def test_placeholder_loadserialized(self):
with open(f"{self.out_dir}/tmp1.yaml", "w") as f_out:
yaml.dump(DummyClass(arg1="v1"), f_out)
test_obj = yaml.load(f"""
a: !LoadSerialized
filename: '{{EXP_DIR}}/{{EXP}}.yaml'
""")
YamlPreloader.preload_obj(test_obj, exp_name = "tmp1", exp_dir=self.out_dir)
def test_inconsistent_loadserialized(self):
with open(f"{self.out_dir}/tmp1.yaml", "w") as f_out:
yaml.dump(DummyClass(arg1="v1"), f_out)
test_obj = yaml.load(f"""
a: !LoadSerialized
filename: {self.out_dir}/tmp1.yaml
bad_arg: 1
""")
with self.assertRaises(ValueError):
YamlPreloader.preload_obj(test_obj, "SOME_EXP_NAME", "SOME_EXP_DIR")
def main() -> None:
parser = argparse.ArgumentParser()
utils.add_dynet_argparse(parser)
parser.add_argument("--src",
help=f"Path of source file to read from.",
required=True)
parser.add_argument("--hyp",
help="Path of file to write hypothesis to.",
required=True)
parser.add_argument("--mod",
help="Path of model file to read.",
required=True)
args = parser.parse_args()
exp_dir = os.path.dirname(__file__)
exp = "{EXP}"
param_collections.ParamManager.init_param_col()
# TODO: can we avoid the LoadSerialized proxy and load stuff directly?
load_experiment = LoadSerialized(filename=args.mod)
uninitialized_experiment = YamlPreloader.preload_obj(load_experiment,
exp_dir=exp_dir,
exp_name=exp)
loaded_experiment = initialize_if_needed(uninitialized_experiment)
model = loaded_experiment.model
inference = model.inference
param_collections.ParamManager.populate()
decoding_task = tasks.DecodingEvalTask(args.src, args.hyp, model,
inference)
decoding_task.eval()
def setUp(self):
events.clear()
ParamManager.init_param_col()
# Load a pre-trained model
load_experiment = LoadSerialized(filename=f"test/data/tiny_jaen.model",
overwrite=[
{
"path": "train",
"val": None
},
{
"path": "status",
"val": None
},
])
EXP_DIR = '.'
EXP = "decode"
uninitialized_experiment = YamlPreloader.preload_obj(load_experiment,
exp_dir=EXP_DIR,
exp_name=EXP)
loaded_experiment = initialize_if_needed(uninitialized_experiment)
ParamManager.populate()
# Pull out the parts we need from the experiment
self.model = loaded_experiment.model
src_vocab = self.model.src_reader.vocab
trg_vocab = self.model.trg_reader.vocab
event_trigger.set_train(False)
self.src_data = list(
self.model.src_reader.read_sents("test/data/head.ja"))
self.trg_data = list(
self.model.trg_reader.read_sents("test/data/head.en"))
import xnmt.tee
from xnmt.param_collection import ParamManager
from xnmt.persistence import initialize_if_needed, YamlPreloader, LoadSerialized, save_to_file
EXP_DIR = os.path.dirname(__file__)
EXP = "programmatic-load"
model_file = f"{EXP_DIR}/models/{EXP}.mod"
log_file = f"{EXP_DIR}/logs/{EXP}.log"
xnmt.tee.set_out_file(log_file)
ParamManager.init_param_col()
load_experiment = LoadSerialized(
filename=f"{EXP_DIR}/models/programmatic.mod",
overwrite=[
{"path" : "train", "val" : None}
]
)
uninitialized_experiment = YamlPreloader.preload_obj(load_experiment, exp_dir=EXP_DIR, exp_name=EXP)
loaded_experiment = initialize_if_needed(uninitialized_experiment)
# if we were to continue training, we would need to set a save model file like this:
# ParamManager.param_col.model_file = model_file
ParamManager.populate()
# run experiment
loaded_experiment(save_fct=lambda: save_to_file(model_file, loaded_experiment))
from xnmt.persistence import initialize_if_needed, YamlPreloader, LoadSerialized, save_to_file
parser = argparse.ArgumentParser()
parser.add_argument("filename")
parser.add_argument("output_vocab")
parser.add_argument("output_embed")
parser.add_argument("--embedding", choices=["src", "trg"], default="src")
args = parser.parse_args()
ParamManager.init_param_col()
load_experiment = LoadSerialized(
filename=args.filename,
)
uninitialized_experiment = YamlPreloader.preload_obj(load_experiment, exp_dir="/tmp/dummy", exp_name="dummy")
experiment = initialize_if_needed(uninitialized_experiment)
if args.embedding == "src":
vocab = experiment.model.src_reader.vocab
tensor = experiment.model.src_embedder.embeddings
else:
vocab = experiment.model.trg_reader.vocab
tensor = experiment.model.trg_embedder.embeddings
with open(args.output_vocab, mode="w") as fp:
for word in vocab.i2w:
print(word, file=fp)
with open(args.output_embed, mode="w") as fp:
