From 49e6da014500bcba3bfbb6033c1ead09b2b20c29 Mon Sep 17 00:00:00 2001
From: "Eric.Lee2021" <305141918@qq.com>
Date: Fri, 12 Mar 2021 01:04:24 +0800
Subject: [PATCH] add mobile mobilenet & shfflenetv1

---
 models/mobilenetv2.py  | 105 +++++++++++++++++
 models/shufflenet.py   | 254 +++++++++++++++++++++++++++++++++++++++++
 models/shufflenetv2.py |   4 +-
 train.py               |  13 ++-
 4 files changed, 371 insertions(+), 5 deletions(-)
 create mode 100644 models/mobilenetv2.py
 create mode 100644 models/shufflenet.py

diff --git a/models/mobilenetv2.py b/models/mobilenetv2.py
new file mode 100644
index 0000000..7cd6062
--- /dev/null
+++ b/models/mobilenetv2.py
@@ -0,0 +1,105 @@
+"""mobilenetv2 in pytorch
+
+
+
+[1] Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen
+
+    MobileNetV2: Inverted Residuals and Linear Bottlenecks
+    https://arxiv.org/abs/1801.04381
+"""
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class LinearBottleNeck(nn.Module):
+
+    def __init__(self, in_channels, out_channels, stride, t=6, class_num=100):
+        super().__init__()
+
+        self.residual = nn.Sequential(
+            nn.Conv2d(in_channels, in_channels * t, 1),
+            nn.BatchNorm2d(in_channels * t),
+            nn.ReLU6(inplace=True),
+
+            nn.Conv2d(in_channels * t, in_channels * t, 3, stride=stride, padding=1, groups=in_channels * t),
+            nn.BatchNorm2d(in_channels * t),
+            nn.ReLU6(inplace=True),
+
+            nn.Conv2d(in_channels * t, out_channels, 1),
+            nn.BatchNorm2d(out_channels)
+        )
+
+        self.stride = stride
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+
+    def forward(self, x):
+
+        residual = self.residual(x)
+
+        if self.stride == 1 and self.in_channels == self.out_channels:
+            residual += x
+
+        return residual
+
+class MobileNetV2(nn.Module):
+
+    def __init__(self, num_classes=100,dropout_factor = 1.0):
+        super().__init__()
+
+        self.pre = nn.Sequential(
+            nn.Conv2d(3, 32, 1, padding=1),
+            nn.BatchNorm2d(32),
+            nn.ReLU6(inplace=True)
+        )
+
+        self.stage1 = LinearBottleNeck(32, 16, 1, 1)
+        self.stage2 = self._make_stage(2, 16, 24, 2, 6)
+        self.stage3 = self._make_stage(3, 24, 32, 2, 6)
+        self.stage4 = self._make_stage(4, 32, 64, 2, 6)
+        self.stage5 = self._make_stage(3, 64, 96, 1, 6)
+        self.stage6 = self._make_stage(3, 96, 160, 1, 6)
+        self.stage7 = LinearBottleNeck(160, 320, 1, 6)
+
+        self.conv1 = nn.Sequential(
+            nn.Conv2d(320, 1280, 1),
+            nn.BatchNorm2d(1280),
+            nn.ReLU6(inplace=True)
+        )
+
+        self.conv2 = nn.Conv2d(1280, num_classes, 1)
+
+        self.dropout = nn.Dropout(dropout_factor)
+
+    def forward(self, x):
+        x = self.pre(x)
+        x = self.stage1(x)
+        x = self.stage2(x)
+        x = self.stage3(x)
+        x = self.stage4(x)
+        x = self.stage5(x)
+        x = self.stage6(x)
+        x = self.stage7(x)
+        x = self.conv1(x)
+        x = F.adaptive_avg_pool2d(x, 1)
+        x = self.dropout(x)
+        x = self.conv2(x)
+        x = x.view(x.size(0), -1)
+
+        return x
+
+    def _make_stage(self, repeat, in_channels, out_channels, stride, t):
+
+        layers = []
+        layers.append(LinearBottleNeck(in_channels, out_channels, stride, t))
+
+        while repeat - 1:
+            layers.append(LinearBottleNeck(out_channels, out_channels, 1, t))
+            repeat -= 1
+
+        return nn.Sequential(*layers)
+
+def mobilenetv2():
+    return MobileNetV2()
diff --git a/models/shufflenet.py b/models/shufflenet.py
new file mode 100644
index 0000000..0cd8d2c
--- /dev/null
+++ b/models/shufflenet.py
@@ -0,0 +1,254 @@
+"""shufflenet in pytorch
+
+
+
+[1] Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun.
+
