Basic training process of image classification -- Based on mobilenet_ V3 as an example

Experience summary from b standing up Lord ——7.2.2 Use Pytorch build MobileNetV3 And training based on transfer learning _ Bili, Bili _bilibili

1. use gpu still cpu To deal with

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

2. Define the method of data preprocessing

data_transform = {
        "train": transforms.Compose([transforms.RandomResizedCrop(224),
                                     transforms.RandomHorizontalFlip(),
                                     transforms.ToTensor(),
                                     transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
        "val": transforms.Compose([transforms.Resize(256),
                                   transforms.CenterCrop(224),
                                   transforms.ToTensor(),
                                   transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}

3. Define the dataset file directory

data_root = os.path.abspath(os.path.join(os.getcwd(), "../.."))
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"])

4. Get data set class_to_idx After that, the key and key value are exchanged , Write file after exchange

train_num = len(train_dataset)

    # {'daisy':0, 'dandelion':1, 'roses':2, 'sunflower':3, 'tulips':4}
    flower_list = train_dataset.class_to_idx
    cla_dict = dict((val, key) for key, val in flower_list.items())
    # write dict into json file
    json_str = json.dumps(cla_dict, indent=4)
    with open('class_indices.json', 'w') as json_file:
        json_file.write(json_str)

5. Generate iterators

 train_loader = torch.utils.data.DataLoader(train_dataset,
                                               batch_size=batch_size, shuffle=True,
                                               num_workers=0)

    validate_dataset = datasets.ImageFolder(root=os.path.join(image_path, "val"),
                                            transform=data_transform["val"])
    val_num = len(validate_dataset)
    validate_loader = torch.utils.data.DataLoader(validate_dataset,
                                                  batch_size=batch_size, shuffle=False,
                                                  num_workers=0)

6. Instantiated neural networks

net = mobilenet_v3_large(num_classes=5)

7. Read the pre training weight file and delete the classified weight

# load pretrain weights
    # download url: https://download.pytorch.org/models/mobilenet_v2-b0353104.pth
    model_weight_path = "./mobilenet_v3_large.pth"
    assert os.path.exists(model_weight_path), "file {} dose not exist.".format(model_weight_path)
    pre_weights = torch.load(model_weight_path, map_location=device)

    # delete classifier weights
    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)

8. Freeze some or all weights

# freeze features weights
    for param in net.features.parameters():
        param.requires_grad = False

9. Define the loss function and optimizer

    # define loss function
    loss_function = nn.CrossEntropyLoss()

    # construct an optimizer
    params = [p for p in net.parameters() if p.requires_grad]
    optimizer = optim.Adam(params, lr=0.0001)

10. Start training

best_acc = 0.0
    #  Save training weight path 
    save_path = './MobileNetV3.pth'
    train_steps = len(train_loader)
    for epoch in range(epochs):
        # train
        net.train()
        running_loss = 0.0
        train_bar = tqdm(train_loader)
        for step, data in enumerate(train_bar):
            images, labels = data
            optimizer.zero_grad()
            logits = net(images.to(device))
            loss = loss_function(logits, labels.to(device))
            loss.backward()
            optimizer.step()

            # print statistics
            running_loss += loss.item()

            train_bar.desc = "train epoch[{}/{}] loss:{:.3f}".format(epoch + 1,
                                                                     epochs,
                                                                     loss)

11. Verify and save the training weight file

        # validate
        net.eval()
        acc = 0.0  # accumulate accurate number / epoch
        with torch.no_grad():
            val_bar = tqdm(validate_loader)
            for val_data in val_bar:
                val_images, val_labels = val_data
                outputs = net(val_images.to(device))
                # loss = loss_function(outputs, test_labels)
                predict_y = torch.max(outputs, dim=1)[1]
                acc += torch.eq(predict_y, val_labels.to(device)).sum().item()

                val_bar.desc = "valid epoch[{}/{}]".format(epoch + 1,
                                                           epochs)
        val_accurate = acc / val_num
        print('[epoch %d] train_loss: %.3f  val_accuracy: %.3f' %
              (epoch + 1, running_loss / train_steps, val_accurate))

        if val_accurate > best_acc:
            best_acc = val_accurate
            torch.save(net.state_dict(), save_path)

Attached separately MobileNet_v3 Network code

from typing import Callable, List, Optional

import torch
from torch import nn, Tensor
from torch.nn import functional as F
from functools import partial


def _make_divisible(ch, divisor=8, min_ch=None):
    """
    This function is taken from the original tf repo.
    It ensures that all layers have a channel number that is divisible by 8
    It can be seen here:
    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
    """
    if min_ch is None:
        min_ch = divisor
    new_ch = max(min_ch, int(ch + divisor / 2) // divisor * divisor)
    # Make sure that round down does not go down by more than 10%.
    if new_ch < 0.9 * ch:
        new_ch += divisor
    return new_ch


class ConvBNActivation(nn.Sequential):
    def __init__(self,
                 in_planes: int,
                 out_planes: int,
                 kernel_size: int = 3,
                 stride: int = 1,
                 groups: int = 1,
                 norm_layer: Optional[Callable[..., nn.Module]] = None,
                 activation_layer: Optional[Callable[..., nn.Module]] = None):
        padding = (kernel_size - 1) // 2
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if activation_layer is None:
            activation_layer = nn.ReLU6
        super(ConvBNActivation, self).__init__(nn.Conv2d(in_channels=in_planes,
                                                         out_channels=out_planes,
                                                         kernel_size=kernel_size,
                                                         stride=stride,
                                                         padding=padding,
                                                         groups=groups,
                                                         bias=False),
                                               norm_layer(out_planes),
                                               activation_layer(inplace=True))


#  Attention mechanism 
class SqueezeExcitation(nn.Module):
    def __init__(self, input_c: int, squeeze_factor: int = 4):
        super(SqueezeExcitation, self).__init__()
        squeeze_c = _make_divisible(input_c // squeeze_factor, 8)
        self.fc1 = nn.Conv2d(input_c, squeeze_c, 1)
        self.fc2 = nn.Conv2d(squeeze_c, input_c, 1)

    def forward(self, x: Tensor) -> Tensor:
        scale = F.adaptive_avg_pool2d(x, output_size=(1, 1))
        scale = self.fc1(scale)
        scale = F.relu(scale, inplace=True)
        scale = self.fc2(scale)
        scale = F.hardsigmoid(scale, inplace=True)
        return scale * x


class InvertedResidualConfig:
    def __init__(self,
                 input_c: int,
                 kernel: int,
                 expanded_c: int,
                 out_c: int,
                 use_se: bool,
                 activation: str,
                 stride: int,
                 width_multi: float):
        self.input_c = self.adjust_channels(input_c, width_multi)
        self.kernel = kernel
        self.expanded_c = self.adjust_channels(expanded_c, width_multi)
        self.out_c = self.adjust_channels(out_c, width_multi)
        self.use_se = use_se
        self.use_hs = activation == "HS"  # whether using h-swish activation
        self.stride = stride

    @staticmethod
    def adjust_channels(channels: int, width_multi: float):
        return _make_divisible(channels * width_multi, 8)


class InvertedResidual(nn.Module):
    def __init__(self,
                 cnf: InvertedResidualConfig,
                 norm_layer: Callable[..., nn.Module]):
        super(InvertedResidual, self).__init__()

        if cnf.stride not in [1, 2]:
            raise ValueError("illegal stride value.")

        self.use_res_connect = (cnf.stride == 1 and cnf.input_c == cnf.out_c)

        layers: List[nn.Module] = []
        activation_layer = nn.Hardswish if cnf.use_hs else nn.ReLU

        # expand
        if cnf.expanded_c != cnf.input_c:
            layers.append(ConvBNActivation(cnf.input_c,
                                           cnf.expanded_c,
                                           kernel_size=1,
                                           norm_layer=norm_layer,
                                           activation_layer=activation_layer))

