pytorch入门编程test6_mobilenet

train.py

import os
import sys
import json

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import transforms, datasets
from tqdm import tqdm

from model_v2 import MobileNetV2

def main():
    device=torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    batch_size=16
    epochs=5
    data_transform={
        "train":transforms.Compose([
            transforms.RandomResizedCrop(224),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            transforms.Normalize([0.5,0.5,0.5,],[0.5,0.5,0.5])

        ]),
        "val":transforms.Compose([
            transforms.Resize(256),
            transforms.CenterCrop(224),
            transforms.ToTensor(),
            transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
        ])

    }
    data_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))  # get data root path
    image_path = os.path.join(data_root, "data_set", "flower_data")
    train_dataset=datasets.ImageFolder(root=os.path.join(image_path,"train"),
                                       transform=data_transform["train"])
    train_num=len(train_dataset)
    val_dataset=datasets.ImageFolder(root=os.path.join(image_path,"val"),
                                     transform=data_transform["val"])
    val_num=len(val_dataset)
    flower_list=train_dataset.class_to_idx
    cla_dict=dict((val,key)for key,val in flower_list.items())
    json_str=json.dumps(cla_dict,indent=4)
    with open("class_indices.json","w") as json_file:
        json_file.write(json_str)
    train_loader=torch.utils.data.Dataloader(train_dataset,
                                             batch_size=batch_size,
                                             shuffle=True,
                                             num_worker=nw)
    val_loader=torch.utils.data.Dataloader(val_dataset,
                                           batch_size=batch_size,
                                           shuffle=False,
                                           num_workers=nw)
    net=MobileNetV2(num_classes=5)
    #开始预训练
    model_weights_path="./mobilenet_v2.pth"
    pre_weights=torch.load(model_weights_path,map_location="cpu")
    pre_dict = {k: v for k, v in pre_weights.items() if net.state_dict()[k].numel() == v.numel()}
    missing_keys, unexpected_keys = net.load_state_dict(pre_dict, strict=False)
    for param in net.features.parameters():
        param.requires_grad=False
    net.to(device)
    loss_function=nn.CrossEntropyLoss()
    params=[p for p in net.parameters() if p.requires_grad()]
    optimizer=optim.Adam(params,lr=0.0001)
    best_acc=0.0

    save_path = './MobileNetV2.pth'
    train_steps = len(train_loader)
    for epoch in range(epochs):
        net.train()
        running_loss=0.0
        train_bar=tqdm(train_loader,file=sys.stdout)
        for step,data in enumerate(train_bar):
            images,labels=data
            optimizer.zero_grad()
            logits=net(images.to(device))
            loss=loss_function(logits,labels)
            loss.backward()
            optimizer.step()
            running_loss=running_loss+loss.item()
    net.eval()
    acc=0.0
    with torch.no_grad():
        val_bar=tqdm(val_loader,file=sys.stdout)
        for val_data in val_bar:
            val_images,val_labels=val_data
            output=net(val_images.to(device))
            pre_dict_y=torch.max(output,dim=1)[1]
            acc=acc+torch.eq(pre_dict_y,val_labels.to(device)).sum().item()
    val_acc=acc/val_num
    if val_acc>best_acc:
        best_acc=val_acc
        torch.save(net.state_dict,save_path)

predict.py

import os
import json

import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt

from model_v2 import MobileNetV2

def main():
    device=torch.device("cuda :0" if torch.cuda.is_available() else "cpu")
    data_transform=transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
    ])
    img_path = "../tulip.jpg"
    assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
    img = Image.open(img_path)

    img=data_transform(img)
    img=torch.unsqueeze(img,dim=0)

    json_path = './class_indices.json'
    with open(json_path,"r") as f:
        class_indict=json.load(f)
    model=MobileNetV2(num_classes=5).to(device)
    model_weight_path = "./MobileNetV2.pth"
    model.load_state_dict(torch.load(model_weight_path,map_location=device))
    model.eval()
    with torch.no_grad():
        output=torch.squeeze(model(img.to(device))).cpu()
        predict=torch.softmax(output,dim=0)
        predict_cla=torch.argmax(predict).numpy()
    print_res='class:{} prob:{}'.format(class_indict[str(predict_cla)],
                                        predict[predict_cla].numpy())

model:

import torch.nn as nn
import torch


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
                               kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(out_channel)
        self.relu = nn.ReLU()
        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
                               kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(out_channel)
        self.downsample = downsample

    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(x)

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        out += identity
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    """
    注意：原论文中，在虚线残差结构的主分支上，第一个1x1卷积层的步距是2，第二个3x3卷积层步距是1。
    但在pytorch官方实现过程中是第一个1x1卷积层的步距是1，第二个3x3卷积层步距是2，
    这么做的好处是能够在top1上提升大概0.5%的准确率。
    可参考Resnet v1.5 https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch
    """
    expansion = 4

    def __init__(self, in_channel, out_channel, stride=1, downsample=None,
                 groups=1, width_per_group=64):
        super(Bottleneck, self).__init__()

        width = int(out_channel * (width_per_group / 64.)) * groups

        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width,
                               kernel_size=1, stride=1, bias=False)  # squeeze channels
        self.bn1 = nn.BatchNorm2d(width)
        # -----------------------------------------
        self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, groups=groups,
                               kernel_size=3, stride=stride, bias=False, padding=1)
        self.bn2 = nn.BatchNorm2d(width)
        # -----------------------------------------
        self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel*self.expansion,
                               kernel_size=1, stride=1, bias=False)  # unsqueeze channels
        self.bn3 = nn.BatchNorm2d(out_channel*self.expansion)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = downsample

    def forward(self, x):
        identity = x
        if self.downsample is not None:
            identity = self.downsample(x)

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

        out += identity
        out = self.relu(out)

        return out


class ResNet(nn.Module):

    def __init__(self,
                 block,
                 blocks_num,
                 num_classes=1000,
                 include_top=True,
                 groups=1,
                 width_per_group=64):
        super(ResNet, self).__init__()
        self.include_top = include_top
        self.in_channel = 64

        self.groups = groups
        self.width_per_group = width_per_group

        self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,
                               padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(self.in_channel)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, blocks_num[0])
        self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)
        self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)
        self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)
        if self.include_top:
            self.avgpool = nn.AdaptiveAvgPool2d((1, 1))  # output size = (1, 1)
            self.fc = nn.Linear(512 * block.expansion, num_classes)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')

    def _make_layer(self, block, channel, block_num, stride=1):
        downsample = None
        if stride != 1 or self.in_channel != channel * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(channel * block.expansion))

        layers = []
        layers.append(block(self.in_channel,
                            channel,
                            downsample=downsample,
                            stride=stride,
                            groups=self.groups,
                            width_per_group=self.width_per_group))
        self.in_channel = channel * block.expansion

        for _ in range(1, block_num):
            layers.append(block(self.in_channel,
                                channel,
                                groups=self.groups,
                                width_per_group=self.width_per_group))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        if self.include_top:
            x = self.avgpool(x)
            x = torch.flatten(x, 1)
            x = self.fc(x)

        return x


def resnet34(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet34-333f7ec4.pth
    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)


def resnet50(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet50-19c8e357.pth
    return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)


def resnet101(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnet101-5d3b4d8f.pth
    return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)


def resnext50_32x4d(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth
    groups = 32
    width_per_group = 4
    return ResNet(Bottleneck, [3, 4, 6, 3],
                  num_classes=num_classes,
                  include_top=include_top,
                  groups=groups,
                  width_per_group=width_per_group)


def resnext101_32x8d(num_classes=1000, include_top=True):
    # https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth
    groups = 32
    width_per_group = 8
    return ResNet(Bottleneck, [3, 4, 23, 3],
                  num_classes=num_classes,
                  include_top=include_top,
                  groups=groups,
                  width_per_group=width_per_group)