+    ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
+    https://arxiv.org/abs/1707.01083v2
+"""
+
+from functools import partial
+
+import torch
+import torch.nn as nn
+
+
+class BasicConv2d(nn.Module):
+
+    def __init__(self, input_channels, output_channels, kernel_size, **kwargs):
+        super().__init__()
+        self.conv = nn.Conv2d(input_channels, output_channels, kernel_size, **kwargs)
+        self.bn = nn.BatchNorm2d(output_channels)
+        self.relu = nn.ReLU(inplace=True)
+
+    def forward(self, x):
+        x = self.conv(x)
+        x = self.bn(x)
+        x = self.relu(x)
+        return x
+
+class ChannelShuffle(nn.Module):
+
+    def __init__(self, groups):
+        super().__init__()
+        self.groups = groups
+
+    def forward(self, x):
+        batchsize, channels, height, width = x.data.size()
+        channels_per_group = int(channels / self.groups)
+
+        #"""suppose a convolutional layer with g groups whose output has
+        #g x n channels; we first reshape the output channel dimension
+        #into (g, n)"""
+        x = x.view(batchsize, self.groups, channels_per_group, height, width)
+
+        #"""transposing and then flattening it back as the input of next layer."""
+        x = x.transpose(1, 2).contiguous()
+        x = x.view(batchsize, -1, height, width)
+
+        return x
+
+class DepthwiseConv2d(nn.Module):
+
+    def __init__(self, input_channels, output_channels, kernel_size, **kwargs):
+        super().__init__()
+        self.depthwise = nn.Sequential(
+            nn.Conv2d(input_channels, output_channels, kernel_size, **kwargs),
+            nn.BatchNorm2d(output_channels)
+        )
+
+    def forward(self, x):
+        return self.depthwise(x)
+
+class PointwiseConv2d(nn.Module):
+    def __init__(self, input_channels, output_channels, **kwargs):
+        super().__init__()
+        self.pointwise = nn.Sequential(
+            nn.Conv2d(input_channels, output_channels, 1, **kwargs),
+            nn.BatchNorm2d(output_channels)
+        )
+
+    def forward(self, x):
+        return self.pointwise(x)
+
+class ShuffleNetUnit(nn.Module):
+
+    def __init__(self, input_channels, output_channels, stage, stride, groups):
+        super().__init__()
+
+        #"""Similar to [9], we set the number of bottleneck channels to 1/4
+        #of the output channels for each ShuffleNet unit."""
+        self.bottlneck = nn.Sequential(
+            PointwiseConv2d(
+                input_channels,
+                int(output_channels / 4),
+                groups=groups
+            ),
+            nn.ReLU(inplace=True)
+        )
+
+        #"""Note that for Stage 2, we do not apply group convolution on the first pointwise
+        #layer because the number of input channels is relatively small."""
+        if stage == 2:
+            self.bottlneck = nn.Sequential(
+                PointwiseConv2d(
+                    input_channels,
+                    int(output_channels / 4),
+                    groups=groups
+                ),
+                nn.ReLU(inplace=True)
+            )
+
+        self.channel_shuffle = ChannelShuffle(groups)
+
+        self.depthwise = DepthwiseConv2d(
+            int(output_channels / 4),
+            int(output_channels / 4),
+            3,
+            groups=int(output_channels / 4),
+            stride=stride,
+            padding=1
+        )
+
+        self.expand = PointwiseConv2d(
+            int(output_channels / 4),
+            output_channels,
+            groups=groups
+        )
+
+        self.relu = nn.ReLU(inplace=True)
+        self.fusion = self._add
+        self.shortcut = nn.Sequential()
+
+        #"""As for the case where ShuffleNet is applied with stride,
+        #we simply make two modifications (see Fig 2 (c)):
+        #(i) add a 3 × 3 average pooling on the shortcut path;
+        #(ii) replace the element-wise addition with channel concatenation,
