_SIZE = 1
config.NETWORK.BATCH_SIZE = 1
config.DATASET.BATCH_SIZE = 1
if list(image_size) != [None, None]:
config.IMAGE_SIZE = list(image_size)
config.NETWORK.IMAGE_SIZE = list(image_size)
# override pre processes image size.
if config.PRE_PROCESSOR:
config.PRE_PROCESSOR.set_image_size(image_size)
# override post processes image size.
if config.POST_PROCESSOR:
config.POST_PROCESSOR.set_image_size(image_size)
print("Override IMAGE_SIZE", config.IMAGE_SIZE)
executor.init_logging(config)
config_util.display(config)
return _export(config, restore_path, image)
def test_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV2
config.DATASET_CLASS = LmThingsOnATable
config.IS_DEBUG = False
config.IMAGE_SIZE = [128, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_STEPS = 1
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.IS_DISTRIBUTION = False
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.DATA_FORMAT = "NCHW"
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
config.DATASET.DATA_FORMAT = "NCHW"
environment.init("test_yolo_v2")
prepare_dirs(recreate=True)
start_training(config)
def run_server(server_info, experiment_id, config_file, restore_path):
environment.init(experiment_id)
if config_file is None:
config = config_util.load_from_experiment()
else:
config = config_util.merge(config, config_util.load(config_file))
if restore_path is None:
restore_file = search_restore_filename(environment.CHECKPOINTS_DIR)
restore_path = os.path.join(environment.CHECKPOINTS_DIR, restore_file)
inference_model = Inference(config, restore_path)
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
s.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
s.bind(server_info)
s.listen(32)
print("boot: {}:{}".format(*server_info))
while True:
client_conn, client_addr = s.accept()
print("\033[Kfrom: {}:{}".format(*client_addr), end="\r")
try:
th = threading.Thread(target=receive_and_send,
args=(client_conn, inference_model),
daemon=True)
th.start()
# th.join()
# receive_and_send(client_conn, inference_model)
except BrokenPipeError:
print("Send data aborted!")
pass
def run(experiment_id, restore_path, config_file, bit, unquant_layers):
if config_file is None and experiment_id is None:
raise Exception("config_file or experiment_id are required")
if experiment_id:
environment.init(experiment_id)
config = config_util.load_from_experiment()
if config_file:
config = config_util.merge(config, config_util.load(config_file))
if restore_path is None:
restore_file = executor.search_restore_filename(
environment.CHECKPOINTS_DIR)
restore_path = os.path.join(environment.CHECKPOINTS_DIR,
restore_file)
if not os.path.exists("{}.index".format(restore_path)):
raise Exception(
"restore file {} dont exists.".format(restore_path))
else:
experiment_id = "profile"
environment.init(experiment_id)
config = config_util.load(config_file)
executor.init_logging(config)
config_util.display(config)
_profile(config, restore_path, bit, unquant_layers)
def test_training():
"""Verify only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = LMBiSeNet
config.DATASET_CLASS = DummyCamvid
config.IS_DEBUG = False
config.IMAGE_SIZE = [128, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_STEPS = 1
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.IS_DISTRIBUTION = False
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.DATA_FORMAT = "NHWC"
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = Resize(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
config.DATASET.DATA_FORMAT = "NHWC"
environment.init("test_lm_bisenet")
prepare_dirs(recreate=True)
start_training(config)
def test_training():
"""Test only no error raised."""
config = EasyDict()
config.NETWORK_CLASS = Darknet
config.DATASET_CLASS = Dummy
config.IS_DEBUG = False
config.IMAGE_SIZE = [28, 14]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.CLASSIFICATION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = Resize(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
environment.init("test_darknet")
prepare_dirs(recreate=True)
start_training(config)
def test_example_classification_config_yaml():
"""
Test that export config and meta yaml from example classification config python.
