datawhale 第五次任务打卡

datawhale第五次任务打卡:可视化学习
使用print打印基础模型

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

print model 结果

ResNet(
  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace=True)
  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (layer1): Sequential(
    (0): Bottleneck(
      (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (downsample): Sequential(
        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
   ... ...
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
  (fc): Linear(in_features=2048, out_features=1000, bias=True)
)

printmodel有局限性，不能显示每层shape，也不能显示对应参数量的大小。

2：使用torchinfo
pip install torchinfo
conda install -c conda-forge torchinfo
torchinfo需要看
torchinfo.summary()可以查看具体怎么应用的。
参数model,input_size

使用例子

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

torchinfo可以进行结构化输出。

3：cnn可视化
cnn卷积核
cnn特征图
cnn显著图
加载模型

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

然后具体输出如下

{'0': Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '1': ReLU(inplace=True),
 '2': MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False),
 '3': Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '4': ReLU(inplace=True),
 '5': MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False),
 '6': Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '7': ReLU(inplace=True),
 '8': Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '9': ReLU(inplace=True),
 '10': MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False),
 '11': Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '12': ReLU(inplace=True),
 '13': Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '14': ReLU(inplace=True),
 '15': MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False),
 '16': Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '17': ReLU(inplace=True),
 '18': Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 '19': ReLU(inplace=True),
 '20': MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)}

我们可视化第三层的参数

conv1 = dict(model.features.named_children())['3']
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')

使用hook获取特征图

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()
    model.features[idx].register_forward_hook(hh)
    
    # forward_model(model,False)
    model.eval()
    _ = model(inputs)
    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())

4:使用flashtorch实现cnn可视化
pip install flashtorch

可视化梯度代码

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)

可视化卷积核

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")

5:tensorboard可视化训练过程
pip install tensorboardX

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)

tensorboard图像可视化

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

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

参数分布可视化

import torch
import numpy as np

# 创建正态分布的张量模拟参数矩阵
def norm(mean, std):
    t = std * torch.randn((100, 20)) + mean
    return t
 
writer = SummaryWriter('./pytorch_tb/')
for step, mean in enumerate(range(-10, 10, 1)):
    w = norm(mean, 1)
    writer.add_histogram("w", w, step)
    writer.flush()
writer.close()