【AI达人特训营】基于全卷积神经网络的图像分类复现

from __future__ import divisionfrom __future__ import print_functionimport paddleimport paddle.nn as nnfrom paddle.nn import functional as Ffrom paddle.utils.download import get_weights_path_from_urlimport pickleimport numpy as npfrom paddle import callbacksfrom paddle.vision.transforms import (
    ToTensor, RandomHorizontalFlip, RandomResizedCrop, SaturationTransform, Compose,
    HueTransform, BrightnessTransform, ContrastTransform, RandomCrop, Normalize, RandomRotation, Resize
)from paddle.vision.datasets import Cifar10from paddle.io import DataLoaderfrom paddle.optimizer.lr import CosineAnnealingDecay, MultiStepDecay, LinearWarmupimport random

__all__ = []
model_urls = {    'resnet18': ('https://paddle-hapi.bj.bcebos.com/models/resnet18.pdparams',                 'cf548f46534aa3560945be4b95cd11c4'),    'resnet34': ('https://paddle-hapi.bj.bcebos.com/models/resnet34.pdparams',                 '8d2275cf8706028345f78ac0e1d31969'),    'resnet50': ('https://paddle-hapi.bj.bcebos.com/models/resnet50.pdparams',                 'ca6f485ee1ab0492d38f323885b0ad80'),    'resnet101': ('https://paddle-hapi.bj.bcebos.com/models/resnet101.pdparams',                  '02f35f034ca3858e1e54d4036443c92d'),    'resnet152': ('https://paddle-hapi.bj.bcebos.com/models/resnet152.pdparams',                  '7ad16a2f1e7333859ff986138630fd7a'),
}class BottleneckBlock(nn.Layer):

    expansion = 4

    def __init__(self,
                 inplanes,
                 planes,
                 stride=1,
                 downsample=None,
                 groups=1,
                 base_width=64,
                 dilation=1,
                 norm_layer=None):
        super(BottleneckBlock, self).__init__()        if norm_layer is None:
            norm_layer = nn.BatchNorm2D
        width = int(planes * (base_width / 64.)) * groups
        self.width = width
        self.conv1 = nn.Conv2D(inplanes, width, 1, bias_attr=False)
        self.bn1 = norm_layer(width)
        self.conv2 = nn.Conv2D(
            width,
            width,            3,
            padding=dilation,
            stride=stride,
            groups=groups,
            dilation=dilation,
            bias_attr=False)
        self.bn2 = norm_layer(width)
        self.conv3 = nn.Conv2D(
            width, planes * self.expansion, 1, bias_attr=False)
        self.width_2 = planes * self.expansion
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU()
        self.downsample = downsample
        self.stride = stride    def forward(self, x):
        identity = 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)        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        out = self.relu(out)        return outclass ResNet(nn.Layer):
    """ResNet model from
    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_

    Args:
        Block (BasicBlock|BottleneckBlock): block module of model.
        depth (int): layers of resnet, default: 50.
        num_classes (int): output dim of last fc layer. If num_classes <=0, last fc layer
                            will not be defined. Default: 1000.
        with_pool (bool): use pool before the last fc layer or not. Default: True.

    Examples:
        .. code-block:: python

            from paddle.vision.models import ResNet
            from paddle.vision.models.resnet import BottleneckBlock, BasicBlock

            resnet50 = ResNet(BottleneckBlock, 50)

            resnet18 = ResNet(BasicBlock, 18)

    """

    def __init__(self, block, depth, num_classes=10, with_pool=False):
        super(ResNet, self).__init__()
        layer_cfg = {            18: [2, 2, 2, 2],            34: [3, 4, 6, 3],            50: [3, 4, 6, 3],            101: [3, 4, 23, 3],            152: [3, 8, 36, 3]
        }
        layers = layer_cfg[depth]
        self.num_classes = num_classes
        self.with_pool = with_pool
        self._norm_layer = nn.BatchNorm2D