"""
config_file = os.path.join("configs", "example", "classification.py")
config = _load_py(config_file)
config_yaml = os.path.join("configs", "example", "classification.yaml")
config_meta = os.path.join("configs", "example",
"classification_meta.yaml")
environment.init("test_example_classification_config_yaml")
saved_config, saved_meta = save_yaml(environment.EXPERIMENT_DIR, config)
print(saved_meta)
with open(config_yaml) as f:
expected = f.read()
with open(saved_config) as f:
data = f.read()
assert expected == data
with open(config_meta) as f:
expected = f.read()
with open(saved_meta) as f:
data = f.read()
assert expected == data
def test_quantize_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = FlowNetSV1Quantized
config.DATASET_CLASS = FlyingChairs
config.IS_DEBUG = False
config.IMAGE_SIZE = [384, 512]
config.BATCH_SIZE = 8
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.IS_DISTRIBUTION = False
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.DATA_FORMAT = "NHWC"
config.NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
config.NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2.0}
config.NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
config.NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
# dataset config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = None
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
config.DATASET.DATA_FORMAT = "NHWC"
config.DATASET.VALIDATION_RATE = 0.2
config.DATASET.VALIDATION_SEED = 2019
config.DATASET.AUGMENTOR = Sequence([
# Geometric transformation
FlipLeftRight(0.5),
FlipTopBottom(0.5),
Translate(-0.2, 0.2),
Rotate(-17, +17),
Scale(1.0, 2.0),
# Pixel-wise augmentation
Brightness(0.8, 1.2),
Contrast(0.2, 1.4),
Color(0.5, 2.0),
Gamma(0.7, 1.5),
# Hue(-128.0, 128.0),
GaussianNoise(0.0, 10.0)
])
config.DATASET.PRE_PROCESSOR = Sequence([
DevideBy255(),
])
environment.init("test_flownet_s_v1_quantize")
prepare_dirs(recreate=True)
start_training(config)
def main(output_file_base, metrics_keys, steps, experiment_id):
environment.init(experiment_id)
output(
environment.TENSORBOARD_DIR,
environment.EXPERIMENT_DIR,
metrics_keys,
steps,
output_file_base="metrics",
)
def test_training():
"""Test only no error raised."""
config = EasyDict()
config.NETWORK_CLASS = LmSinglePoseV1Quantize
config.DATASET_CLASS = MscocoSinglePersonKeypoints
config.IS_DEBUG = False
config.IMAGE_SIZE = [160, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.IS_DISTRIBUTION = False
config.TASK = Tasks.KEYPOINT_DETECTION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
config.NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2.0}
config.NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
config.NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = Sequence([
ResizeWithJoints(image_size=config.IMAGE_SIZE),
JointsToGaussianHeatmap(image_size=config.IMAGE_SIZE, stride=2),
DivideBy255()
])
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
environment.init("test_lm_single_pose_v1")
prepare_dirs(recreate=True)
start_training(config)
def main(network, dataset, config_file, experiment_id, restore_path):
environment.init(experiment_id)
config = config_util.load_from_experiment()
if config_file:
config = config_util.merge(config, config_util.load(config_file))
if network:
network_class = module_loader.load_network_class(network)
config.NETWORK_CLASS = network_class
if dataset:
dataset_class = module_loader.load_dataset_class(dataset)
config.DATASET_CLASS = dataset_class
executor.init_logging(config)
config_util.display(config)
evaluate(config, restore_path)
def run(network, dataset, config_file, experiment_id, recreate):
environment.init(experiment_id)
config = config_util.load(config_file)
if network:
network_class = module_loader.load_network_class(network)
config.NETWORK_CLASS = network_class
if dataset:
dataset_class = module_loader.load_dataset_class(dataset)
config.DATASET_CLASS = dataset_class
config_util.display(config)
executor.init_logging(config)
executor.prepare_dirs(recreate)
config_util.copy_to_experiment_dir(config_file)
config_util.save_yaml(environment.EXPERIMENT_DIR, config)
start_training(config)
def test_training():
"""Test only no error raised."""
