学习李沐动手学深度学习中的实现ssd

代码已注释,运行时出现小问题在代码后说明。

import torch
import torchvision
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l
import matplotlib.pyplot as plt


def cls_predictor(num_inputs, num_anchors, num_classes):
    # 输入通道数:num_inputs,
    # 输出通道数:锚框的个数num_anchors×(类别数num_classes+背景类1),
    # 此时高宽没有归一化,所以卷积核3×3,填充1,保证输出高宽和输入高宽一样。
    return nn.Conv2d(num_inputs,
                     num_anchors * (num_classes + 1),
                     kernel_size=3, padding=1)


def bbox_predictor(num_inputs, num_anchors):
    # 每个锚框4个偏移量值故乘4。
    return nn.Conv2d(num_inputs, num_anchors * 4, kernel_size=3, padding=1)


def forward(x, block):
    # 返回block块输出。
    return block(x)


# 测试张量维度
Y1 = forward(torch.zeros((2, 8, 20, 20)), cls_predictor(8, 5, 10))
Y2 = forward(torch.zeros((2, 16, 10, 10)), cls_predictor(16, 3, 10))
print(Y1.shape, Y2.shape)
# 结果torch.Size([2, 55, 20, 20]) torch.Size([2, 33, 10, 10])
# 特征图尺度改变除了批量之外,其他都发生变化,55与33是预测输出通道个数。(批量大小,通道数,高度,宽度)


def flatten_pred(pred):
    # 利用permute函数进行换序操作,把通道数放在最后。
    # start_dim=1沿维度1拉成:批量数×(高×宽×通道数)的二维张量,为了下面拼接。
    # 换序操作避免类别预测在flatten后相距较远。
    return torch.flatten(pred.permute(0, 2, 3, 1), start_dim=1)


def concat_preds(preds):
    # 沿一维度拼接。
    return torch.cat([flatten_pred(p) for p in preds], dim=1)


# 测试沿一维度拼接结果55 * 20 * 20 + 33 * 10 * 10 = 25300,
# 结果:torch.Size([2, 25300])
print(concat_preds([Y1, Y2]).shape)


# 定义一个简单的CNN网络,输入维度in_channels,输出out_channels,高宽减半。
def down_sample_blk(in_channels, out_channels):
    blk = []
    # 卷积,BN层,ReLU激活函数,重复两次。
    for _ in range(2):
        blk.append(nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1))
        blk.append(nn.BatchNorm2d(out_channels))
        blk.append(nn.ReLU())
        in_channels = out_channels
    # 池化层默认步长等于2,形成高宽减半的效果。
    blk.append(nn.MaxPool2d(2))
    # 放在Sequential中。加星:*args:接收若干个位置参数,转换成元组tuple形式。
    return nn.Sequential(*blk)


print(forward(torch.zeros((2, 3, 20, 20)), down_sample_blk(3, 10)).shape)
# 结果:torch.Size([2, 10, 10, 10]),高和宽减半块会更改输入通道的数量,并将输入特征图的高度和宽度减半。


def base_net():
    blk = []
    num_filters = [3, 16, 32, 64]
    # 通道3-16-32-64,通道数翻倍,高宽减半。
    for i in range(len(num_filters) - 1):
        blk.append(down_sample_blk(num_filters[i], num_filters[i+1]))
    return nn.Sequential(*blk)


print(forward(torch.zeros((2, 3, 256, 256)), base_net()).shape)
# torch.Size([2, 64, 32, 32])
# 通道3×2^3,256/2^3


def get_blk(i):
    if i == 0:
        blk = base_net()
    elif i == 1:
        blk = down_sample_blk(64, 128)
    elif i == 4:
        # 全局最大池化,高宽变1。
        blk = nn.AdaptiveMaxPool2d((1,1))
    # i等于2或3通道数没有改变因为数据集小,通道数没必要搞太大。
    else:
        blk = down_sample_blk(128, 128)
    return blk


def blk_forward(X, blk, size, ratio, cls_predictor, bbox_predictor):
    # 算出特征图Y
    Y = blk(X)
    # 在特征图Y尺度下面锚框缩放比和宽高比。
    # 锚框只要Y的高和宽不需要具体值,故可以提前生成。
    anchors = d2l.multibox_prior(Y, sizes=size, ratios=ratio)
    # 类别预测。
    cls_preds = cls_predictor(Y)
    # 偏移预测。
    bbox_preds = bbox_predictor(Y)
    return (Y, anchors, cls_preds, bbox_preds)