        # depthwise
        layers.append(ConvBNActivation(cnf.expanded_c,
                                       cnf.expanded_c,
                                       kernel_size=cnf.kernel,
                                       stride=cnf.stride,
                                       groups=cnf.expanded_c,
                                       norm_layer=norm_layer,
                                       activation_layer=activation_layer))

        if cnf.use_se:
            layers.append(SqueezeExcitation(cnf.expanded_c))

        # project
        layers.append(ConvBNActivation(cnf.expanded_c,
                                       cnf.out_c,
                                       kernel_size=1,
                                       norm_layer=norm_layer,
                                       activation_layer=nn.Identity))

        self.block = nn.Sequential(*layers)
        self.out_channels = cnf.out_c
        self.is_strided = cnf.stride > 1

    def forward(self, x: Tensor) -> Tensor:
        result = self.block(x)
        if self.use_res_connect:
            result += x

        return result


class MobileNetV3(nn.Module):
    def __init__(self,
                 inverted_residual_setting: List[InvertedResidualConfig],
                 last_channel: int,
                 num_classes: int = 1000,
                 block: Optional[Callable[..., nn.Module]] = None,
                 norm_layer: Optional[Callable[..., nn.Module]] = None):
        super(MobileNetV3, self).__init__()

        if not inverted_residual_setting:
            raise ValueError("The inverted_residual_setting should not be empty.")
        elif not (isinstance(inverted_residual_setting, List) and
                  all([isinstance(s, InvertedResidualConfig) for s in inverted_residual_setting])):
            raise TypeError("The inverted_residual_setting should be List[InvertedResidualConfig]")

        if block is None:
            block = InvertedResidual

        if norm_layer is None:
            norm_layer = partial(nn.BatchNorm2d, eps=0.001, momentum=0.01)

        layers: List[nn.Module] = []

        # building first layer
        firstconv_output_c = inverted_residual_setting[0].input_c
        layers.append(ConvBNActivation(3,
                                       firstconv_output_c,
                                       kernel_size=3,
                                       stride=2,
                                       norm_layer=norm_layer,
                                       activation_layer=nn.Hardswish))
        # building inverted residual blocks
        for cnf in inverted_residual_setting:
            layers.append(block(cnf, norm_layer))

        # building last several layers
        lastconv_input_c = inverted_residual_setting[-1].out_c
        lastconv_output_c = 6 * lastconv_input_c
        layers.append(ConvBNActivation(lastconv_input_c,
                                       lastconv_output_c,
                                       kernel_size=1,
                                       norm_layer=norm_layer,
                                       activation_layer=nn.Hardswish))
        self.features = nn.Sequential(*layers)
        self.avgpool = nn.AdaptiveAvgPool2d(1)
        self.classifier = nn.Sequential(nn.Linear(lastconv_output_c, last_channel),
                                        nn.Hardswish(inplace=True),
                                        nn.Dropout(p=0.2, inplace=True),
                                        nn.Linear(last_channel, num_classes))

        # initial weights
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode="fan_out")
                if m.bias is not None:
                    nn.init.zeros_(m.bias)
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.ones_(m.weight)
                nn.init.zeros_(m.bias)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.zeros_(m.bias)

    def _forward_impl(self, x: Tensor) -> Tensor:
        x = self.features(x)
        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.classifier(x)

        return x

    def forward(self, x: Tensor) -> Tensor:
        return self._forward_impl(x)


def mobilenet_v3_large(num_classes: int = 1000,
                       reduced_tail: bool = False) -> MobileNetV3:
    """
    Constructs a large MobileNetV3 architecture from
    "Searching for MobileNetV3" <https://arxiv.org/abs/1905.02244>.

    weights_link:
    https://download.pytorch.org/models/mobilenet_v3_large-8738ca79.pth

