Pytorch 深度学习特征图可视化——（Yolo网络、rcnn）

写在前面

 想系统学习深度学西可查看weibuweibu123此人博文

下面代码可以对实现特征图的可视化；主要以Yolov4作为例子，使用者仅仅修改自己想可视乎网络的层数或者某层的任意维度

目录

写在前面

        对Yolo系列、r-cnn系列都有较好的表现形式，下面我们以Yolov4网络做详细介绍

1：获得网络的模型结构：

Yolobody(
  (backbone): CSPDarkNet(
    (conv1): BasicConv(
      (conv): Conv2d(3, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (mish): Mish()
    )
    (stages): ModuleList(
      (0): Resblock_body(
        (downsaple_conv): BasicConv(
          (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (mish): Mish()
        )
        (split_conv0): BasicConv(
          (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (mish): Mish()
        )
        (split_conv1): BasicConv(
          (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (mish): Mish()
        )
        (block_conv): Sequential(
          (0): Resblock(
            (block): Sequential(
              (0): BasicConv(
                (conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (mish): Mish()
              )
              (1): BasicConv(
                (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (mish): Mish()
              )
            )
          )

2：定义钩子函数

# 定义钩子函数，获取指定层名称的特征
activation = {} # 保存获取的输出
def get_activation(name):
    def hook(model, input, output):
        activation[name] = output.detach()
    return hook

3：根据钩子函数可视化特征图

比如我们想可视化 上述模型中倒数第六行的卷积层的特征图，我们从模型上发现他的模型位置是：backbone->stage[0]->block_conv[0]->block[1]->conv  !!!!看（）里面的

4：详细代码

import matplotlib.pyplot as plt
import torch
import torch.nn as nn
from torch.nn import functional as F
from torchvision import transforms
import numpy as np
from PIL import Image
from collections import OrderedDict
import cv2
from net.yolov4 import Yolobody

# 定义钩子函数，获取指定层名称的特征
activation = {} # 保存获取的输出
def get_activation(name):
    def hook(model, input, output):
        activation[name] = output.detach()
    return hook

def main():
    anchors_mask    = [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
    #调用模型
    model = Yolobody(anchors_mask,20,False)
    # print(model)
    model.eval()
    # 根据刚刚指定的层数更改
    model.backbone.stages[0].block_conv[0].block[1].conv.register_forward_hook(get_activation('conv')) 
    _,_,_ = model(input_img)
    bn = activation['conv'] # 结果将保存在activation字典中
    print(bn.shape)
    #显示特征图，通过更改下面的代码可以看到64维中任何几维
    plt.figure(figsize=(12,12))
    for i in range(64):
        if i <63:
            continue
        else:
            j=i
            j = j-63
            plt.subplot(1,2,j+1)
            #显示每个通道的特征图因此用灰色显示
            plt.imshow(bn[0,i,:,:], cmap='gray')
            plt.axis('off')
    plt.show()
    return 0

if  __name__=='__main__':
    transform = transforms.Compose([
    transforms.Resize([416,416]),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])
    # 从测试集中读取一张图片，并显示出来
    img_path = 'F:/tupian/0048.jpg'
    img = Image.open(img_path)
    #给图片增加一个N维度
    input_img = transform(img).unsqueeze(0)
    #[1,3,224,224]
    print(input_img.shape)
    # imgarray = np.array(img) / 255.0
    # plt.figure(figsize=(8,8))
    # plt.imshow(imgarray)
    # plt.axis('off')
    # plt.title("the first picture")
    # plt.show()
    # #将图片resize。精度变低
    # image = img.resize([416,416])
    # imgarray = np.array(image) / 255.0
    # plt.figure(figsize=(8,8))
    # plt.imshow(imgarray)
    # plt.title("the second picture")
    # plt.show()
    main()

    # 将图片处理成模型可以预测的形式

5：可视化结果