tensorboard

python pytorch 计算机视觉

之前介绍过 visdom 模块，visdom 模块不能将网络结构可视化，而 tensorboard 模块可以，因此这里学习了 tensorboard 模块，这里是在 pytorch 上使用tensorboard的帮助文档，本文依据文档进行改编，官方 github 地址：https://github.com/lanpa/tensorboardX

tensorboard 可视化一共分为四步

• tensorboard 安装
• 创建 writer 实例
• 添加需要的图表等信息
• 运行 events 日志

1. tensorboard 安装

需要安装两个 package，一个是 tensorboardX，另一个是 tensorboard（启动网页）。使用 pip install tensorboardX 和 pip install tensorboard 命令进行安装。

2. 创建一个 writer 实例

在添加文字或者创建图表时，首先需要创建一个 writer 实例，官方文档如下，在我们创建 writer 时若没有参数（如下面的 writer2），默认文件在 runs 目录下，默认的子文件夹名字为该文件的创建日期，当然也可以手动设定子文件夹的名字如 writer 和 writer3 所示

from tensorboardX import SummaryWriter 
#SummaryWriter encapsulates everything 
writer = SummaryWriter('runs/exp-1') 
#creates writer object. The log will be saved in 'runs/exp-1' 
writer2 = SummaryWriter() 
#creates writer2 object with auto generated file name, the dir will be something like 'runs/Aug20-17-20-33' 
writer3 = SummaryWriter(comment='3x learning rate') 
#creates writer3 object with auto generated file name, the comment will be appended to the filename. The dir will be something like 'runs/Aug20-17-20-33-3xlearning rate'

3. 添加数据形式

3.1 记录标量

（1）add_scalar

add_scalar(tag, scalar_value, global_step, walltime)

• tag：数据标签
• scalar_value：数据的值，即 y 轴的值
• global_step：全局步数，即 x 轴的值
• walltime：记录 event 的时间，可选

from tensorboardX import SummaryWriter 
import time
writer = SummaryWriter("runs/scalar") 
x = range(100) 
for i in x:     
    time.sleep(0.1)
    writer.add_scalar('y=2x', i * 2, i, walltime=time.time()) 
writer.close()

运行后进入到 runs 的上级目录，输入 tensorboard --logdir=runs/scalar，进入到网址http://localhost:6006/即可看到可视化结果

（2）add_scalars
add_scalars(main_tag, scalar_dict, global_step, walltime)

• main_tag：数据标签
• tag_scalar_dict：数据的值，即 y 轴的值
• global_step：全局步数，即 x 轴的值
• walltime：记录 event 的时间，可选

from tensorboardX import 
import numpy as np
SummaryWriter writer = SummaryWriter() 
r = 5 
for i in range(100):     
    writer.add_scalars('run_14h', {'xsinx':i*np.sin(i/r),                                                                                        
                                   'xcosx':i*np.cos(i/r),
                                   'tanx': np.tan(i/r)}, i) 
writer.close() 
# This call adds three values to the same scalar plot with the tag 
# 'run_14h' in TensorBoard's scalar section.

3.2 记录文本

add_text(tag, text_string, global_step, walltime)

• tag：数据标签
• text_string：数据的值
• global_step：全局步数，即 x 轴的值
• walltime：记录 event 的时间，可选

from tensorboardX import SummaryWriter
import time

writer = SummaryWriter("runs/text")
x = range(20)
for i in x:
# 最多添加十个epoch
   writer.add_text('text', "This is epoch {}".format(i), i)
   time.sleep(0.1)
writer.close()

3.3 记录图片

（1）add_image

add_image(tag, img_tensor, global_step, walltime, dataformats)

• tag：标签
• img_tensor：An uint8 or float Tensor of shape [channel, height, width] where channel is 1, 3, or 4. The elements in img_tensor can either have values in [0, 1] (float32) or [0, 255] (uint8). Users are responsible to scale the data in the correct range/type.
• global_step：记录 epoch
• walltime：记录时间
• dataformats：指定张量每个维度的含义，例如 CHW，[channel，height，width]

img_tensor: Default is (3,H,W)(3,H,W). You can use torchvision.utils.make_grid() to convert a batch of tensor into 3xHxW format or use add_images() and let us do the job. Tensor with (1,H,W)(1,H,W), (H,W)(H,W), (H,W,3)(H,W,3) is also suitible as long as corresponding dataformats argument is passed. e.g. CHW, HWC, HW.

from tensorboardX import SummaryWriter
import numpy as np
img = np.zeros((3, 100, 100))
img[0] = np.arange(0, 10000).reshape(100, 100) / 10000
img[1] = 1 - np.arange(0, 10000).reshape(100, 100) / 10000

img_HWC = np.zeros((100, 100, 3))
img_HWC[:, :, 0] = np.arange(0, 10000).reshape(100, 100) / 10000
img_HWC[:, :, 1] = 1 - np.arange(0, 10000).reshape(100, 100) / 10000

writer = SummaryWriter("runs/image")
writer.add_image('my_image', img, 0)

# If you have non-default dimension setting, set the dataformats argument.
writer.add_image('my_image_HWC', img_HWC, 0, dataformats='HWC')
writer.close()