    Args:
        num_classes (int): number of classes
        reduced_tail (bool): If True, reduces the channel counts of all feature layers
            between C4 and C5 by 2. It is used to reduce the channel redundancy in the
            backbone for Detection and Segmentation.
    """
    width_multi = 1.0
    bneck_conf = partial(InvertedResidualConfig, width_multi=width_multi)
    adjust_channels = partial(InvertedResidualConfig.adjust_channels, width_multi=width_multi)

    reduce_divider = 2 if reduced_tail else 1

    inverted_residual_setting = [
        # input_c, kernel, expanded_c, out_c, use_se, activation, stride
        bneck_conf(16, 3, 16, 16, False, "RE", 1),
        bneck_conf(16, 3, 64, 24, False, "RE", 2),  # C1
        bneck_conf(24, 3, 72, 24, False, "RE", 1),
        bneck_conf(24, 5, 72, 40, True, "RE", 2),  # C2
        bneck_conf(40, 5, 120, 40, True, "RE", 1),
        bneck_conf(40, 5, 120, 40, True, "RE", 1),
        bneck_conf(40, 3, 240, 80, False, "HS", 2),  # C3
        bneck_conf(80, 3, 200, 80, False, "HS", 1),
        bneck_conf(80, 3, 184, 80, False, "HS", 1),
        bneck_conf(80, 3, 184, 80, False, "HS", 1),
        bneck_conf(80, 3, 480, 112, True, "HS", 1),
        bneck_conf(112, 3, 672, 112, True, "HS", 1),
        bneck_conf(112, 5, 672, 160 // reduce_divider, True, "HS", 2),  # C4
        bneck_conf(160 // reduce_divider, 5, 960 // reduce_divider, 160 // reduce_divider, True, "HS", 1),
        bneck_conf(160 // reduce_divider, 5, 960 // reduce_divider, 160 // reduce_divider, True, "HS", 1),
    ]
    last_channel = adjust_channels(1280 // reduce_divider)  # C5

    return MobileNetV3(inverted_residual_setting=inverted_residual_setting,
                       last_channel=last_channel,
                       num_classes=num_classes)


def mobilenet_v3_small(num_classes: int = 1000,
                       reduced_tail: bool = False) -> MobileNetV3:
    """
    Constructs a large MobileNetV3 architecture from
    "Searching for MobileNetV3" <https://arxiv.org/abs/1905.02244>.

    weights_link:
    https://download.pytorch.org/models/mobilenet_v3_small-047dcff4.pth

    Args:
        num_classes (int): number of classes
        reduced_tail (bool): If True, reduces the channel counts of all feature layers
            between C4 and C5 by 2. It is used to reduce the channel redundancy in the
            backbone for Detection and Segmentation.
    """
    width_multi = 1.0
    bneck_conf = partial(InvertedResidualConfig, width_multi=width_multi)
    adjust_channels = partial(InvertedResidualConfig.adjust_channels, width_multi=width_multi)

    reduce_divider = 2 if reduced_tail else 1

    inverted_residual_setting = [
        # input_c, kernel, expanded_c, out_c, use_se, activation, stride
        bneck_conf(16, 3, 16, 16, True, "RE", 2),  # C1
        bneck_conf(16, 3, 72, 24, False, "RE", 2),  # C2
        bneck_conf(24, 3, 88, 24, False, "RE", 1),
        bneck_conf(24, 5, 96, 40, True, "HS", 2),  # C3
        bneck_conf(40, 5, 240, 40, True, "HS", 1),
        bneck_conf(40, 5, 240, 40, True, "HS", 1),
        bneck_conf(40, 5, 120, 48, True, "HS", 1),
        bneck_conf(48, 5, 144, 48, True, "HS", 1),
        bneck_conf(48, 5, 288, 96 // reduce_divider, True, "HS", 2),  # C4
        bneck_conf(96 // reduce_divider, 5, 576 // reduce_divider, 96 // reduce_divider, True, "HS", 1),
        bneck_conf(96 // reduce_divider, 5, 576 // reduce_divider, 96 // reduce_divider, True, "HS", 1)
    ]
    last_channel = adjust_channels(1024 // reduce_divider)  # C5

    return MobileNetV3(inverted_residual_setting=inverted_residual_setting,
                       last_channel=last_channel,
                       num_classes=num_classes)