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, 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:
print("KeyboardInterrpt in server - ending server")
stream.release()
pool.terminate()
pool.join()
server.socket.close()
server.shutdown()
return
def run_prediction(input_image, model, config_file, 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
# initialize Network
nn = _init(model, config)
# 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, (nn, image_data), 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,
"pre": bench_pre,
"post": bench_post,
"inference": bench_inference,
},
)
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,
bench_inference,
bench_post,
bench_pre + bench_post + bench_inference,
))
sqlstring = sqlstring + ");\n" return sqlstring ##====================================================================== ## Lets GO! ##====================================================================== ## import config and connect db import config config.init_db(opts.connect_yaml) ## Load yaml with table def table_def_yaml = args[0] tob = config.load_yaml(table_def_yaml, as_object=True) #print tob, tob.table ## Create the table sql = get_create_table_sql(tob, drop=True) config.DB.execute(sql) config.CONN.commit() # All done config.CONN.close() print "--- CREATED TABLE: %s ---" % tob.table print sql
def load_cron_config():
cron = config.load_yaml('app/config/deployment/cron.yml')
return cron
def run_prediction(input_image, model, config_file, 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
# initialize Network
nn = _init(model, config)
pre_process = build_pre_process(config.PRE_PROCESSOR)
post_process = build_post_process(config.POST_PROCESSOR)
# call functions once to exclude the first result which include some initializations
init_output = _pre_process(image_data, pre_process, config.DATA_FORMAT)
init_output = _run(nn, init_output)
init_output = _post_process(init_output, post_process)
results_total = []
results_pre = []
results_run = []
results_post = []
for _ in range(trial):
# pre process for image
output, bench_pre = _timerfunc(
_pre_process, (image_data, pre_process, config.DATA_FORMAT))
# run the model to inference
output, bench_run = _timerfunc(_run, (nn, output))
# pre process for output
output, bench_post = _timerfunc(_post_process, (output, post_process))
results_total.append(bench_pre + bench_run + bench_post)
results_pre.append(bench_pre)
results_run.append(bench_run)
results_post.append(bench_post)
time_stat = {
"total": {
"mean": np.mean(results_total),
"std": np.std(results_total)
},
"pre": {
"mean": np.mean(results_pre),
"std": np.std(results_pre)
},
"post": {
"mean": np.mean(results_post),
"std": np.std(results_post)
},
"run": {
"mean": np.mean(results_run),
"std": np.std(results_run)
},
}
# json output
json_output = JsonOutput(
task=Tasks(config.TASK),
classes=config.CLASSES,
image_size=config.IMAGE_SIZE,
data_format=config.DATA_FORMAT,
bench=time_stat,
)
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".format(trial))
logger.info(time_stat)
def load_cron_config():
cron = config.load_yaml('app/config/deployment/cron.yml')
return cron