（2）add_images

add_images(tag: str, img_tensor，global_step, walltime, dataformats: Optional[str] = ‘NCHW’)

• tag：标签
• img_tensor：An uint8 or float Tensor of shape [channel, height, width] where channel is 1, 3, or 4. The elements in img_tensor can either have values in [0, 1] (float32) or [0, 255] (uint8). Users are responsible to scale the data in the correct range/type.
• global_step：记录 epoch
• walltime：记录时间
• dataformats：指定张量每个维度的含义，例如 NCHW，[number，channel，height，width]

img_tensor: Default is (N,3,H,W)(N,3,H,W). If dataformats is specified, other shape will be accepted. e.g. NCHW or NHWC.

from tensorboardX import SummaryWriter 
import numpy as np 

img_batch = np.zeros((16, 3, 100, 100)) 
for i in range(16):     
img_batch[i, 0] = np.arange(0, 10000).reshape(100, 100) / 10000 / 16 * i     img_batch[i, 1] = (1 - np.arange(0, 10000).reshape(100, 100) / 10000) / 16 * i 
writer = SummaryWriter("runs/images") 
writer.add_images('my_image_batch', img_batch, 0) 
writer.close()

3.3 添加计算图

add_graph(model, input_to_model=None, verbose=False)

• model：需要绘制的模型
• imput_to_model：一个变量或者 tuple 类型的变量
• verbose：是否在 console 中打印计算图结构

import torch
import torch.nn as nn
import torch.nn.functional as F
from tensorboardX import SummaryWriter


class Net1(nn.Module):
    def __init__(self):
        super(Net1, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)
        self.bn = nn.BatchNorm2d(20)

    def forward(self, x):
        x = F.max_pool2d(self.conv1(x), 2)
        x = F.relu(x) + F.relu(-x)
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = self.bn(x)
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        x = F.softmax(x, dim=1)
        return x


dummy_input = torch.rand(13, 1, 28, 28)

model = Net1()
# 使用with语句，可以不调用w.close
# with SummaryWriter(comment='Net1') as w:
with SummaryWriter("runs/graph") as w:
    # 第一个参数为需要保存的模型
    # 第二个参数为输入值->元祖类型
    w.add_graph(model, (dummy_input), verbose=True)

4. 运行 tensorboard

当我们在程序中添加了程序日志 events 之后，就可以使用 tensorboard --logdir=<your_log_dir> 运行日志进行可视化了，例如：tensorboard/runs 下有两个文件夹 linear 和 graph，进入到 tensorboard 文件夹中，输入 tensorboard --logdir=runs 即可运行两个文件夹，如果指向运行其中一个，输入 tensorboard --logdir=runs/linear 即可

5. tensorboard 官方 demo

运行时需要将 mnist/MNIST 数据集放在 demo.py 同级目录下

import torch
import torchvision.utils as vutils
import numpy as np
import torchvision.models as models
from torchvision import datasets
from tensorboardX import SummaryWriter

resnet18 = models.resnet18(False)
writer = SummaryWriter("runs/demo")
sample_rate = 44100
freqs = [262, 294, 330, 349, 392, 440, 440, 440, 440, 440, 440]

for n_iter in range(100):
    dummy_s1 = torch.rand(1)
    dummy_s2 = torch.rand(1)
    # data grouping by `slash`
    writer.add_scalar('data/scalar1', dummy_s1[0], n_iter)
    writer.add_scalar('data/scalar2', dummy_s2[0], n_iter)

    writer.add_scalars('data/scalar_group', {'xsinx': n_iter * np.sin(n_iter),
                                             'xcosx': n_iter * np.cos(n_iter),
                                             'arctanx': np.arctan(n_iter)}, n_iter)

    dummy_img = torch.rand(32, 3, 64, 64)  # output from network
    if n_iter % 10 == 0:
        x = vutils.make_grid(dummy_img, normalize=True, scale_each=True)
        writer.add_image('Image', x, n_iter)

        dummy_audio = torch.zeros(sample_rate * 2)
        for i in range(x.size(0)):
            # amplitude of sound should in [-1, 1]
            dummy_audio[i] = np.cos(freqs[n_iter // 10] * np.pi * float(i) / float(sample_rate))
        writer.add_audio('myAudio', dummy_audio, n_iter, sample_rate=sample_rate)

        writer.add_text('Text', 'text logged at step:' + str(n_iter), n_iter)

        for name, param in resnet18.named_parameters():
            writer.add_histogram(name, param.clone().cpu().data.numpy(), n_iter)

        # needs tensorboard 0.4RC or later
        writer.add_pr_curve('xoxo', np.random.randint(2, size=100), np.random.rand(100), n_iter)

dataset = datasets.MNIST('mnist', train=False, download=False)
images = dataset.data[:100].float()
label = dataset.targets[:100]

features = images.view(100, 784)
writer.add_embedding(features, metadata=label, label_img=images.unsqueeze(1))

# export scalar data to JSON for external processing
writer.export_scalars_to_json("./all_scalars.json")
writer.close()

本文由 Yonghui Wang 创作，采用 知识共享署名4.0 国际许可协议进行许可
本站文章除注明转载/出处外，均为本站原创或翻译，转载前请务必署名
最后编辑时间为: Dec 19, 2024 12:18 pm