config = EasyDict()
config.NETWORK_CLASS = YoloV2Quantize
config.DATASET_CLASS = Pascalvoc2007
config.IS_DEBUG = False
config.IMAGE_SIZE = [128, 160]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.OBJECT_DETECTION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
config.NETWORK.ACTIVATION_QUANTIZER_KWARGS = {
'bit': 2,
'max_value': 2.0
}
config.NETWORK.WEIGHT_QUANTIZER = binary_channel_wise_mean_scaling_quantizer
config.NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
# daasegt config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = ResizeWithGtBoxes(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
environment.init("test_yolov_2_quantize")
prepare_dirs(recreate=True)
start_training(config)
def main(model):
if model == "yolov2":
weight_file = 'inputs/yolo-voc.weights'
experiment_id = "convert_weight_from_darknet/yolo_v2"
config_file = "configs/convert_weight_from_darknet/yolo_v2.py"
if model == "darknet19":
weight_file = 'inputs/darknet19_448.weights'
experiment_id = "convert_weight_from_darknet/darknet19"
config_file = "configs/convert_weight_from_darknet/darknet19.py"
recreate = True
environment.init(experiment_id)
executor.prepare_dirs(recreate)
config = config_util.load(config_file)
config_util.display(config)
config_util.copy_to_experiment_dir(config_file)
convert(config, weight_file)
def test_training():
"""Test only that no error raised."""
config = EasyDict()
config.NETWORK_CLASS = LmResnetQuantize
config.DATASET_CLASS = Dummy
config.IS_DEBUG = False
config.IMAGE_SIZE = [32, 32]
config.BATCH_SIZE = 2
config.TEST_STEPS = 1
config.MAX_STEPS = 2
config.SAVE_CHECKPOINT_STEPS = 1
config.KEEP_CHECKPOINT_MAX = 5
config.SUMMARISE_STEPS = 1
config.IS_PRETRAIN = False
config.TASK = Tasks.CLASSIFICATION
# network model config
config.NETWORK = EasyDict()
config.NETWORK.OPTIMIZER_CLASS = tf.train.AdamOptimizer
config.NETWORK.OPTIMIZER_KWARGS = {"learning_rate": 0.001}
config.NETWORK.IMAGE_SIZE = config.IMAGE_SIZE
config.NETWORK.BATCH_SIZE = config.BATCH_SIZE
config.NETWORK.ACTIVATION_QUANTIZER = linear_mid_tread_half_quantizer
config.NETWORK.ACTIVATION_QUANTIZER_KWARGS = {'bit': 2, 'max_value': 2}
config.NETWORK.WEIGHT_QUANTIZER = binary_mean_scaling_quantizer
config.NETWORK.WEIGHT_QUANTIZER_KWARGS = {}
# dataset config
config.DATASET = EasyDict()
config.DATASET.PRE_PROCESSOR = Resize(config.IMAGE_SIZE)
config.DATASET.BATCH_SIZE = config.BATCH_SIZE
environment.init("test_lm_resnet_quantize")
prepare_dirs(recreate=True)
start_training(config)
def run(input_dir, output_dir, experiment_id, config_file, restore_path,
save_images):
environment.init(experiment_id)
config = config_util.load_from_experiment()
if config_file:
config = config_util.merge(config, config_util.load(config_file))
if not os.path.isdir(input_dir):
raise Exception("Input directory {} does not exist.".format(input_dir))
if restore_path is None:
restore_file = search_restore_filename(environment.CHECKPOINTS_DIR)
restore_path = os.path.join(environment.CHECKPOINTS_DIR, restore_file)
print("Restore from {}".format(restore_path))
if not os.path.exists("{}.index".format(restore_path)):
raise Exception("restore file {} dont exists.".format(restore_path))
print("---- start predict ----")
_run(input_dir, output_dir, config, restore_path, save_images)
print("---- end predict ----")
def _run(config_file, experiment_id, restore_path, image_size, step_size, cpu):
if experiment_id:
environment.init(experiment_id)
config = config_util.load_from_experiment()
if config_file:
config = config_util.merge(config, config_util.load(config_file))
if restore_path is None:
restore_file = executor.search_restore_filename(
environment.CHECKPOINTS_DIR)
restore_path = os.path.join(environment.CHECKPOINTS_DIR,
restore_file)
if not os.path.exists("{}.index".format(restore_path)):
raise Exception(
"restore file {} dont exists.".format(restore_path))
else:
experiment_id = "measure_latency"
environment.init(experiment_id)
config = config_util.load(config_file)
config.BATCH_SIZE = 1
config.NETWORK.BATCH_SIZE = 1
config.DATASET.BATCH_SIZE = 1
if list(image_size) != [None, None]:
config.IMAGE_SIZE = list(image_size)
config.NETWORK.IMAGE_SIZE = list(image_size)
