学习笔记|Pytorch使用教程21(TensorBoard使用（二）)

学习笔记|Pytorch使用教程21

本学习笔记主要摘自“深度之眼”，做一个总结，方便查阅。
使用Pytorch版本为1.2

• add_image and torchvision.utils.make_grid
• AlexNet卷积核与特征图可视化
• add_graph and torchsummary

一.add_image and torchvision.utils.make_grid

1.add_image()
功能:记录图像

• tag:图像的标签名，图的唯一标识
• img_tensor :图像数据，注意尺度
• global_step : x轴
• dataformats :数据形式，CHW, HWC，HW

测试代码：

import os
import torch
import time
import torchvision.models as models
import torchvision.transforms as transforms
import torchvision.utils as vutils
from tools.my_dataset import RMBDataset
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader
from tools.common_tools import set_seed
from model.lenet import LeNet


set_seed(1)  # 设置随机种子


# ----------------------------------- 3 image -----------------------------------
# flag = 0
flag = 1
if flag:

    writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")

    # img 1     random
    fake_img = torch.randn(3, 512, 512)
    writer.add_image("fake_img", fake_img, 1)
    time.sleep(1)

    # img 2     ones
    fake_img = torch.ones(3, 512, 512)
    time.sleep(1)
    writer.add_image("fake_img", fake_img, 2)

    # img 3     1.1
    fake_img = torch.ones(3, 512, 512) * 1.1
    time.sleep(1)
    writer.add_image("fake_img", fake_img, 3)

    # img 4     HW
    fake_img = torch.rand(512, 512)
    writer.add_image("fake_img", fake_img, 4, dataformats="HW")

    # img 5     HWC
    fake_img = torch.rand(512, 512, 3)
    writer.add_image("fake_img", fake_img, 5, dataformats="HWC")

    writer.close()

查看可视化输出：
查看img1：fake_img = torch.randn(3, 512, 512)

查看img2：fake_img = torch.ones(3, 512, 512)
这里的 是一个全为一的tensor，会认为这个tensor的区间为[0, 1]，所以会自动 *255，使其区间为[0, 255]，乘以255之后，图像的像素值为255，所以图像是白色的。

查看img3:fake_img = torch.ones(3, 512, 512) * 1.1
由于乘以1.1之后，最大值大于1了，认为区间为[0, 255], 所以图像是黑色的。

查看img4:fake_img = torch.rand(512, 512)
这是一张单通道的灰度图

查看img5：fake_img = torch.rand(512, 512, 3)

2.torchvision.utils.make_ grid
功能:制作网格图像

• tensor :图像数据，BCH*W形式
• nrow:行数(列数自动计算)
• padding :图像间距(像素单位)
• normalize :是否将像素值标准化
• range:标准化范围
• scale_each:是否单张图维度标准化
• pad_value : padding的像素值

测试代码：

# ----------------------------------- 4 make_grid -----------------------------------
# flag = 0
flag = 1
if flag:
    writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")

    split_dir = os.path.join("..", "..", "data", "rmb_split")
    train_dir = os.path.join(split_dir, "train")
    # train_dir = "path to your training data"

    transform_compose = transforms.Compose([transforms.Resize((32, 64)), transforms.ToTensor()])
    train_data = RMBDataset(data_dir=train_dir, transform=transform_compose)
    train_loader = DataLoader(dataset=train_data, batch_size=16, shuffle=True)
    data_batch, label_batch = next(iter(train_loader))

    # img_grid = vutils.make_grid(data_batch, nrow=4, normalize=True, scale_each=True)
    img_grid = vutils.make_grid(data_batch, nrow=4, normalize=False, scale_each=False)
    writer.add_image("input img", img_grid, 0)

    writer.close()

可视化结果：

当设置：img_grid = vutils.make_grid(data_batch, nrow=4, normalize=True, scale_each=True)

二.AlexNet卷积核与特征图可视化

1.卷积核可视化
测试代码：

import torch.nn as nn
from PIL import Image
import torchvision.transforms as transforms
from torch.utils.tensorboard import SummaryWriter
import torchvision.utils as vutils
from tools.common_tools import set_seed
import torchvision.models as models

set_seed(1)  # 设置随机种子


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

    alexnet = models.alexnet(pretrained=True)

    kernel_num = -1
    vis_max = 1

    for sub_module in alexnet.modules():
        if isinstance(sub_module, nn.Conv2d):
            kernel_num += 1
            if kernel_num > vis_max:
                break
            kernels = sub_module.weight
            c_out, c_int, k_w, k_h = tuple(kernels.shape)

            for o_idx in range(c_out):
                kernel_idx = kernels[o_idx, :, :, :].unsqueeze(1)   # make_grid需要 BCHW，这里拓展C维度
                kernel_grid = vutils.make_grid(kernel_idx, normalize=True, scale_each=True, nrow=c_int)
                writer.add_image('{}_Convlayer_split_in_channel'.format(kernel_num), kernel_grid, global_step=o_idx)

            kernel_all = kernels.view(-1, 3, k_h, k_w)  # 3, h, w
            kernel_grid = vutils.make_grid(kernel_all, normalize=True, scale_each=True, nrow=8)  # c, h, w
            writer.add_image('{}_all'.format(kernel_num), kernel_grid, global_step=322)

            print("{}_convlayer shape:{}".format(kernel_num, tuple(kernels.shape)))

    writer.close()

输出:

0_convlayer shape:(64, 3, 11, 11)
1_convlayer shape:(192, 64, 5, 5)

查看可视化效果：


2.特征图可视化

测试代码：

# ----------------------------------- 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)

    # forward
    convlayer1 = alexnet.features[0]
    fmap_1 = convlayer1(img_tensor)

    # 预处理
    fmap_1.transpose_(0, 1)  # bchw=(1, 64, 55, 55) --> (64, 1, 55, 55)
    fmap_1_grid = vutils.make_grid(fmap_1, normalize=True, scale_each=True, nrow=8)

    writer.add_image('feature map in conv1', fmap_1_grid, global_step=322)
    writer.close()

可视化结果

三.add_graph and torchsummary

1.add_graph()
功能:可视化模型计算图

• model :模型，必须是nn.Module
• input_to_model:输出给模型的数据
• verbose :是否打印计算图结构信息

这个pytorch = 1.2 版本有问题，需要更新到 pytorch = 1.3 版本

测试代码：

# ----------------------------------- 5 add_graph -----------------------------------

# flag = 0
flag = 1
if flag:

    writer = SummaryWriter(comment='test_your_comment', filename_suffix="_test_your_filename_suffix")

    # 模型
    fake_img = torch.randn(1, 3, 32, 32)

    lenet = LeNet(classes=2)

    writer.add_graph(lenet, fake_img)

    writer.close()

    from torchsummary import summary
    print(summary(lenet, (3, 32, 32), device="cpu"))

输出：

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1            [-1, 6, 28, 28]             456
            Conv2d-2           [-1, 16, 10, 10]           2,416
            Linear-3                  [-1, 120]          48,120
            Linear-4                   [-1, 84]          10,164
            Linear-5                    [-1, 2]             170
================================================================
Total params: 61,326
Trainable params: 61,326
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.01
Forward/backward pass size (MB): 0.05
Params size (MB): 0.23
Estimated Total Size (MB): 0.30
----------------------------------------------------------------
None

可视化结果


2.torchsummary
功能:查看模型信息，便于调试

• model : pytorch模型
• input_size :模型输入size
• batch_size : batch size
• device :“cuda”or“cpu”

测试代码如上。