+        #which makes it easy to enlarge channel dimension with little extra
+        #computation cost.
+        if stride != 1 or input_channels != output_channels:
+            self.shortcut = nn.AvgPool2d(3, stride=2, padding=1)
+
+            self.expand = PointwiseConv2d(
+                int(output_channels / 4),
+                output_channels - input_channels,
+                groups=groups
+            )
+
+            self.fusion = self._cat
+
+    def _add(self, x, y):
+        return torch.add(x, y)
+
+    def _cat(self, x, y):
+        return torch.cat([x, y], dim=1)
+
+    def forward(self, x):
+        shortcut = self.shortcut(x)
+
+        shuffled = self.bottlneck(x)
+        shuffled = self.channel_shuffle(shuffled)
+        shuffled = self.depthwise(shuffled)
+        shuffled = self.expand(shuffled)
+
+        output = self.fusion(shortcut, shuffled)
+        output = self.relu(output)
+
+        return output
+
+class ShuffleNet(nn.Module):
+
+    def __init__(self, num_blocks = [2,4,2], num_classes=100, groups=3, dropout_factor = 1.0):
+        super().__init__()
+
+        if groups == 1:
+            out_channels = [24, 144, 288, 567]
+        elif groups == 2:
+            out_channels = [24, 200, 400, 800]
+        elif groups == 3:
+            out_channels = [24, 240, 480, 960]
+        elif groups == 4:
+            out_channels = [24, 272, 544, 1088]
+        elif groups == 8:
+            out_channels = [24, 384, 768, 1536]
+
+        self.conv1 = BasicConv2d(3, out_channels[0], 3, padding=1, stride=1)
+        self.input_channels = out_channels[0]
+
+        self.stage2 = self._make_stage(
+            ShuffleNetUnit,
+            num_blocks[0],
+            out_channels[1],
+            stride=2,
+            stage=2,
+            groups=groups
+        )
+
+        self.stage3 = self._make_stage(
+            ShuffleNetUnit,
+            num_blocks[1],
+            out_channels[2],
+            stride=2,
+            stage=3,
+            groups=groups
+        )
+
+        self.stage4 = self._make_stage(
+            ShuffleNetUnit,
+            num_blocks[2],
+            out_channels[3],
+            stride=2,
+            stage=4,
+            groups=groups
+        )
+
+        self.avg = nn.AdaptiveAvgPool2d((1, 1))
+        self.fc = nn.Linear(out_channels[3], num_classes)
+        self.dropout = nn.Dropout(dropout_factor)
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.stage2(x)
+        x = self.stage3(x)
+        x = self.stage4(x)
+        x = self.avg(x)
+        x = x.view(x.size(0), -1)
+        x = self.dropout(x)
+        x = self.fc(x)
+
+        return x
+
+    def _make_stage(self, block, num_blocks, output_channels, stride, stage, groups):
+        """make shufflenet stage
+
+        Args:
+            block: block type, shuffle unit
+            out_channels: output depth channel number of this stage
+            num_blocks: how many blocks per stage
+            stride: the stride of the first block of this stage
+            stage: stage index
+            groups: group number of group convolution
+        Return:
+            return a shuffle net stage
+        """
+        strides = [stride] + [1] * (num_blocks - 1)
+
+        stage = []
+
+        for stride in strides:
+            stage.append(
+                block(
+                    self.input_channels,
+                    output_channels,
+                    stride=stride,
+                    stage=stage,
+                    groups=groups
+                )
+            )
+            self.input_channels = output_channels
+
+        return nn.Sequential(*stage)
+
+def shufflenet():
+    return ShuffleNet([4, 8, 4])
diff --git a/models/shufflenetv2.py b/models/shufflenetv2.py
index 5164161..a94f9a7 100644
--- a/models/shufflenetv2.py
+++ b/models/shufflenetv2.py
@@ -99,7 +99,7 @@ class ShuffleUnit(nn.Module):
 
