使用pytorch查看中间层特征矩阵以及卷积核参数

推荐一个可视化工具：TensorBoard

注：
本次所使用的为AlexNet与ResNet34俩个网络，关于这俩个网络的详细信息可以在我另外俩篇blog查看

• ResNet——CNN经典网络模型详解(pytorch实现)
• AlexNet–CNN经典网络模型详解（pytorch实现）

查看中间层特征矩阵

AlexNet

alexnet_model.py

import torch.nn as nn
import torch



class AlexNet(nn.Module):
    def __init__(self, num_classes=1000, init_weights=False):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 48, kernel_size=11, stride=4, padding=2),  # input[3, 224, 224]  output[48, 55, 55]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[48, 27, 27]
            nn.Conv2d(48, 128, kernel_size=5, padding=2),           # output[128, 27, 27]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 13, 13]
            nn.Conv2d(128, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 192, kernel_size=3, padding=1),          # output[192, 13, 13]
            nn.ReLU(inplace=True),
            nn.Conv2d(192, 128, kernel_size=3, padding=1),          # output[128, 13, 13]
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),                  # output[128, 6, 6]
        )
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            nn.Linear(128 * 6 * 6, 2048),
            nn.ReLU(inplace=True),
            nn.Dropout(p=0.5),
            nn.Linear(2048, 2048),
            nn.ReLU(inplace=True),
            nn.Linear(2048, num_classes),
        )
        if init_weights:
            self._initialize_weights()

    def forward(self, x):
        outputs = []
        for name, module in self.features.named_children():
            x = module(x)
            if name in ["0", "3", "6"]:
                outputs.append(x)

        return outputs

    def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                nn.init.constant_(m.bias, 0)

在 for name, module in self.features.named_children():设置一个断点来确认name是否为conv

analyze_feature_map.py

import torch
from alexnet_model import AlexNet
from resnet_model import resnet34
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
from torchvision import transforms

#图像预处理，要与生成alexnet.pth文件的train预处理一致
data_transform = transforms.Compose(
    [transforms.Resize((224, 224)),
     transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

# data_transform = transforms.Compose(
#     [transforms.Resize(256),
#      transforms.CenterCrop(224),
#      transforms.ToTensor(),
#      transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])

# create model
model = AlexNet(num_classes=5)
# model = resnet34(num_classes=5)
# load model weights
model_weight_path = "./AlexNet.pth"  # "./resNet34.pth"
model.load_state_dict(torch.load(model_weight_path))
print(model)

# load image
img = Image.open("roses.jpg")
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)

# forward
out_put = model(img)
for feature_map in out_put:
    # [N, C, H, W] -> [C, H, W]
    im = np.squeeze(feature_map.detach().numpy())
    # [C, H, W] -> [H, W, C]print(model)
    im = np.transpose(im, [1, 2, 0])

    # show top 12 feature maps
    plt.figure()
    for i in range(12):
        ax = plt.subplot(3, 4, i+1)#行，列，索引
        # [H, W, C]
        plt.imshow(im[:, :, i], cmap='gray')#cmap默认为蓝绿图
    plt.show()

图中的俩个.pth文件为训练模型所生成，所以文件目录应该为

在out_put = model(img)设置一个断点，来查看print(model)的信息
在for feature_map in out_put:设置断点out_put = model(img)
原图

其输出为：
conv1：
conv2：
conv3

若将plt.imshow(im[:, :, i], cmap=‘gray’)中 cmap='gray’去掉

ResnetNet34

resnet_model.py

import torch.nn as nn
import torch


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_channel, out_channel, stride=1, downsample=None):
        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):
    expansion = 4

    def __init__(self, in_channel, out_channel, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,
                               kernel_size=1, stride=1, bias=False)  # squeeze channels
        self.bn1 = nn.BatchNorm2d(out_channel)
        # -----------------------------------------
        self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,
                               kernel_size=3, stride=stride, bias=False, padding=1)
        self.bn2 = nn.BatchNorm2d(out_channel)
        # -----------------------------------------
        self.conv3 = nn.Conv2d(in_channels=out_channel, 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):
        super(ResNet, self).__init__()
        self.include_top = include_top
        self.in_channel = 64

        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))
        self.in_channel = channel * block.expansion

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

        return nn.Sequential(*layers)

    def forward(self, x):
        outputs = []
        x = self.conv1(x)
        outputs.append(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)#仅查看layer1
        outputs.append(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 outputs


def resnet34(num_classes=1000, include_top=True):
    return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)


def resnet101(num_classes=1000, include_top=True):
    return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)

analyze_feature_map.py

import torch
from alexnet_model import AlexNet
from resnet_model import resnet34
import matplotlib.pyplot as plt
import numpy as np
from PIL import Image
from torchvision import transforms

