TensorBoard使用

 安装tensorboard

pip install tensorboard

安装后运行python显示no module named 'past'可以使用

pip install future

通过设置参数避免和其他人端口一样

tensorboard --logdir=logs --port=6008

from torch.utils.tensorboard import SummaryWriter

# 创建一个实例
writer = SummaryWriter("log")

# writer.add_image()
# y = 2x
for i in range(100):
    writer.add_scalar("y=2x",2*i,i)

writer.close()

利用numpy.array()，对PIL图片进行转换

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

# 创建一个实例
writer = SummaryWriter("log")
image_path = "dataset/train/ants_image/0013035.jpg"
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)

# 从PIL到numpy，需要在add_image()中指定shape中每一个数字/维表示的含义
writer.add_image("test",img_array,1,dataformats='HWC')
for i in range(100):
    writer.add_scalar("y=2x",3*i,i);
writer.close()

更改代码重新运行，step1为蚂蚁，step2为蜜蜂

image_path = "dataset/train/bees_image/21399619_3e61e5bb6f.jpg"
writer.add_image("test",img_array,2,dataformats='HWC')

如果更改

writer.add_image("train",img_array,2,dataformats='HWC')

可以很直观的观察给model提供了哪些数据，得到了哪些结果。