def run(FLAGS, cfg):
# build detector
trainer = Trainer(cfg, mode='test')
# load weights
if cfg.architecture in ['DeepSORT', 'ByteTrack']:
trainer.load_weights_sde(cfg.det_weights, cfg.reid_weights)
else:
trainer.load_weights(cfg.weights)
# export model
trainer.export(FLAGS.output_dir)
if FLAGS.export_serving_model:
from paddle_serving_client.io import inference_model_to_serving
model_name = os.path.splitext(os.path.split(cfg.filename)[-1])[0]
inference_model_to_serving(
dirname="{}/{}".format(FLAGS.output_dir, model_name),
serving_server="{}/{}/serving_server".format(FLAGS.output_dir,
model_name),
serving_client="{}/{}/serving_client".format(FLAGS.output_dir,
model_name),
model_filename="model.pdmodel",
params_filename="model.pdiparams")
def run(FLAGS, cfg):
# build detector
trainer = Trainer(cfg, mode='eval')
# load weights
if cfg.architecture in ['DeepSORT']:
if cfg.det_weights != 'None':
trainer.load_weights_sde(cfg.det_weights, cfg.reid_weights)
else:
trainer.load_weights_sde(None, cfg.reid_weights)
else:
trainer.load_weights(cfg.weights)
# post quant model
trainer.post_quant(FLAGS.output_dir)