# override pre processes image size.
if config.PRE_PROCESSOR:
config.PRE_PROCESSOR.set_image_size(image_size)
# override post processes image size.
if config.POST_PROCESSOR:
config.POST_PROCESSOR.set_image_size(image_size)
print("Override IMAGE_SIZE", config.IMAGE_SIZE)
executor.init_logging(config)
config_util.display(config)
overall_times, only_network_times = _measure_time(config, restore_path,
step_size)
overall_times = np.array(overall_times)
only_network_times = np.array(only_network_times)
# list of physical_device_desc
devices = [
device.physical_device_desc
for device in device_lib.list_local_devices()
if device.physical_device_desc
]
message = """
---- measure latency result ----
total number of execution (number of samples): {}
network: {}
use gpu by network: {}
image size: {}
devices: {}
* overall (include pre-post-process which execute on cpu)
total time: {:.4f} msec
latency
mean (SD=standard deviation): {:.4f} (SD={:.4f}) msec, min: {:.4f} msec, max: {:.4f} msec
FPS
mean (SD=standard deviation): {:.4f} (SD={:.4f}), min: {:.4f}, max: {:.4f}
* network only (exclude pre-post-process):
total time: {:.4f} msec
latency
mean (SD=standard deviation): {:.4f} (SD={:.4f}) msec, min: {:.4f} msec, max: {:.4f} msec
FPS
mean (SD=standard deviation): {:.4f} (SD={:.4f}), min: {:.4f}, max: {:.4f}
---- measure latency result ----
""".format(
step_size,
config.NETWORK_CLASS.__name__,
not cpu,
config.IMAGE_SIZE,
devices,
# overall
np.sum(overall_times) * 1000,
# latency
np.mean(overall_times) * 1000,
np.std(overall_times) * 1000,
np.min(overall_times) * 1000,
np.max(overall_times) * 1000,
# FPS
np.mean(1 / overall_times),
np.std(1 / overall_times),
np.min(1 / overall_times),
np.max(1 / overall_times),
# network only
np.sum(only_network_times) * 1000,
# latency
np.mean(only_network_times) * 1000,
np.std(only_network_times) * 1000,
np.min(only_network_times) * 1000,
np.max(only_network_times) * 1000,
# FPS
np.mean(1 / only_network_times),
np.std(1 / only_network_times),
np.min(1 / only_network_times),
np.max(1 / only_network_times),
)
print(message)
session_config = tf.ConfigProto()
session_config.gpu_options.allow_growth = True
self.sess = tf.Session(graph=graph, config=session_config)
self.sess.run(init_op)
saver.restore(self.sess, restore_path)
def __call__(self, input_data):
feed_dict = {self.images_placeholder: input_data * (1 / 255.0)}
t_begin = time.time()
output = self.sess.run(self.output_op, feed_dict=feed_dict)
calc_time = time.time() - t_begin
return output, calc_time
if __name__ == '__main__':
environment.init(args.experiment_id)
config = config_util.load_from_experiment()
print(config)
if args.config_file is not None:
config = config_util.merge(config, config_util.load(args.config_file))
if args.restore_path is None:
restore_file = search_restore_filename(environment.CHECKPOINTS_DIR)
restore_path = os.path.join(environment.CHECKPOINTS_DIR, restore_file)
else:
restore_path = args.restore_path
print("Restore from {}".format(restore_path))
inference_model = Inference(config, restore_path)
window_name = os.path.basename(restore_path)
run_demo(inference_model,
diff_step=args.diff_step,
