pytorch 查看模型的显存占用 pytorch查看模型结构

可视化网格结构

直接print的话，只能得出基础构件的信息，既不能显示出每一层的shape，也不能显示对应参数量的大小

import torchvision.models as models
model = models.resnet18()
print(model)

使用torchinfo可视化网络结构 

trochinfo的使用也是十分简单，我们只需要使用torchinfo.summary()就行了，必需的参数分别是model，input_size[batch_size,channel,h,w]

import torchvision.models as models
from torchinfo import summary
resnet18 = models.resnet18() # 实例化模型
summary(resnet18, (1, 3, 224, 224)) # 1：batch_size 3:图片的通道数 224: 图片的高宽

CNN可视化 

 网络可以通过named_children()的形式查看其层结构，输出gennerater，用字典查看

import torch
from torchvision.models import vgg11

model = vgg11(pretrained=True)
print(dict(model.features.named_children()))

查看特定卷积层的权重，红色是正值，蓝色是负值

conv1 = dict(model.features.named_children())['3']
#卷积层参数情况conv1.weight.detach()
kernel_set = conv1.weight.detach()
num = len(conv1.weight.detach())
print(kernel_set.shape)
for i in range(0,num):
    i_kernel = kernel_set[i]
    plt.figure(figsize=(20, 17))
    if (len(i_kernel)) > 1:
        for idx, filer in enumerate(i_kernel):
            plt.subplot(9, 9, idx+1) 
            plt.axis('off')
            plt.imshow(filer[ :, :].detach(),cmap='bwr')

CNN特征图可视化，特征图和卷积核对应，卷积核是模型的参数，特征图是模型对应的结果。

在PyTorch中，提供了一个专用的接口使得网络在前向传播过程中能够获取到特征图，这个接口的名称非常形象，叫做hook。可以想象这样的场景，数据通过网络向前传播，网络某一层我们预先设置了一个钩子，数据传播过后钩子上会留下数据在这一层的样子，读取钩子的信息就是这一层的特征图。

Hook类中的__call__函数中有module获取这一层的层名，fea_in和fea_out是输入和输出的特征图是什么样的

class Hook(object):
    def __init__(self):
        self.module_name = []
        self.features_in_hook = []
        self.features_out_hook = []

    def __call__(self,module, fea_in, fea_out):
        print("hooker working", self)
        self.module_name.append(module.__class__)
        self.features_in_hook.append(fea_in)
        self.features_out_hook.append(fea_out)
        return None
    

def plot_feature(model, idx, inputs):
    hh = Hook()
    #在相应的层添加hook
    model.features[idx].register_forward_hook(hh)
    
    # forward_model(model,False)
    model.eval（)
    #进行前向传播
    _ = model(inputs)
    #查看module_name
    print(hh.module_name)
    print((hh.features_in_hook[0][0].shape))
    print((hh.features_out_hook[0].shape))
    
    out1 = hh.features_out_hook[0]

    total_ft  = out1.shape[1]
    first_item = out1[0].cpu().clone()    

    plt.figure(figsize=(20, 17))
    

    for ftidx in range(total_ft):
        if ftidx > 99:
            break
        ft = first_item[ftidx]
        plt.subplot(10, 10, ftidx+1) 
        
        plt.axis('off')
        #plt.imshow(ft[ :, :].detach(),cmap='gray')
        plt.imshow(ft[ :, :].detach())

CNN class activation map可视化方法

class activation map （CAM）的作用是判断哪些变量对模型来说是重要的，在CNN可视化的场景下，即判断图像中哪些像素点对预测结果是重要的。

import torch
from torchvision.models import vgg11,resnet18,resnet101,resnext101_32x8d
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np

model = vgg11(pretrained=True)
img_path = './dog.png'
# resize操作是为了和传入神经网络训练图片大小一致
img = Image.open(img_path).resize((224,224))
# 需要将原始图片转为np.float32格式并且在0-1之间 
rgb_img = np.float32(img)/255
plt.imshow(img)

from pytorch_grad_cam import GradCAM,ScoreCAM,GradCAMPlusPlus,AblationCAM,XGradCAM,EigenCAM,FullGrad
from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
from pytorch_grad_cam.utils.image import show_cam_on_image

target_layers = [model.features[-1]]
# 选取合适的类激活图，但是ScoreCAM和AblationCAM需要batch_size
cam = GradCAM(model=model,target_layers=target_layers)
targets = [ClassifierOutputTarget(preds)]   
# 上方preds需要设定，比如ImageNet有1000类，这里可以设为200
grayscale_cam = cam(input_tensor=img_tensor, targets=targets)
grayscale_cam = grayscale_cam[0, :]
cam_img = show_cam_on_image(rgb_img, grayscale_cam, use_rgb=True)
print(type(cam_img))
Image.fromarray(cam_img)

