[二十]深度学习Pytorch-Hook函数与CAM算法

0. 往期内容

[一]深度学习Pytorch-张量定义与张量创建

[二]深度学习Pytorch-张量的操作：拼接、切分、索引和变换

[三]深度学习Pytorch-张量数学运算

[四]深度学习Pytorch-线性回归

[五]深度学习Pytorch-计算图与动态图机制

[六]深度学习Pytorch-autograd与逻辑回归

[七]深度学习Pytorch-DataLoader与Dataset(含人民币二分类实战)

[八]深度学习Pytorch-图像预处理transforms

[九]深度学习Pytorch-transforms图像增强(剪裁、翻转、旋转)

[十]深度学习Pytorch-transforms图像操作及自定义方法

[十一]深度学习Pytorch-模型创建与nn.Module

[十二]深度学习Pytorch-模型容器与AlexNet构建

[十三]深度学习Pytorch-卷积层(1D/2D/3D卷积、卷积nn.Conv2d、转置卷积nn.ConvTranspose)

[十四]深度学习Pytorch-池化层、线性层、激活函数层

[十五]深度学习Pytorch-权值初始化

[十六]深度学习Pytorch-18种损失函数loss function

[十七]深度学习Pytorch-优化器Optimizer

[十八]深度学习Pytorch-学习率Learning Rate调整策略

[十九]深度学习Pytorch-可视化工具TensorBoard

[二十]深度学习Pytorch-Hook函数与CAM算法

1. Hook函数概念

2. Hook函数与特征图提取

2.1 Tensor.register_hook

return为tensor的话会将该tensor覆盖原来的梯度。

代码示例：

# ----------------------------------- 1 tensor hook 1 -----------------------------------
flag = 0
# flag = 1
if flag:

    w = torch.tensor([1.], requires_grad=True)
    x = torch.tensor([2.], requires_grad=True)
    a = torch.add(w, x)
    b = torch.add(w, 1)
    y = torch.mul(a, b)

    a_grad = list()

    def grad_hook(grad):
        a_grad.append(grad)

    handle = a.register_hook(grad_hook) #注册到对应的张量上

    y.backward()

    # 查看梯度
    print("gradient:", w.grad, x.grad, a.grad, b.grad, y.grad)
    print("a_grad[0]: ", a_grad[0])
    handle.remove()


# ----------------------------------- 2 tensor hook 2 -----------------------------------
flag = 0
# flag = 1
if flag:

    w = torch.tensor([1.], requires_grad=True)
    x = torch.tensor([2.], requires_grad=True)
    a = torch.add(w, x)
    b = torch.add(w, 1)
    y = torch.mul(a, b)

    a_grad = list()

    def grad_hook(grad):
        grad *= 2

    handle = w.register_hook(grad_hook)

    y.backward()

    # 查看梯度
    print("w.grad: ", w.grad) #输出10，梯度扩大了两倍
    handle.remove()
#######################
    def grad_hook(grad):
        grad *= 2
        return grad*3

    handle = w.register_hook(grad_hook)

    y.backward()

    # 查看梯度
    print("w.grad: ", w.grad) #输出30，将上面输出的10扩大了3倍
    handle.remove()

官网示例：

v = torch.tensor([0., 0., 0.], requires_grad=True)
h = v.register_hook(lambda grad: grad * 2)  # double the gradient
v.backward(torch.tensor([1., 2., 3.]))
v.grad


h.remove()  # removes the hook

2.2 register_forward_hook

代码示例：

flag = 1
if flag:

    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.conv1 = nn.Conv2d(1, 2, 3)
            self.pool1 = nn.MaxPool2d(2, 2)

        def forward(self, x):
            x = self.conv1(x)
            x = self.pool1(x)
            return x

    def forward_hook(module, data_input, data_output):
        fmap_block.append(data_output)
        input_block.append(data_input)

    def forward_pre_hook(module, data_input):
        print("forward_pre_hook input:{}".format(data_input))

    def backward_hook(module, grad_input, grad_output):
        print("backward hook input:{}".format(grad_input))
        print("backward hook output:{}".format(grad_output))

    # 初始化网络
    net = Net()
    net.conv1.weight[0].detach().fill_(1)
    net.conv1.weight[1].detach().fill_(2)
    net.conv1.bias.data.detach().zero_()

    # 注册hook
    fmap_block = list()
    input_block = list()
    net.conv1.register_forward_hook(forward_hook)
    net.conv1.register_forward_pre_hook(forward_pre_hook)
    net.conv1.register_backward_hook(backward_hook)

    # inference
    fake_img = torch.ones((1, 1, 4, 4))   # batch size * channel * H * W
    output = net(fake_img)

    loss_fnc = nn.L1Loss()
    target = torch.randn_like(output)
    loss = loss_fnc(target, output)
    loss.backward()

    # 观察
    print("output shape: {}\noutput value: {}\n".format(output.shape, output))
    print("feature maps shape: {}\noutput value: {}\n".format(fmap_block[0].shape, fmap_block[0]))
    print("input shape: {}\ninput value: {}".format(input_block[0][0].shape, input_block[0]))

