task3:PyTorch可视化

可视化网络结构

使用print函数打印模型基础信息

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

使用torchinfo可视化网络结构

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

CNN卷积核可视化

# 在PyTorch中可视化卷积核也非常方便，核心在于特定层的卷积核即特定层的模型权重，可视化卷积核就等价于可视化对应的权重矩阵。下面给出在PyTorch中可视化卷积核的实现方案，以torchvision自带的VGG11模型为例。
# 首先加载模型，并确定模型的层信息
import torch
from torchvision.models import vgg11

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

CNN特征图可视化方法

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):
    hh = Hook()
    model.features[idx].register_forward_hook(hh)
    
    forward_model(model,False)
    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

# 相比可视化卷积核与可视化特征图，CAM系列可视化更为直观，能够一目了然地确定重要区域，进而进行可解释性分析或模型优化改进。
# CAM系列操作的实现可以通过开源工具包pytorch-grad-cam来实现。
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.jpg'
# 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)]
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

# - 可视化梯度
# Download example images
# !mkdir -p images
# !wget -nv \
#    https://github.com/MisaOgura/flashtorch/raw/master/examples/images/great_grey_owl.jpg \
#    https://github.com/MisaOgura/flashtorch/raw/master/examples/images/peacock.jpg   \
#    https://github.com/MisaOgura/flashtorch/raw/master/examples/images/toucan.jpg    \
#    -P /content/images

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)

![ft-gradient](./figures/ft_gradient.png)

# - 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")

![ft-activate](./figures/ft_activate.png)