def run(model, config_file):
global nn, pre_process, post_process
filename, file_extension = os.path.splitext(model)
supported_files = ['.so', '.pb']
if file_extension not in supported_files:
raise Exception("""
Unknown file type. Got %s%s.
Please check the model file (-m).
Only .pb (protocol buffer) or .so (shared object) file is supported.
""" % (filename, file_extension))
config = load_yaml(config_file)
pre_process = build_pre_process(config.PRE_PROCESSOR)
post_process = build_post_process(config.POST_PROCESSOR)
if file_extension == '.so': # Shared library
nn = NNLib()
nn.load(model)
elif file_extension == '.pb': # Protocol Buffer file
# only load tensorflow if user wants to use GPU
from lmnet.tensorflow_graph_runner import TensorflowGraphRunner
nn = TensorflowGraphRunner(model)
run_impl(config)
def run(model, config_file):
global nn, pre_process, post_process
filename, file_extension = os.path.splitext(model)
supported_files = ['.so', '.pb']
if file_extension not in supported_files:
raise Exception("""
Unknown file type. Got %s%s.
Please check the model file (-m).
Only .pb (protocol buffer) or .so (shared object) file is supported.
""" % (filename, file_extension))
config = load_yaml(config_file)
pre_process = build_pre_process(config.PRE_PROCESSOR)
post_process = build_post_process(config.POST_PROCESSOR)
if file_extension == '.so': # Shared library
nn = NNLib()
nn.load(model)
elif file_extension == '.pb': # Protocol Buffer file
# only load tensorflow if user wants to use GPU
from lmnet.tensorflow_graph_runner import TensorflowGraphRunner
nn = TensorflowGraphRunner(model)
if config.TASK == "IMAGE.CLASSIFICATION":
run_classification(config)
if config.TASK == "IMAGE.OBJECT_DETECTION":
run_object_detection(config)
if config.TASK == "IMAGE.SEMANTIC_SEGMENTATION":
run_sementic_segmentation(config)
def run_prediction(input_image, model, config_file, max_percent_incorrect_values=0.1, trial=1):
if not input_image or not model or not config_file:
logger.error('Please check usage with --help option')
exit(1)
config = load_yaml(config_file)
# load the image
image_data = load_image(input_image)
raw_image = image_data
# pre process for image
image_data, bench_pre = _timerfunc(_pre_process, (image_data, config.PRE_PROCESSOR, config.DATA_FORMAT), trial)
# add the batch dimension
image_data = np.expand_dims(image_data, axis=0)
# run the model to inference
output, bench_inference = _timerfunc(_run, (model, image_data, config), trial)
logger.info('Output: (before post process)\n{}'.format(output))
# pre process for output
output, bench_post = _timerfunc(_post_process, (output, config.POST_PROCESSOR), trial)
logger.info('Output: (after post process)\n{}'.format(output))
# json output
json_output = JsonOutput(
task=Tasks(config.TASK),
classes=config.CLASSES,
image_size=config.IMAGE_SIZE,
data_format=config.DATA_FORMAT,
bench={
"total": (bench_pre + bench_post + bench_inference) / trial,
"pre": bench_pre / trial,
"post": bench_post / trial,
"inference": bench_inference / trial,
},
)
image_from_json = ImageFromJson(
task=Tasks(config.TASK),
classes=config.CLASSES,
image_size=config.IMAGE_SIZE,
)
output_dir = "output"
outputs = output
raw_images = [raw_image]
image_files = [input_image]
json_obj = json_output(outputs, raw_images, image_files)
_save_json(output_dir, json_obj)
filename_images = image_from_json(json_obj, raw_images, image_files)
_save_images(output_dir, filename_images)
logger.info("Benchmark avg result(sec) for {} trials: pre_process: {} inference: {} post_process: {} Total: {}"
.format(trial, bench_pre / trial, bench_inference / trial, bench_post / trial,
(bench_pre + bench_post + bench_inference) / trial,))
def run(model, config_file, port=80):
global nn, pre_process, post_process, config, stream, pool
filename, file_extension = os.path.splitext(model)
supported_files = ['.so', '.pb']
if file_extension not in supported_files:
raise Exception("""
Unknown file type. Got %s%s.
Please check the model file (-m).
Only .pb (protocol buffer) or .so (shared object) file is supported.
""" % (filename, file_extension))
if file_extension == '.so': # Shared library
nn = NNLib()
nn.load(model)
elif file_extension == '.pb': # Protocol Buffer file
# only load tensorflow if user wants to use GPU
from lmnet.tensorflow_graph_runner import TensorflowGraphRunner
nn = TensorflowGraphRunner(model)
nn = NNLib()
nn.load(model)
stream = VideoStream(CAMERA_SOURCE, CAMERA_WIDTH, CAMERA_HEIGHT,
CAMERA_FPS)
config = load_yaml(config_file)
pre_process = build_pre_process(config.PRE_PROCESSOR)
post_process = build_post_process(config.POST_PROCESSOR)
pool = Pool(processes=1, initializer=_init_worker)
try:
server = ThreadedHTTPServer(('', port), MotionJpegHandler)
print("server starting")
server.serve_forever()
except KeyboardInterrupt as e:
print("KeyboardInterrpt in server - ending server")
stream.release()
pool.terminate()
pool.join()
server.socket.close()
server.shutdown()
return
def run(library, config_file):
global nn, pre_process, post_process
nn = NNLib()
nn.load(library)
nn.init()
config = load_yaml(config_file)
pre_process = build_pre_process(config.PRE_PROCESSOR)
post_process = build_post_process(config.POST_PROCESSOR)
if config.TASK == "IMAGE.CLASSIFICATION":
run_classification(config)
if config.TASK == "IMAGE.OBJECT_DETECTION":
run_object_detection(config)
def run_prediction(input_image,
model,
config_file,
max_percent_incorrect_values=0.1):
if not input_image or not model or not config_file:
print('Please check usage with --help option')
exit(1)
config = load_yaml(config_file)
# run the model
output, raw_image = _run(model, input_image, config)
print('Output: (before post process)')
print(output)
# pre process for output
output = _post_process(output, config.POST_PROCESSOR)
print('Output: ')
print(output)
# json output
json_output = JsonOutput(
task=Tasks(config.TASK),
classes=config.CLASSES,
image_size=config.IMAGE_SIZE,
data_format=config.DATA_FORMAT,
)
image_from_json = ImageFromJson(
task=Tasks(config.TASK),
classes=config.CLASSES,
image_size=config.IMAGE_SIZE,
)
output_dir = "output"
outputs = output
raw_images = [raw_image]
image_files = [input_image]
json_obj = json_output(outputs, raw_images, image_files)
_save_json(output_dir, json_obj)
filename_images = image_from_json(json_obj, raw_images, image_files)
_save_images(output_dir, filename_images)