        self.inplanes = 64
        self.dilation = 1

        self.conv1 = nn.Conv2D(            3,
            self.inplanes,
            kernel_size=7,
            stride=2,
            padding=3,
            bias_attr=False)
        self.bn1 = self._norm_layer(self.inplanes)
        self.relu = nn.ReLU()        # self.maxpool = nn.MaxPool2D(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)        if with_pool:
            self.avgpool = nn.AdaptiveAvgPool2D((1, 1))        if num_classes > 0:
            self.fc = nn.Linear(512 * block.expansion, num_classes)
        self.final_conv = nn.Conv2D(512 * block.expansion, 1024, 2)
        self.final_conv2 = nn.Conv2D(1024, 10, 1)    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
        norm_layer = self._norm_layer
        downsample = None
        previous_dilation = self.dilation        if dilate:
            self.dilation *= stride
            stride = 1
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2D(
                    self.inplanes,
                    planes * block.expansion,                    1,
                    stride=stride,
                    bias_attr=False),
                norm_layer(planes * block.expansion), )

        layers = []
        layers.append(
            block(self.inplanes, planes, stride, downsample, 1, 64,
                  previous_dilation, norm_layer))
        self.inplanes = planes * block.expansion        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes, norm_layer=norm_layer))        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)        ### 
        # 更改为全卷积层 
        ###

        # if self.with_pool:
        #     x = self.avgpool(x)

        # if self.num_classes > 0:
        #     x = paddle.flatten(x, 1)
        #     x = self.fc(x)

        ### 
        # 全卷积层 
        ###
        
        x = self.final_conv(x)
        x = self.final_conv2(x)
        x = x.reshape([-1, 10], -1)        return xdef _resnet(arch, Block, depth, pretrained, **kwargs):
    model = ResNet(Block, depth, **kwargs)    if pretrained:        assert arch in model_urls, "{} model do not have a pretrained model now, you should set pretrained=False".format(
            arch)
        weight_path = get_weights_path_from_url(model_urls[arch][0],
                                                model_urls[arch][1])

        param = paddle.load(weight_path)
        model.set_dict(param)    return modeldef resnet50(pretrained=False, **kwargs):
    """ResNet 50-layer model

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet

    Examples:
        .. code-block:: python

            from paddle.vision.models import resnet50

            # build model
            model = resnet50()

            # build model and load imagenet pretrained weight
            # model = resnet50(pretrained=True)
    """
    return _resnet('resnet50', BottleneckBlock, 50, pretrained, **kwargs)

net = resnet50()
paddle.summary(net, (1,3,32,32))

class ToArray(object):
    def __call__(self, img):
        img = np.array(img)
        img = np.transpose(img, [2, 0, 1])
        img = img / 255.
        return img.astype('float32')class RandomApply(object):
    def __init__(self, transform, p=0.5):
        super().__init__()
        self.p = p
        self.transform = transform        

    def __call__(self, img):
        if self.p < random.random():            return img
        img = self.transform(img)        return img                                                                                                                    
class LRSchedulerM(callbacks.LRScheduler):                                                                                                           
    def __init__(self, by_step=False, by_epoch=True, warm_up=True):                                                                                                
        super().__init__(by_step, by_epoch)                                                                                                                          
        assert by_step ^ warm_up
        self.warm_up = warm_up        
    def on_epoch_end(self, epoch, logs=None):
        if self.by_epoch and not self.warm_up:            if self.model._optimizer and hasattr(
                self.model._optimizer, '_learning_rate') and isinstance(
                    self.model._optimizer._learning_rate, paddle.optimizer.lr.LRScheduler):                                                                                         
                self.model._optimizer._learning_rate.step()                                                                                          
                                                                                                                                                     
    def on_train_batch_end(self, step, logs=None):                                                                                                   
        if self.by_step or self.warm_up:                                                                                                                             
            if self.model._optimizer and hasattr(
                self.model._optimizer, '_learning_rate') and isinstance(
                    self.model._optimizer._learning_rate, paddle.optimizer.lr.LRScheduler):                                                                                         
                self.model._optimizer._learning_rate.step()            if self.model._optimizer._learning_rate.last_epoch >= self.model._optimizer._learning_rate.warmup_steps:
                self.warm_up = Falsedef _on_train_batch_end(self, step, logs=None):
    logs = logs or {}
    logs['lr'] = self.model._optimizer.get_lr()
    self.train_step += 1
    if self._is_write():
        self._updates(logs, 'train')def _on_train_begin(self, logs=None):
    self.epochs = self.params['epochs']    assert self.epochs
    self.train_metrics = self.params['metrics'] + ['lr']    assert self.train_metrics
    self._is_fit = True
    self.train_step = 0callbacks.VisualDL.on_train_batch_end = _on_train_batch_end
callbacks.VisualDL.on_train_begin = _on_train_begin