 class ShuffleNetV2(nn.Module):
 
-    def __init__(self, ratio=1., class_num=100, dropout_factor = 1.0):
+    def __init__(self, ratio=1., num_classes=100, dropout_factor = 1.0):
         super().__init__()
         if ratio == 0.5:
             out_channels = [48, 96, 192, 1024]
@@ -126,7 +126,7 @@ class ShuffleNetV2(nn.Module):
             nn.ReLU(inplace=True)
         )
 
-        self.fc = nn.Linear(out_channels[3], class_num)
+        self.fc = nn.Linear(out_channels[3], num_classes)
 
         self.dropout = nn.Dropout(dropout_factor)
 
diff --git a/train.py b/train.py
index eb8cfc6..35f9399 100644
--- a/train.py
+++ b/train.py
@@ -17,6 +17,8 @@ from hand_data_iter.datasets import *
 from models.resnet import resnet50,resnet101
 from models.squeezenet import squeezenet1_1,squeezenet1_0
 from models.shufflenetv2 import ShuffleNetV2
+from models.shufflenet import ShuffleNet
+from models.mobilenetv2 import MobileNetV2
 from loss.loss import *
 import cv2
 import time
@@ -44,7 +46,12 @@ def trainer(ops,f_log):
         elif ops.model == "squeezenet1_1":
             model_ = squeezenet1_1(pretrained=True, num_classes=ops.num_classes,dropout_factor=ops.dropout)
         elif ops.model == "shufflenetv2":
-            model_ = ShuffleNetV2(ratio=1., class_num=ops.num_classes, dropout_factor=ops.dropout)
+            model_ = ShuffleNetV2(ratio=1., num_classes=ops.num_classes, dropout_factor=ops.dropout)
+        elif ops.model == "shufflenet":
+            model_ = ShuffleNet(num_blocks = [2,4,2], num_classes=ops.num_classes, groups=3, dropout_factor = ops.dropout)
+        elif ops.model == "mobilenetv2":
+            model_ = MobileNetV2(num_classes=ops.num_classes , dropout_factor = ops.dropout)
+
         else:
             print(" no support the model")
 
@@ -156,8 +163,8 @@ if __name__ == "__main__":
         help = 'seed') # 设置随机种子
     parser.add_argument('--model_exp', type=str, default = './model_exp',
         help = 'model_exp') # 模型输出文件夹
-    parser.add_argument('--model', type=str, default = 'shufflenetv2',
-        help = 'model : resnet_34,resnet_50,resnet_101,squeezenet1_0,squeezenet1_1,shufflenetv2') # 模型类型
+    parser.add_argument('--model', type=str, default = 'mobilenetv2',
+        help = 'model : resnet_34,resnet_50,resnet_101,squeezenet1_0,squeezenet1_1,shufflenetv2,shufflenet,mobilenetv2') # 模型类型
     parser.add_argument('--num_classes', type=int , default = 42,
         help = 'num_classes') #  landmarks 个数*2
     parser.add_argument('--GPUS', type=str, default = '0',
-- 
GitLab