2.3 register_forward_pre_hook

2.4 register_backward_hook

3. CAM算法

4. 完整代码

hook_methods.py

# -*- coding:utf-8 -*-
"""
@file name  : hook_methods.py
@brief      : pytorch的hook函数
"""
import torch
import torch.nn as nn
from tools.common_tools import set_seed

set_seed(1)  # 设置随机种子


# ----------------------------------- 1 tensor hook 1 -----------------------------------
flag = 0
# flag = 1
if flag:

    w = torch.tensor([1.], requires_grad=True)
    x = torch.tensor([2.], requires_grad=True)
    a = torch.add(w, x)
    b = torch.add(w, 1)
    y = torch.mul(a, b)

    a_grad = list()

    def grad_hook(grad):
        a_grad.append(grad)

    handle = a.register_hook(grad_hook) #注册到对应的张量上

    y.backward()

    # 查看梯度
    print("gradient:", w.grad, x.grad, a.grad, b.grad, y.grad)
    print("a_grad[0]: ", a_grad[0])
    handle.remove()


# ----------------------------------- 2 tensor hook 2 -----------------------------------
flag = 0
# flag = 1
if flag:

    w = torch.tensor([1.], requires_grad=True)
    x = torch.tensor([2.], requires_grad=True)
    a = torch.add(w, x)
    b = torch.add(w, 1)
    y = torch.mul(a, b)

    a_grad = list()

    def grad_hook(grad):
        grad *= 2

    handle = w.register_hook(grad_hook)

    y.backward()

    # 查看梯度
    print("w.grad: ", w.grad) #输出10，梯度扩大了两倍
    handle.remove()
#######################
    def grad_hook(grad):
        grad *= 2
        return grad*3

    handle = w.register_hook(grad_hook)

    y.backward()

    # 查看梯度
    print("w.grad: ", w.grad) #输出30，将上面输出的10扩大了3倍
    handle.remove()



# ----------------------------------- 3 Module.register_forward_hook and pre hook -----------------------------------
# flag = 0
flag = 1
if flag:

    class Net(nn.Module):
        def __init__(self):
            super(Net, self).__init__()
            self.conv1 = nn.Conv2d(1, 2, 3)
            self.pool1 = nn.MaxPool2d(2, 2)

        def forward(self, x):
            x = self.conv1(x)
            x = self.pool1(x)
            return x

    def forward_hook(module, data_input, data_output):
        fmap_block.append(data_output)
        input_block.append(data_input)

    def forward_pre_hook(module, data_input):
        print("forward_pre_hook input:{}".format(data_input))

    def backward_hook(module, grad_input, grad_output):
        print("backward hook input:{}".format(grad_input))
        print("backward hook output:{}".format(grad_output))

    # 初始化网络
    net = Net()
    net.conv1.weight[0].detach().fill_(1)
    net.conv1.weight[1].detach().fill_(2)
    net.conv1.bias.data.detach().zero_()

    # 注册hook
    fmap_block = list()
    input_block = list()
    net.conv1.register_forward_hook(forward_hook)
    net.conv1.register_forward_pre_hook(forward_pre_hook)
    net.conv1.register_backward_hook(backward_hook)

    # inference
    fake_img = torch.ones((1, 1, 4, 4))   # batch size * channel * H * W
    output = net(fake_img)

    loss_fnc = nn.L1Loss()
    target = torch.randn_like(output)
    loss = loss_fnc(target, output)
    loss.backward()

    # 观察
    print("output shape: {}\noutput value: {}\n".format(output.shape, output))
    print("feature maps shape: {}\noutput value: {}\n".format(fmap_block[0].shape, fmap_block[0]))
    print("input shape: {}\ninput value: {}".format(input_block[0][0].shape, input_block[0]))

hook_fmap_vis.py

# -*- coding:utf-8 -*-
"""
@file name  : hook_fmap_vis.py
@brief      : 采用hook函数可视化特征图
"""
import torch.nn as nn
import numpy as np
from PIL import Image
import torchvision.transforms as transforms
import torchvision.utils as vutils
from torch.utils.tensorboard import SummaryWriter
from tools.common_tools import set_seed
import torchvision.models as models

set_seed(1)  # 设置随机种子

# ----------------------------------- feature map visualization -----------------------------------
# flag = 0
flag = 1
if flag:
    writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")

    # 数据
    path_img = "./lena.png"     # your path to image
    normMean = [0.49139968, 0.48215827, 0.44653124]
    normStd = [0.24703233, 0.24348505, 0.26158768]

    norm_transform = transforms.Normalize(normMean, normStd)
    img_transforms = transforms.Compose([
        transforms.Resize((224, 224)),
        transforms.ToTensor(),
        norm_transform
    ])

    img_pil = Image.open(path_img).convert('RGB')
    if img_transforms is not None:
        img_tensor = img_transforms(img_pil)
    img_tensor.unsqueeze_(0)    # chw --> bchw

    # 模型
    alexnet = models.alexnet(pretrained=True)

    # 注册hook
    fmap_dict = dict()
    for name, sub_module in alexnet.named_modules():

        if isinstance(sub_module, nn.Conv2d):
            key_name = str(sub_module.weight.shape)
            fmap_dict.setdefault(key_name, list())

            n1, n2 = name.split(".")

            def hook_func(m, i, o): #module input output
                key_name = str(m.weight.shape)
                fmap_dict[key_name].append(o)

            alexnet._modules[n1]._modules[n2].register_forward_hook(hook_func) #对所有卷积层注册hook

    # forward
    output = alexnet(img_tensor)

    # add image
    for layer_name, fmap_list in fmap_dict.items():
        fmap = fmap_list[0]
        fmap.transpose_(0, 1)

        nrow = int(np.sqrt(fmap.shape[0]))
        fmap_grid = vutils.make_grid(fmap, normalize=True, scale_each=True, nrow=nrow)
        writer.add_image('feature map in {}'.format(layer_name), fmap_grid, global_step=322)