99 lines
3.0 KiB
Python
99 lines
3.0 KiB
Python
# Copyright 2020 The HuggingFace Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import math
|
|
|
|
import torch
|
|
import torch.nn.functional as F
|
|
from packaging import version
|
|
|
|
from .utils import logging
|
|
|
|
|
|
logger = logging.get_logger(__name__)
|
|
|
|
|
|
def _gelu_python(x):
|
|
"""
|
|
Original Implementation of the GELU activation function in Google BERT repo when initially created. For
|
|
information: OpenAI GPT's GELU is slightly different (and gives slightly different results): 0.5 * x * (1 +
|
|
torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3)))) This is now written in C in
|
|
torch.nn.functional Also see the Gaussian Error Linear Units paper: https://arxiv.org/abs/1606.08415
|
|
"""
|
|
return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))
|
|
|
|
|
|
def gelu_new(x):
|
|
"""
|
|
Implementation of the GELU activation function currently in Google BERT repo (identical to OpenAI GPT). Also see
|
|
the Gaussian Error Linear Units paper: https://arxiv.org/abs/1606.08415
|
|
"""
|
|
return 0.5 * x * (1.0 + torch.tanh(math.sqrt(2.0 / math.pi) * (x + 0.044715 * torch.pow(x, 3.0))))
|
|
|
|
|
|
if version.parse(torch.__version__) < version.parse("1.4"):
|
|
gelu = _gelu_python
|
|
else:
|
|
gelu = F.gelu
|
|
|
|
|
|
def gelu_fast(x):
|
|
return 0.5 * x * (1.0 + torch.tanh(x * 0.7978845608 * (1.0 + 0.044715 * x * x)))
|
|
|
|
|
|
def _silu_python(x):
|
|
"""
|
|
See Gaussian Error Linear Units (Hendrycks et al., https://arxiv.org/abs/1606.08415) where the SiLU (Sigmoid Linear
|
|
Unit) was originally introduced and coined, and see Sigmoid-Weighted Linear Units for Neural Network Function
|
|
Approximation in Reinforcement Learning (Elfwing et al., https://arxiv.org/abs/1702.03118) and Swish: a Self-Gated
|
|
Activation Function (Ramachandran et al., https://arxiv.org/abs/1710.05941v1) where the SiLU was experimented with
|
|
later.
|
|
"""
|
|
return x * torch.sigmoid(x)
|
|
|
|
|
|
if version.parse(torch.__version__) < version.parse("1.7"):
|
|
silu = _silu_python
|
|
else:
|
|
silu = F.silu
|
|
|
|
|
|
def mish(x):
|
|
return x * torch.tanh(torch.nn.functional.softplus(x))
|
|
|
|
|
|
def linear_act(x):
|
|
return x
|
|
|
|
|
|
ACT2FN = {
|
|
"relu": F.relu,
|
|
"silu": silu,
|
|
"swish": silu,
|
|
"gelu": gelu,
|
|
"tanh": torch.tanh,
|
|
"gelu_new": gelu_new,
|
|
"gelu_fast": gelu_fast,
|
|
"mish": mish,
|
|
"linear": linear_act,
|
|
"sigmoid": torch.sigmoid,
|
|
}
|
|
|
|
|
|
def get_activation(activation_string):
|
|
if activation_string in ACT2FN:
|
|
return ACT2FN[activation_string]
|
|
else:
|
|
raise KeyError("function {} not found in ACT2FN mapping {}".format(activation_string, list(ACT2FN.keys())))
|