# 覆盖率从小到大
sizes = [[0.2, 0.272],
         [0.37, 0.447],
         [0.54, 0.619],
         [0.71, 0.79],
         [0.88, 0.961]]
# 宽高比常用组合×5个
ratios = [[1, 2, 0.5]] * 5
# n+m-1
num_anchors = len(sizes[0]) + len(ratios[0]) - 1


# 简版SSD
class TinySSD(nn.Module):
    def __init__(self, num_classes, **kwargs):
        super(TinySSD, self).__init__(**kwargs)
        # 类别数
        self.num_classes = num_classes
        # 5个块的输出channel数
        idx_to_in_channels = [64, 128, 128, 128, 128]
        for i in range(5):
            # 即赋值语句self.blk_i=get_blk(i)
            # setattr用法:
            # Sets the named attribute on the given object to the specified value.
            # setattr(x, 'y', v) is equivalent to ``x.y = v''
            # 调用get_blk函数遍历每个块,同时对每个块分别进行类别预测和偏移预测。
            setattr(self, f'blk_{i}', get_blk(i))
            setattr(self, f'cls_{i}', cls_predictor(idx_to_in_channels[i],
                                                    num_anchors, num_classes))
            setattr(self, f'bbox_{i}', bbox_predictor(idx_to_in_channels[i],
                                                      num_anchors))

    def forward(self, X):
        anchors, cls_preds, bbox_preds = [None] * 5, [None] * 5, [None] * 5
        for i in range(5):
            # getattr(self,'blk_%d'%i)即访问self.blk_i
            # 除了X,其余都存起来了
            X, anchors[i], cls_preds[i], bbox_preds[i] = blk_forward(
                X, getattr(self, f'blk_{i}'), sizes[i], ratios[i],
                getattr(self, f'cls_{i}'), getattr(self, f'bbox_{i}'))
        anchors = torch.cat(anchors, dim=1)
        cls_preds = concat_preds(cls_preds)
        # 0维不动,1维未知,2维为预测类别加背景(+1)。
        cls_preds = cls_preds.reshape(cls_preds.shape[0], -1, self.num_classes + 1)
        bbox_preds = concat_preds(bbox_preds)
        return anchors, cls_preds, bbox_preds


net = TinySSD(num_classes=1)
# 测试维度
X = torch.zeros((32, 3, 256, 256))
anchors, cls_preds, bbox_preds = net(X)

print('output anchors:', anchors.shape)
print('output class preds:', cls_preds.shape)
print('output bbox preds:', bbox_preds.shape)
# 结果:
# 5440个锚框,每个框四个参数定义
# output anchors: torch.Size([1, 5444, 4])
# 批量32,5440个锚框,对每个锚框分类,定义的类别num_classes=1,加上背景,等于2。
# output class preds: torch.Size([32, 5444, 2])
# 每个锚框四个预测5444×4
# output bbox preds: torch.Size([32, 21776])

batch_size = 32
# 香蕉数据集,类别为1(香蕉)
train_iter, _ = d2l.load_data_bananas(batch_size)

device, net = d2l.try_gpu(), TinySSD(num_classes=1)
# 梯度下降法,优化器,学习率,weight_decay权值衰减。
trainer = torch.optim.SGD(net.parameters(), lr=0.2, weight_decay=5e-4)
# 损失函数:交叉熵损失函数
cls_loss = nn.CrossEntropyLoss(reduction='none')
# 均绝对误差
bbox_loss = nn.L1Loss(reduction='none')


def calc_loss(cls_preds, cls_labels, bbox_preds, bbox_labels, bbox_masks):
    batch_size, num_classes = cls_preds.shape[0], cls_preds.shape[2]
    # 类别的损失函数,预测的类别和标注的类别,第二次reshape第0维为批量大小,然后沿第一个维度取平均值。
    cls = cls_loss(cls_preds.reshape(-1, num_classes), cls_labels.reshape(-1)).reshape(batch_size, -1).mean(dim=1)
    # 都乘个masks,当锚框对应背景框masks为0,意味着背景框不用预测偏移量,沿着第一个维度取平均值。
    bbox = bbox_loss(bbox_preds * bbox_masks, bbox_labels * bbox_masks).mean(dim=1)
    # 返回两个损失(误差)之和。
    return cls + bbox


# 我们可以沿用准确率评价分类结果。
# 由于偏移量使用了范数损失,我们使用平均绝对误差来评价边界框的预测结果。
# 这些预测结果是从生成的锚框及其预测偏移量中获得的。
def cls_eval(cls_preds, cls_labels):
    # 由于类别预测结果放在最后一维,argmax需要指定最后一维。
    return float((cls_preds.argmax(dim=-1).type(cls_labels.dtype) == cls_labels).sum())


def bbox_eval(bbox_preds, bbox_labels, bbox_masks):
    # abs取绝对值
    return float((torch.abs((bbox_labels - bbox_preds) * bbox_masks)).sum())


