Pytorch 可视化之tensorboardX

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/zw__chen/article/details/82859653

使用tensorboardX需要安装tensorflow和tensorboardX，安装语句如下：

pip install tensorboardX
pip install tensorflow 

其核心的语句为三句：

from tensorboardX import SummaryWriter

 writer = SummaryWriter('./log/')  # 设置保存的log文件夹
 writer.add_scalar('name', y, x) # 设置图的名字，和y、x的值，注意这里不是x,y，而是y,x
 writer.close() # 关闭输入

接下来我们来举个栗子吧～

from tensorboardX import SummaryWriter

if __name__ == '__main__':
    # x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
    writer = SummaryWriter('./log/')
    for i in range(1, 10):
        writer.add_scalar('test', i, i)
    writer.close()