model = paddle.Model(resnet50())# 加载checkpoint# model.load('output/ResNet50-FCN/299.pdparams')MAX_EPOCH = 300LR = 0.01WEIGHT_DECAY = 5e-4MOMENTUM = 0.9BATCH_SIZE = 256CIFAR_MEAN = [0.5071, 0.4865, 0.4409]
CIFAR_STD = [0.1942, 0.1918, 0.1958]
DATA_FILE = Nonemodel.prepare(
    paddle.optimizer.Momentum(
        learning_rate=LinearWarmup(CosineAnnealingDecay(LR, MAX_EPOCH), 2000, 0., LR),
        momentum=MOMENTUM,
        parameters=model.parameters(),
        weight_decay=WEIGHT_DECAY),
    paddle.nn.CrossEntropyLoss(),
    paddle.metric.Accuracy(topk=(1,5)))# 定义数据集增强方式transforms = Compose([
    RandomCrop(32, padding=4),
    RandomApply(BrightnessTransform(0.1)),
    RandomApply(ContrastTransform(0.1)),
    RandomHorizontalFlip(),
    RandomRotation(15),
    ToArray(),
    Normalize(CIFAR_MEAN, CIFAR_STD),    # Resize(size=224)])
val_transforms = Compose([ToArray(), Normalize(CIFAR_MEAN, CIFAR_STD)])# 加载训练和测试数据集train_set = Cifar10(DATA_FILE, mode='train', transform=transforms)
test_set = Cifar10(DATA_FILE, mode='test', transform=val_transforms)# 定义保存方式和训练可视化checkpoint_callback = paddle.callbacks.ModelCheckpoint(save_freq=1, save_dir='output/ResNet50-FCN')
callbacks = [LRSchedulerM(),checkpoint_callback, callbacks.VisualDL('vis_logs/resnet50_FCN.log')]# 训练模型model.fit(
    train_set,
    test_set,
    epochs=MAX_EPOCH, 
    batch_size=BATCH_SIZE,
    shuffle=True,
    num_workers=4,
    verbose=1, 
    callbacks=callbacks,
)

model = paddle.Model(paddle.vision.models.resnet50(pretrained=False))# 加载checkpoint# model.load('output/ResNet50/299.pdparams')MAX_EPOCH = 300LR = 0.01WEIGHT_DECAY = 5e-4MOMENTUM = 0.9BATCH_SIZE = 256CIFAR_MEAN = [0.5071, 0.4865, 0.4409]
CIFAR_STD = [0.1942, 0.1918, 0.1958]
DATA_FILE = Nonemodel.prepare(
    paddle.optimizer.Momentum(
        learning_rate=LinearWarmup(CosineAnnealingDecay(LR, MAX_EPOCH), 2000, 0., LR),
        momentum=MOMENTUM,
        parameters=model.parameters(),
        weight_decay=WEIGHT_DECAY),
    paddle.nn.CrossEntropyLoss(),
    paddle.metric.Accuracy(topk=(1,5)))# 定义数据集增强方式transforms = Compose([
    RandomCrop(32, padding=4),
    RandomApply(BrightnessTransform(0.1)),
    RandomApply(ContrastTransform(0.1)),
    RandomHorizontalFlip(),
    RandomRotation(15),
    ToArray(),
    Normalize(CIFAR_MEAN, CIFAR_STD),
])
val_transforms = Compose([ToArray(), Normalize(CIFAR_MEAN, CIFAR_STD)])# 加载训练和测试数据集train_set = Cifar100(DATA_FILE, mode='train', transform=transforms)
test_set = Cifar100(DATA_FILE, mode='test', transform=val_transforms)# 定义保存方式和训练可视化checkpoint_callback = paddle.callbacks.ModelCheckpoint(save_freq=1, save_dir='output/ResNet50')
callbacks = [LRSchedulerM(),checkpoint_callback, callbacks.VisualDL('vis_logs/resnet50.log')]# 训练模型model.fit(
    train_set,
    test_set,
    epochs=MAX_EPOCH, 
    batch_size=BATCH_SIZE,
    shuffle=True,
    num_workers=4,
    verbose=1, 
    callbacks=callbacks,
)