You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
74 lines
2.2 KiB
74 lines
2.2 KiB
# Copyright (c) 2022 PaddlePaddle Authors. 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 paddle |
|
import paddle.nn as nn |
|
|
|
from paddle.nn.initializer import TruncatedNormal, Constant, Assign |
|
|
|
# Common initializations |
|
ones_ = Constant(value=1.) |
|
zeros_ = Constant(value=0.) |
|
trunc_normal_ = TruncatedNormal(std=.02) |
|
|
|
|
|
# Common Layers |
|
def drop_path(x, drop_prob=0., training=False): |
|
""" |
|
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). |
|
the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper... |
|
See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... |
|
""" |
|
if drop_prob == 0. or not training: |
|
return x |
|
keep_prob = paddle.to_tensor(1 - drop_prob) |
|
shape = (paddle.shape(x)[0], ) + (1, ) * (x.ndim - 1) |
|
random_tensor = keep_prob + paddle.rand(shape, dtype=x.dtype) |
|
random_tensor = paddle.floor(random_tensor) # binarize |
|
output = x.divide(keep_prob) * random_tensor |
|
return output |
|
|
|
|
|
class DropPath(nn.Layer): |
|
def __init__(self, drop_prob=None): |
|
super(DropPath, self).__init__() |
|
self.drop_prob = drop_prob |
|
|
|
def forward(self, x): |
|
return drop_path(x, self.drop_prob, self.training) |
|
|
|
|
|
class Identity(nn.Layer): |
|
def __init__(self): |
|
super(Identity, self).__init__() |
|
|
|
def forward(self, input): |
|
return input |
|
|
|
|
|
# common funcs |
|
|
|
|
|
def to_2tuple(x): |
|
if isinstance(x, (list, tuple)): |
|
return x |
|
return tuple([x] * 2) |
|
|
|
|
|
def add_parameter(layer, datas, name=None): |
|
parameter = layer.create_parameter( |
|
shape=(datas.shape), default_initializer=Assign(datas)) |
|
if name: |
|
layer.add_parameter(name, parameter) |
|
return parameter
|
|
|