# 训练模型
num_epochs, timer = 10, d2l.Timer()
# 画图
animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
                        legend=['class error', 'bbox mae'])
net = net.to(device)
for epoch in range(num_epochs):
    # 训练精确度的和,训练精确度的和中的示例数
    # 绝对误差的和,绝对误差的和中的示例数
    metric = d2l.Accumulator(4)
    net.train()
    for features, target in train_iter:
        timer.start()
        trainer.zero_grad()
        X, Y = features.to(device), target.to(device)
        # 生成多尺度的锚框,为每个锚框预测类别和偏移量
        anchors, cls_preds, bbox_preds = net(X)
        # 为每个锚框标注类别和偏移量
        bbox_labels, bbox_masks, cls_labels = d2l.multibox_target(anchors, Y)
        # 根据类别和偏移量的预测和标注值计算损失函数
        l = calc_loss(cls_preds, cls_labels, bbox_preds, bbox_labels,
                      bbox_masks)
        l.mean().backward()
        trainer.step()
        metric.add(cls_eval(cls_preds, cls_labels), cls_labels.numel(),
                   bbox_eval(bbox_preds, bbox_labels, bbox_masks),
                   bbox_labels.numel())
    cls_err, bbox_mae = 1 - metric[0] / metric[1], metric[2] / metric[3]
    animator.add(epoch + 1, (cls_err, bbox_mae))
print(f'class err {cls_err:.2e}, bbox mae {bbox_mae:.2e}')
print(f'{len(train_iter.dataset) / timer.stop():.1f} examples/sec on '
      f'{str(device)}')
plt.show()

# 预测
X = torchvision.io.read_image('../img/banana.jpg').unsqueeze(0).float()
img = X.squeeze(0).permute(1, 2, 0).long()


def predict(X):
    net.eval()
    anchors, cls_preds, bbox_preds = net(X.to(device))
    # softmax函数相当于概率
    cls_probs = F.softmax(cls_preds, dim=2).permute(0, 2, 1)
    output = d2l.multibox_detection(cls_probs, bbox_preds, anchors)
    idx = [i for i, row in enumerate(output[0]) if row[0] != -1]
    return output[0, idx]


output = predict(X)


# 筛选0.9以下的边界框
def display(img, output, threshold):
    d2l.set_figsize((5, 5))
    fig = d2l.plt.imshow(img)
    for row in output:
        score = float(row[1])
        if score < threshold:
            continue
        h, w = img.shape[0:2]
        bbox = [row[2:6] * torch.tensor((w, h, w, h), device=row.device)]
        d2l.show_bboxes(fig.axes, bbox, '%.2f' % score, 'w')


display(img, output.cpu(), threshold=0.9)
plt.show()

结果,gpu1050ti:

torch.Size([2, 55, 20, 20]) torch.Size([2, 33, 10, 10])
torch.Size([2, 25300])
torch.Size([2, 10, 10, 10])
torch.Size([2, 64, 32, 32])
D:\anaconda\envs\pytorch\lib\site-packages\torch\functional.py:445: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at  ..\aten\src\ATen\native\TensorShape.cpp:2157.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
output anchors: torch.Size([1, 5444, 4])
output class preds: torch.Size([32, 5444, 2])
output bbox preds: torch.Size([32, 21776])
read 1000 training examples
read 100 validation examples
class err 3.80e-03, bbox mae 3.77e-03 3493.3 examples/sec on cuda:0

学习李沐动手学深度学习中的实现ssd_第1张图片

学习李沐动手学深度学习中的实现ssd_第2张图片 

细节:由于用的pycharm,故

%matplotlib inline

 这个是不行的,根据网上经验,得调用

import matplotlib.pyplot as plt

并在结尾

plt.show()

将图片打印出来。

但是在本程序中如果仅仅是在结尾出加上plt.show( ),会出现如下不正常现象:

学习李沐动手学深度学习中的实现ssd_第3张图片

并报错:

UserWarning: Tight layout not applied. The left and right margins cannot be made large enough to accommodate all axes decorations. 

根据报错去找网上经验,并不适用。在编写代码时输出训练结果图片并没有出现问题,故怀疑加上预测结果图片后,不能通过在程序结尾加上plt.show()分别输出两个图片。

经过不断尝试:

将训练程序下面和预测结果下面分别加上plt.show(),可在程序中看plt.show()的位置,问题解决!

你可能感兴趣的:(pytorch)