关于tensorboard笔记

------------恢复内容开始------------

关于tensorboard:

它的使用是在训练模型之后的分析模型结果阶段。作用是将cnn度量可视化，使我们可以更清楚地了解这个训练过程中发生了什么事情。具体而言：

• Tracking and visualizing metrics such as loss and accuracy
• Visualizing the model graph (ops and layers)
• Viewing histograms of weights, biases, or other tensors as they change over time
• Projecting embeddings to a lower dimensional space
• Displaying images, text, and audio data
• Profiling TensorFlow programs
• And much more

关于使用：

pip install tensorboard（这个版本要在1.15及以上）
Pytorch的1.1.0版本就加入了tensorboard的实用程序包：
from torch.utils.tensorboard import SummaryWriter(SummaryWriter是一个类）

 

To use TensorBoard our task is to get the data we want displayed saved to a file that TensorBoard can read.

 

创建一个SummaryWriter实例、PyTorch网络实例并对一组的images和labels进行分析。之后图像和网络图都被加进了Tensorboard.

 

tb  = SummaryWriter()

network  = Network()

images, labels  = next ( iter (train_loader))

grid  = torchvision.utils.make_grid(images)


tb.add_image( 'images' , grid)

tb.add_graph(network, images)

tb.close()

 

Running TensorBoard:（运行.py文件，会在.py文件所在的目录下生成一个runs文件夹）
默认SummaryWriter实体会把数据写入磁盘中的./runs目录下，运行命令时通过传参告诉数据位置：

tensorboard --logdir=runs

访问TensorBoard接口：

http://localhost:6006

（这时可以看到的式网络图和图片数据）

 在终端cd 到events.out文件所在的上上级目录，然后tensorboard --logdir=上级目录

然后通过谷歌点开访问接口

 http://localhost:6006/ 

TensorBoard Histograms And Scalars:

我们可以添加到TensorBoard的下一个导入类型是数值数据。我们可以添加将随时间或epoch显示的标量值。我们还可以在直方图中添加值，以查看值的频率分布。

例子：
tb.add_scalar('Loss', total_loss, epoch)

tb.add_scalar('Number Correct', total_correct, epoch)

tb.add_scalar('Accuracy', total_correct / len(train_set), epoch)

 

tb.add_histogram('conv1.bias', network.conv1.bias, epoch)

tb.add_histogram('conv1.weight', network.conv1.weight, epoch)

tb.add_histogram('conv1.weight.grad', network.conv1.weight.grad, epoch)

在训练循环体中放置上面的calls:

 

network = Network()

train_loader = torch.utils.data.DataLoader(train_set, batch_size=100)

optimizer = optim.Adam(network.parameters(), lr=0.01)

 

images, labels = next(iter(train_loader))

grid = torchvision.utils.make_grid(images)

 

tb = SummaryWriter()

tb.add_image('images', grid)

tb.add_graph(network, images)

for epoch in range(1):

 

    total_loss = 0

    total_correct = 0

 

    for batch in train_loader: # Get Batch

 

        # Pass Batch

        # Calculate Loss

        # Calculate Gradient

        # Update Weights

 

    tb.add_scalar('Loss', total_loss, epoch)

    tb.add_scalar('Number Correct', total_correct, epoch)

    tb.add_scalar('Accuracy', total_correct / len(train_set), epoch)

 

    tb.add_histogram('conv1.bias', network.conv1.bias, epoch)

    tb.add_histogram('conv1.weight', network.conv1.weight, epoch)

    tb.add_histogram(

        'conv1.weight.grad'

        ,network.conv1.weight.grad

        ,epoch

    )

 

    print(

        "epoch", epoch,

        "total_correct:", total_correct,

        "loss:", total_loss

    )

 

tb.close()

 

加入到Tensorboard中的这些值还会随着玩过训练实时更新。

TensorBoard的真正强大之处在于它能够对多次运行进行比较。这允许我们通过改变超参数值和比较运行来快速试验，以查看哪些参数工作得最好。

 

另一个例子：(来自参考https://blog.csdn.net/wuzhihuaw/article/details/121357355）

 

import numpy as np
from torch.utils.tensorboard  import SummaryWriter

writer  = SummaryWriter(comment = 'tensorboard_test' )

for x  in range ( 50 ):
    writer.add_scalar( 'y=2x' , x  * 2 , x)
    writer.add_scalar( 'y=pow(2, x)' ,  2 * * x, x)

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

 

------------恢复内容结束------------