def run(FLAGS, cfg):
# init parallel environment if nranks > 1
init_parallel_env()
# build trainer
trainer = Trainer(cfg, mode='eval')
# load weights
trainer.load_weights(cfg.weights, 'resume')
# training
trainer.evaluate()
def run(FLAGS, cfg):
# init parallel environment if nranks > 1
init_parallel_env()
if FLAGS.enable_ce:
set_random_seed(0)
# build trainer
trainer = Trainer(cfg, mode='train')
# load weights
trainer.load_weights(cfg.pretrain_weights, FLAGS.weight_type)
# training
trainer.train()
def run(FLAGS, cfg):
# init fleet environment
if cfg.fleet:
init_fleet_env()
else:
# init parallel environment if nranks > 1
init_parallel_env()
if FLAGS.enable_ce:
set_random_seed(0)
# build trainer
trainer = Trainer(cfg, mode='train')
# load weights
if not FLAGS.slim_config:
trainer.load_weights(cfg.pretrain_weights, FLAGS.weight_type)
# training
trainer.train(FLAGS.eval)
def run(FLAGS, cfg):
# init fleet environment
if cfg.fleet:
init_fleet_env()
else:
# init parallel environment if nranks > 1
init_parallel_env()
if FLAGS.enable_ce:
set_random_seed(0)
# build trainer
trainer = Trainer(cfg, mode='train')
# load weights
if FLAGS.resume is not None:
trainer.resume_weights(FLAGS.resume)
elif 'pretrain_weights' in cfg and cfg.pretrain_weights:
trainer.load_weights(cfg.pretrain_weights)
# training
trainer.train(FLAGS.eval)
def run(FLAGS, cfg):
if FLAGS.json_eval:
logger.info(
"In json_eval mode, PaddleDetection will evaluate json files in "
"output_eval directly. And proposal.json, bbox.json and mask.json "
"will be detected by default.")
json_eval_results(cfg.metric,
json_directory=FLAGS.output_eval,
dataset=cfg['EvalDataset'])
return
# init parallel environment if nranks > 1
init_parallel_env()
# build trainer
trainer = Trainer(cfg, mode='eval')
# load weights
trainer.load_weights(cfg.weights)
# training
trainer.evaluate()