in grolp/models/embodied_bert.py [0:0]
def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.PathLike]], *model_args, **kwargs):
config = kwargs.pop("config", None)
state_dict = kwargs.pop("state_dict", None)
cache_dir = kwargs.pop("cache_dir", None)
from_tf = kwargs.pop("from_tf", False)
force_download = kwargs.pop("force_download", False)
resume_download = kwargs.pop("resume_download", False)
proxies = kwargs.pop("proxies", None)
output_loading_info = kwargs.pop("output_loading_info", False)
local_files_only = kwargs.pop("local_files_only", False)
use_auth_token = kwargs.pop("use_auth_token", None)
revision = kwargs.pop("revision", None)
mirror = kwargs.pop("mirror", None)
# Load config if we don't provide a configuration
if not isinstance(config, PretrainedConfig):
config_path = config if config is not None else pretrained_model_name_or_path
config, model_kwargs = cls.config_class.from_pretrained(
config_path,
*model_args,
cache_dir=cache_dir,
return_unused_kwargs=True,
force_download=force_download,
resume_download=resume_download,
proxies=proxies,
local_files_only=local_files_only,
use_auth_token=use_auth_token,
revision=revision,
**kwargs,
)
else:
model_kwargs = kwargs
# Load model
if pretrained_model_name_or_path is not None:
pretrained_model_name_or_path = str(pretrained_model_name_or_path)
if os.path.isdir(pretrained_model_name_or_path):
if from_tf and os.path.isfile(os.path.join(pretrained_model_name_or_path, TF_WEIGHTS_NAME + ".index")):
# Load from a TF 1.0 checkpoint in priority if from_tf
archive_file = os.path.join(pretrained_model_name_or_path, TF_WEIGHTS_NAME + ".index")
elif from_tf and os.path.isfile(os.path.join(pretrained_model_name_or_path, TF2_WEIGHTS_NAME)):
# Load from a TF 2.0 checkpoint in priority if from_tf
archive_file = os.path.join(pretrained_model_name_or_path, TF2_WEIGHTS_NAME)
elif os.path.isfile(os.path.join(pretrained_model_name_or_path, WEIGHTS_NAME)):
# Load from a PyTorch checkpoint
archive_file = os.path.join(pretrained_model_name_or_path, WEIGHTS_NAME)
else:
raise EnvironmentError(
"Error no file named {} found in directory {} or `from_tf` set to False".format(
[WEIGHTS_NAME, TF2_WEIGHTS_NAME, TF_WEIGHTS_NAME + ".index"],
pretrained_model_name_or_path,
)
)
elif os.path.isfile(pretrained_model_name_or_path) or is_remote_url(pretrained_model_name_or_path):
archive_file = pretrained_model_name_or_path
elif os.path.isfile(pretrained_model_name_or_path + ".index"):
assert (
from_tf
), "We found a TensorFlow checkpoint at {}, please set from_tf to True to load from this checkpoint".format(
pretrained_model_name_or_path + ".index"
)
archive_file = pretrained_model_name_or_path + ".index"
else:
archive_file = hf_bucket_url(
pretrained_model_name_or_path,
filename=(TF2_WEIGHTS_NAME if from_tf else WEIGHTS_NAME),
revision=revision,
mirror=mirror,
)
try:
# Load from URL or cache if already cached
resolved_archive_file = cached_path(
archive_file,
cache_dir=cache_dir,
force_download=force_download,
proxies=proxies,
resume_download=resume_download,
local_files_only=local_files_only,
use_auth_token=use_auth_token,
)
except EnvironmentError as err:
logger.error(err)
msg = (
f"Can't load weights for '{pretrained_model_name_or_path}'. Make sure that:\n\n"
f"- '{pretrained_model_name_or_path}' is a correct model identifier listed on 'https://huggingface.co/models'\n\n"
f"- or '{pretrained_model_name_or_path}' is the correct path to a directory containing a file named one of {WEIGHTS_NAME}, {TF2_WEIGHTS_NAME}, {TF_WEIGHTS_NAME}.\n\n"
)
raise EnvironmentError(msg)
if resolved_archive_file == archive_file:
logger.info("loading weights file {}".format(archive_file))
else:
logger.info("loading weights file {} from cache at {}".format(archive_file, resolved_archive_file))
else:
resolved_archive_file = None
config.name_or_path = pretrained_model_name_or_path
# Instantiate model.
model = cls(config, *model_args, **model_kwargs)
if state_dict is None and not from_tf:
try:
state_dict = torch.load(resolved_archive_file, map_location="cpu")
except Exception:
raise OSError(
f"Unable to load weights from pytorch checkpoint file for '{pretrained_model_name_or_path}' "
f"at '{resolved_archive_file}'"
"If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True. "
)
missing_keys = []
unexpected_keys = []
error_msgs = []
if from_tf:
if resolved_archive_file.endswith(".index"):
# Load from a TensorFlow 1.X checkpoint - provided by original authors
model = cls.load_tf_weights(model, config, resolved_archive_file[:-6]) # Remove the '.index'
else:
# Load from our TensorFlow 2.0 checkpoints
try:
from .modeling_tf_pytorch_utils import load_tf2_checkpoint_in_pytorch_model
model = load_tf2_checkpoint_in_pytorch_model(model, resolved_archive_file, allow_missing_keys=True)
except ImportError:
logger.error(
"Loading a TensorFlow model in PyTorch, requires both PyTorch and TensorFlow to be installed. Please see "
"https://pytorch.org/ and https://www.tensorflow.org/install/ for installation instructions."
