使用torchinfo工具包，学习网络结构可视化的方案
import os import numpy as np import torch import torchvision.models as models from torchinfo import summary resnet18 = models.resnet18() resnet18
summary(resnet18, (1, 3, 224, 224))
输出：
========================================================================================== Layer (type:depth-idx) Output Shape Param # ========================================================================================== ResNet [1, 1000] -- ├─Conv2d: 1-1 [1, 64, 112, 112] 9,408 ├─BatchNorm2d: 1-2 [1, 64, 112, 112] 128 ├─ReLU: 1-3 [1, 64, 112, 112] -- ├─MaxPool2d: 1-4 [1, 64, 56, 56] -- ├─Sequential: 1-5 [1, 64, 56, 56] -- │ └─BasicBlock: 2-1 [1, 64, 56, 56] -- │ │ └─Conv2d: 3-1 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-2 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-3 [1, 64, 56, 56] -- │ │ └─Conv2d: 3-4 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-5 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-6 [1, 64, 56, 56] -- │ └─BasicBlock: 2-2 [1, 64, 56, 56] -- │ │ └─Conv2d: 3-7 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-8 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-9 [1, 64, 56, 56] -- │ │ └─Conv2d: 3-10 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-11 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-12 [1, 64, 56, 56] -- ├─Sequential: 1-6 [1, 128, 28, 28] -- │ └─BasicBlock: 2-3 [1, 128, 28, 28] -- │ │ └─Conv2d: 3-13 [1, 128, 28, 28] 73,728 │ │ └─BatchNorm2d: 3-14 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-15 [1, 128, 28, 28] -- │ │ └─Conv2d: 3-16 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-17 [1, 128, 28, 28] 256 │ │ └─Sequential: 3-18 [1, 128, 28, 28] 8,448 │ │ └─ReLU: 3-19 [1, 128, 28, 28] -- │ └─BasicBlock: 2-4 [1, 128, 28, 28] -- │ │ └─Conv2d: 3-20 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-21 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-22 [1, 128, 28, 28] -- │ │ └─Conv2d: 3-23 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-24 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-25 [1, 128, 28, 28] -- ├─Sequential: 1-7 [1, 256, 14, 14] -- │ └─BasicBlock: 2-5 [1, 256, 14, 14] -- │ │ └─Conv2d: 3-26 [1, 256, 14, 14] 294,912 │ │ └─BatchNorm2d: 3-27 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-28 [1, 256, 14, 14] -- │ │ └─Conv2d: 3-29 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-30 [1, 256, 14, 14] 512 │ │ └─Sequential: 3-31 [1, 256, 14, 14] 33,280 │ │ └─ReLU: 3-32 [1, 256, 14, 14] -- │ └─BasicBlock: 2-6 [1, 256, 14, 14] -- │ │ └─Conv2d: 3-33 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-34 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-35 [1, 256, 14, 14] -- │ │ └─Conv2d: 3-36 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-37 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-38 [1, 256, 14, 14] -- ├─Sequential: 1-8 [1, 512, 7, 7] -- │ └─BasicBlock: 2-7 [1, 512, 7, 7] -- │ │ └─Conv2d: 3-39 [1, 512, 7, 7] 1,179,648 │ │ └─BatchNorm2d: 3-40 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-41 [1, 512, 7, 7] -- │ │ └─Conv2d: 3-42 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-43 [1, 512, 7, 7] 1,024 │ │ └─Sequential: 3-44 [1, 512, 7, 7] 132,096 │ │ └─ReLU: 3-45 [1, 512, 7, 7] -- │ └─BasicBlock: 2-8 [1, 512, 7, 7] -- │ │ └─Conv2d: 3-46 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-47 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-48 [1, 512, 7, 7] -- │ │ └─Conv2d: 3-49 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-50 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-51 [1, 512, 7, 7] -- ├─AdaptiveAvgPool2d: 1-9 [1, 512, 1, 1] -- ├─Linear: 1-10 [1, 1000] 513,000 ========================================================================================== Total params: 11,689,512 Trainable params: 11,689,512 Non-trainable params: 0 Total mult-adds (G): 1.81 ========================================================================================== Input size (MB): 0.60 Forward/backward pass size (MB): 39.75 Params size (MB): 46.76 Estimated Total Size (MB): 87.11 ==========================================================================================2. 可视化CNN卷积核
确定并寻找卷积层，并可视化卷积层中的卷积核
from matplotlib import pyplot as plt
conv1 = dict(resnet18.named_children())["conv1"]
kernel_set = conv1.weight.cpu().detach()
num = len(conv1.weight.cpu().detach())
print(num, 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")
64 torch.Size([64, 3, 7, 7]) D:anacondaenvspytorch_enclibsite-packagesipykernel_launcher.py:8: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
3. 可视化特征图这里用到了PyTorch中的hook接口,相当于数据进行前向传播过程中的特征图会被hook捕捉，前向传播之后可以另行查看
tip:除了这里使用的自定义hook之外,还可以使用PyTorch自带的nn.Module.register_ forward_hook0等方式,可以自行查阅官方文档学习~
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
inputs = torch.rand(1,3,224,224).cuda()
hh = Hook()
dict(resnet18.named_children())["conv1"].register_forward_hook(hh)
resnet18.eval()
_= resnet18(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(ftI : : J.detach().cmap= 'gray ")
plt.imshow(ft[ :,: ].detach())
hooker working <__main__.Hook object at 0x00000249594C3A88> [4. 可视化Class Activation Map（CAM）] torch.Size([1, 3, 224, 224]) torch.Size([1, 64, 112, 112])
如果要研究分类模型某一层对于输出某一类的“激活效果”，往往使用CAM的方式。可以借助grad-cam工具包快速实现
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) grad_cam5. 使用TensorBoard可视化模型结构
首先安装pip install tensorboardx
运行：tensorboard --logdir=/path/to/logs/ --port=xxxx
from tensorboardX import SummaryWriter
writer = SummaryWriter('./tb_logs/')
writer.add_graph(model, input_to_model = torch.rand(1, 3, 224, 224))
writer.close()
6. 使用TensorBoard可视化图像
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()
7. 使用TensorBoard可视化连续变量
TensorBoard可以用来可视化连续变量（或时序变量）的变化过程，通过add_scalar实现：
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()如果想在同一张图中显示多个曲线，则需要分别建立存放子路径（使用SummaryWriter指定路径即可自动创建，但需要在tensorboard运行目录下），同时在add_scalar中修改曲线的标签使其一致即可：
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()
如果想在同一张图中显示多个曲线，则需要分别建立存放子路径（使用SummaryWriter指定路径即可自动创建，但需要在tensorboard运行目录下），同时在add_scalar中修改曲线的标签使其一致即可：
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()