 使用FlashTorch快速实现CNN可视化

import matplotlib.pyplot as plt
import torchvision.models as models
from flashtorch.utils import apply_transforms, load_image
from flashtorch.saliency import Backprop

model = models.alexnet(pretrained=True)
backprop = Backprop(model)

image = load_image('/content/images/great_grey_owl.jpg')
owl = apply_transforms(image)

target_class = 24
backprop.visualize(owl, target_class, guided=True, use_gpu=True)

import torchvision.models as models
from flashtorch.activmax import GradientAscent

model = models.vgg16(pretrained=True)
g_ascent = GradientAscent(model.features)

# specify layer and filter info
conv5_1 = model.features[24]
conv5_1_filters = [45, 271, 363, 489]

g_ascent.visualize(conv5_1, conv5_1_filters, title="VGG16: conv5_1")

使用TensorBoard可视化训练过程

TensorBoard可以可视化模型结构，输入的数据以及训练的过程

先要安装tensorboardX。要先定义两个变量logdir，Log放到什么地方，另一个是port，默认6006。

首先要定义writer,writer指定的path要和tensorboard运行的path一样，这样才能读取你写入的东西。

pip install tensorboardX
#在使用TensorBoard前，我们需要先指定一个文件夹供TensorBoard保存记录下来的数据。然后调用#tensorboard中的SummaryWriter作为上述“记录员”
from tensorboardX import SummaryWriter
writer = SummaryWriter('./runs')
#如果使用PyTorch自带的tensorboard，则采用如下方式import：
from torch.utils.tensorboard import SummaryWriter
#启动tensorboard也很简单，在命令行中输入
tensorboard --logdir=/path/to/logs/ --port=xxxx

TensorBoard模型结构可视化

#首先定义模型：
import torch.nn as nn

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3,out_channels=32,kernel_size = 3)
        self.pool = nn.MaxPool2d(kernel_size = 2,stride = 2)
        self.conv2 = nn.Conv2d(in_channels=32,out_channels=64,kernel_size = 5)
        self.adaptive_pool = nn.AdaptiveMaxPool2d((1,1))
        self.flatten = nn.Flatten()
        self.linear1 = nn.Linear(64,32)
        self.relu = nn.ReLU()
        self.linear2 = nn.Linear(32,1)
        self.sigmoid = nn.Sigmoid()

    def forward(self,x):
        x = self.conv1(x)
        x = self.pool(x)
        x = self.conv2(x)
        x = self.pool(x)
        x = self.adaptive_pool(x)
        x = self.flatten(x)
        x = self.linear1(x)
        x = self.relu(x)
        x = self.linear2(x)
        y = self.sigmoid(x)
        return y

model = Net()
print(model)

#都是给定一个输入数据，前向传播后得到模型的结构，再通过TensorBoard进行可视化，使用add_graph
writer.add_graph(model, input_to_model = torch.rand(1, 3, 224, 224))
writer.close()

 TensorBoard图像可视化

• 对于单张图片的显示使用add_image
• 对于多张图片的显示使用add_images
• 有时需要使用torchvision.utils.make_grid将多张图片拼成一张图片后，用writer.add_image显示

import torchvision
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

transform_train = transforms.Compose(
    [transforms.ToTensor()])
transform_test = transforms.Compose(
    [transforms.ToTensor()])

train_data = datasets.CIFAR10(".", train=True, download=True, transform=transform_train)
test_data = datasets.CIFAR10(".", train=False, download=True, transform=transform_test)
train_loader = DataLoader(train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(test_data, batch_size=64)

images, labels = next(iter(train_loader))
 
# 仅查看一张图片
writer = SummaryWriter('./pytorch_tb')
writer.add_image('images[0]', images[0])
writer.close()
 
# 将多张图片拼接成一张图片，中间用黑色网格分割
# create grid of images
writer = SummaryWriter('./pytorch_tb')
img_grid = torchvision.utils.make_grid(images)
writer.add_image('image_grid', img_grid)
writer.close()
 
# 将多张图片直接写入
writer = SummaryWriter('./pytorch_tb')
writer.add_images("images",images,global_step = 0)
writer.close()

 TensorBoard连续变量可视化

writer1 = SummaryWriter('./pytorch_tb/x')
writer2 = SummaryWriter('./pytorch_tb/y')
for i in range(500):
    x = i
    y = x*2
    writer1.add_scalar("same", x, i) #日志中记录x在第step i 的值
    writer2.add_scalar("same", y, i) #日志中记录y在第step i 的值
writer1.close()
writer2.close()