)
raise
else:
# Convert old format to new format if needed from a PyTorch state_dict
old_keys = []
new_keys = []
for key in state_dict.keys():
new_key = None
if "gamma" in key:
new_key = key.replace("gamma", "weight")
if "beta" in key:
new_key = key.replace("beta", "bias")
if new_key:
old_keys.append(key)
new_keys.append(new_key)
for old_key, new_key in zip(old_keys, new_keys):
state_dict[new_key] = state_dict.pop(old_key)
# copy state_dict so _load_from_state_dict can modify it
metadata = getattr(state_dict, "_metadata", None)
state_dict = state_dict.copy()
if metadata is not None:
state_dict._metadata = metadata
# PyTorch's `_load_from_state_dict` does not copy parameters in a module's descendants
# so we need to apply the function recursively.
def load(module: nn.Module, prefix=""):
local_metadata = {} if metadata is None else metadata.get(prefix[:-1], {})
module._load_from_state_dict(
state_dict,
prefix,
local_metadata,
True,
missing_keys,
unexpected_keys,
error_msgs,
)
for name, child in module._modules.items():
if child is not None:
load(child, prefix + name + ".")
# Make sure we are able to load base models as well as derived models (with heads)
start_prefix = ""
model_to_load = model
has_prefix_module = any(s.startswith(cls.base_model_prefix) for s in state_dict.keys())
if not hasattr(model, cls.base_model_prefix) and has_prefix_module:
start_prefix = cls.base_model_prefix + "."
if hasattr(model, cls.base_model_prefix) and not has_prefix_module:
model_to_load = getattr(model, cls.base_model_prefix)
load(model_to_load, prefix=start_prefix)
state_dict = {k: v for k, v in state_dict.items() if k.startswith("cls")}
missing_keys = [k for k in missing_keys if not k.startswith("cls")]
unexpected_keys = [k for k in unexpected_keys if not k.startswith("cls")]
load(model.cls, prefix="cls.")
if model.__class__.__name__ != model_to_load.__class__.__name__:
base_model_state_dict = model_to_load.state_dict().keys()
head_model_state_dict_without_base_prefix = [
key.split(cls.base_model_prefix + ".")[-1] for key in model.state_dict().keys()
]
missing_keys.extend(head_model_state_dict_without_base_prefix - base_model_state_dict)
# Some models may have keys that are not in the state by design, removing them before needlessly warning
# the user.
if cls._keys_to_ignore_on_load_missing is not None:
for pat in cls._keys_to_ignore_on_load_missing:
missing_keys = [k for k in missing_keys if re.search(pat, k) is None]
if cls._keys_to_ignore_on_load_unexpected is not None:
for pat in cls._keys_to_ignore_on_load_unexpected:
unexpected_keys = [k for k in unexpected_keys if re.search(pat, k) is None]
if len(unexpected_keys) > 0:
logger.warning(
f"Some weights of the model checkpoint at {pretrained_model_name_or_path} were not used when "
f"initializing {model.__class__.__name__}: {unexpected_keys}\n"
f"- This IS expected if you are initializing {model.__class__.__name__} from the checkpoint of a model trained on another task "
f"or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n"
f"- This IS NOT expected if you are initializing {model.__class__.__name__} from the checkpoint of a model that you expect "
f"to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model)."
)
else:
logger.info(f"All model checkpoint weights were used when initializing {model.__class__.__name__}.\n")
if len(missing_keys) > 0:
logger.warning(
f"Some weights of {model.__class__.__name__} were not initialized from the model checkpoint at {pretrained_model_name_or_path} "
f"and are newly initialized: {missing_keys}\n"
f"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference."
)
else:
logger.info(
f"All the weights of {model.__class__.__name__} were initialized from the model checkpoint at {pretrained_model_name_or_path}.\n"
f"If your task is similar to the task the model of the checkpoint was trained on, "
f"you can already use {model.__class__.__name__} for predictions without further training."
)
if len(error_msgs) > 0:
raise RuntimeError(
"Error(s) in loading state_dict for {}:\n\t{}".format(
model.__class__.__name__, "\n\t".join(error_msgs)
)
)
# make sure token embedding weights are still tied if needed
model.tie_weights()
# Set model in evaluation mode to deactivate DropOut modules by default
model.eval()
if output_loading_info:
loading_info = {
"missing_keys": missing_keys,
"unexpected_keys": unexpected_keys,
"error_msgs": error_msgs,
}
return model, loading_info
if hasattr(config, "xla_device") and config.xla_device and is_torch_tpu_available():
import torch_xla.core.xla_model as xm
model = xm.send_cpu_data_to_device(model, xm.xla_device())
model.to(xm.xla_device())
return model