# ***************************************************************
# Copyright (c) 2023 Jittor. All Rights Reserved.
# Maintainers:
# Wenyang Zhou <576825820@qq.com>
# Dun Liang <randonlang@gmail.com>.
#
# This file is subject to the terms and conditions defined in
# file 'LICENSE.txt', which is part of this source code package.
# ***************************************************************
# This model is generated by pytorch converter.
import jittor as jt
from jittor import init
from jittor import nn
__all__ = ['MobileNetV2', 'mobilenet_v2']
def _make_divisible(v, divisor, min_value=None):
if (min_value is None):
min_value = divisor
new_v = max(min_value, ((int((v + (divisor / 2))) // divisor) * divisor))
if (new_v < (0.9 * v)):
new_v += divisor
return new_v
class ConvBNReLU(nn.Sequential):
def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1):
padding = ((kernel_size - 1) // 2)
super(ConvBNReLU, self).__init__(nn.Conv(in_planes, out_planes, kernel_size, stride, padding, groups=groups, bias=False), nn.BatchNorm(out_planes), nn.ReLU6())
class InvertedResidual(nn.Module):
def __init__(self, inp, oup, stride, expand_ratio):
super(InvertedResidual, self).__init__()
self.stride = stride
assert (stride in [1, 2])
hidden_dim = int(round((inp * expand_ratio)))
self.use_res_connect = ((self.stride == 1) and (inp == oup))
layers = []
if (expand_ratio != 1):
layers.append(ConvBNReLU(inp, hidden_dim, kernel_size=1))
layers.extend([ConvBNReLU(hidden_dim, hidden_dim, stride=stride, groups=hidden_dim), nn.Conv(hidden_dim, oup, 1, 1, 0, bias=False), nn.BatchNorm(oup)])
self.conv = nn.Sequential(*layers)
def execute(self, x):
if self.use_res_connect:
return (x + self.conv(x))
else:
return self.conv(x)
[文档]
class MobileNetV2(nn.Module):
'''
MobileNetV2源自论文 `Mobilenetv2: Inverted residuals and linear bottlenecks <https://arxiv.org/abs/1801.04381>`__。mobilenet_v2基于倒置残差结构, 其中使用线性瓶颈在压缩表示中传递消息。
参数:
- num_classes (int, optional): 类别数。默认值: 1000。
- width_mult (float, optional): 宽度乘数 - 按此比例调整每层中通道数。默认值: 1.0。
- init_weights (bool, optional): 是否初始化权重。默认值: True。
- inverted_residual_setting (List[List[int]], optional): 定义网络结构的参数列表, 其中每个元素是一个拥有4个整数的列表, 分别表示扩展因子(t)、输出通道数(c)、重复次数(n)和步幅(s)。默认值: None, 会自动采用MobileNetV2的标准配置。
- round_nearest (int, optional): 将每层的通道数四舍五入为该数的倍数。设为1则取消四舍五入。默认值: 8。
- block (callable[..., nn.Module], optional): 用于指定MobileNet中倒置残差构建块的模块。如果为None, 则使用InvertedResidual。默认值: None。
属性:
- features (nn.Sequential): MobileNetV2的特征提取部分。
- classifier (nn.Sequential): MobileNetV2的分类部分。
代码示例:
>>> import jittor as jt
>>> from jittor.models.mobilenet import MobileNetV2
>>> model = MobileNetV2(num_classes=1000, width_mult=1.0)
>>> print(model)
MobileNetV2(
features: Sequential(
0: ConvBNReLU(
...)))
'''
def __init__(self, num_classes=1000, width_mult=1.0, inverted_residual_setting=None, round_nearest=8, block=None):
super(MobileNetV2, self).__init__()
if (block is None):
block = InvertedResidual
input_channel = 32
last_channel = 1280
if (inverted_residual_setting is None):
inverted_residual_setting = [[1, 16, 1, 1], [6, 24, 2, 2], [6, 32, 3, 2], [6, 64, 4, 2], [6, 96, 3, 1], [6, 160, 3, 2], [6, 320, 1, 1]]
if ((len(inverted_residual_setting) == 0) or (len(inverted_residual_setting[0]) != 4)):
raise ValueError('inverted_residual_setting should be non-empty or a 4-element list, got {}'.format(inverted_residual_setting))
input_channel = _make_divisible((input_channel * width_mult), round_nearest)
self.last_channel = _make_divisible((last_channel * max(1.0, width_mult)), round_nearest)
features = [ConvBNReLU(3, input_channel, stride=2)]
for (t, c, n, s) in inverted_residual_setting:
output_channel = _make_divisible((c * width_mult), round_nearest)
for i in range(n):
stride = (s if (i == 0) else 1)
features.append(block(input_channel, output_channel, stride, expand_ratio=t))
input_channel = output_channel
features.append(ConvBNReLU(input_channel, self.last_channel, kernel_size=1))
self.features = nn.Sequential(*features)
self.classifier = nn.Sequential(nn.Dropout(0.2), nn.Linear(self.last_channel, num_classes))
def _forward_impl(self, x):
x = self.features(x)
x = nn.AdaptiveAvgPool2d(1)(x)
x = jt.reshape(x, (x.shape[0], -1))
x = self.classifier(x)
return x
def execute(self, x):
return self._forward_impl(x)
[文档]
def mobilenet_v2(pretrained=False):
'''
构建一个MobileNetV2模型
MobileNetV2源自论文 `Mobilenetv2: Inverted residuals and linear bottlenecks <https://arxiv.org/abs/1801.04381>`__。mobilenet_v2基于倒置残差结构, 其中使用线性瓶颈在压缩表示中传递消息。
参数:
- `pretrained` (bool, optional): 表示是否预加载预训练模型。默认为 `False`。
返回值:
- 返回构建好的MobileNetV2模型实例。如果 `pretrained` 为 `True`, 则返回在ImageNet上预训练的模型。
代码示例:
>>> import jittor as jt
>>> from jittor.models.mobilenet import *
>>> net = mobilenet_v2(pretrained=False)
>>> x = jt.rand(1, 3, 224, 224)
>>> y = net(x)
>>> y.shape
[1, 1000]
'''
model = MobileNetV2()
if pretrained: model.load("jittorhub://mobilenet_v2.pkl")
return model