#图像预处理，要与生成alexnet.pth文件的train预处理一致
# data_transform = transforms.Compose(
#     [transforms.Resize((224, 224)),
#      transforms.ToTensor(),
#      transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

data_transform = transforms.Compose(
    [transforms.Resize(256),
     transforms.CenterCrop(224),
     transforms.ToTensor(),
     transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])

# create model
# model = AlexNet(num_classes=5)
model = resnet34(num_classes=5)
# load model weights
model_weight_path = "./resNet34.pth"  # "./resNet34.pth"
model.load_state_dict(torch.load(model_weight_path))
print(model)

# load image
img = Image.open("roses.jpg")
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)

# forward
out_put = model(img)
for feature_map in out_put:
    # [N, C, H, W] -> [C, H, W]
    im = np.squeeze(feature_map.detach().numpy())
    # [C, H, W] -> [H, W, C]print(model)
    im = np.transpose(im, [1, 2, 0])

    # show top 12 feature maps
    plt.figure()
    for i in range(12):
        ax = plt.subplot(3, 4, i+1)#行，列，索引
        # [H, W, C]
        plt.imshow(im[:, :, i])#cmap默认为蓝绿图
    plt.show()

在img = Image.open(“roses.jpg”)设置断点打印model层结构为
最终的输出为

对比可以发现resnet比alexnet更加好

查看卷积核参数

AlnexNet

analyze_kernel_weight.py

import torch
from alexnet_model import AlexNet
from resnet_model import resnet34
import matplotlib.pyplot as plt
import numpy as np


# create model
model = AlexNet(num_classes=5)
# model = resnet34(num_classes=5)
# load model weights
model_weight_path = "./AlexNet.pth"  # "resNet34.pth"
model.load_state_dict(torch.load(model_weight_path))
print(model)

weights_keys = model.state_dict().keys()
for key in weights_keys:
    # remove num_batches_tracked para(in bn)
    if "num_batches_tracked" in key:
        continue
    # [kernel_number, kernel_channel, kernel_height, kernel_width]
    weight_t = model.state_dict()[key].numpy()

    # read a kernel information
    # k = weight_t[0, :, :, :]

    # calculate mean, std, min, max
    weight_mean = weight_t.mean()
    weight_std = weight_t.std(ddof=1)
    weight_min = weight_t.min()
    weight_max = weight_t.max()
    print("mean is {}, std is {}, min is {}, max is {}".format(weight_mean,
                                                               weight_std,
                                                               weight_max,
                                                               weight_min))

    # plot hist image
    plt.close()
    weight_vec = np.reshape(weight_t, [-1])
    plt.hist(weight_vec, bins=50)
    plt.title(key)
    plt.show()

在weights_keys = model.state_dict().keys()设置断点来单步运行查看weights_keys
卷积核1kernel值分布
卷积核1偏置分布
下面也都一样

ResNet34

analyze_kernel_weight.py

import torch
from alexnet_model import AlexNet
from resnet_model import resnet34
import matplotlib.pyplot as plt
import numpy as np


# create model
# model = AlexNet(num_classes=5)
model = resnet34(num_classes=5)
# load model weights
model_weight_path = "./resNet34.pth"  # "resNet34.pth"
model.load_state_dict(torch.load(model_weight_path))
print(model)

weights_keys = model.state_dict().keys()
for key in weights_keys:
    # remove num_batches_tracked para(in bn)
    if "num_batches_tracked" in key:
        continue
    # [kernel_number, kernel_channel, kernel_height, kernel_width]
    weight_t = model.state_dict()[key].numpy()

    # read a kernel information
    # k = weight_t[0, :, :, :]

    # calculate mean, std, min, max
    weight_mean = weight_t.mean()
    weight_std = weight_t.std(ddof=1)
    weight_min = weight_t.min()
    weight_max = weight_t.max()
    print("mean is {}, std is {}, min is {}, max is {}".format(weight_mean,
                                                               weight_std,
                                                               weight_max,
                                                               weight_min))

    # plot hist image
    plt.close()
    weight_vec = np.reshape(weight_t, [-1])
    plt.hist(weight_vec, bins=50)
    plt.title(key)
    plt.show()

卷积层
BN层
对BN忘记同学可以查看Batch Normalization（BN）超详细解析
weight为 $\gamma$参数
bias为 $\beta$参数
mean就是 $\mu$参数
var就是 $\sigma^{2}$