小土堆Pytorch学习笔记（三、TensorBoard的使用（2））

一、查找add_image（ ）函数的定义和使用方法

 def add_image(
        self, tag, img_tensor, global_step=None, walltime=None, dataformats="CHW"
    ):
        """Add image data to summary.

        Note that this requires the ``pillow`` package.

        Args:
            tag (string): Data identifier
            img_tensor (torch.Tensor, numpy.array, or string/blobname): Image data
            global_step (int): Global step value to record
            walltime (float): Optional override default walltime (time.time())
              seconds after epoch of event
            dataformats (string): Image data format specification of the form
              CHW, HWC, HW, WH, etc.
        Shape:
            img_tensor: Default is :math:`(3, H, W)`. You can use ``torchvision.utils.make_grid()`` to
            convert a batch of tensor into 3xHxW format or call ``add_images`` and let us do the job.
            Tensor with :math:`(1, H, W)`, :math:`(H, W)`, :math:`(H, W, 3)` is also suitable as long as
            corresponding ``dataformats`` argument is passed, e.g. ``CHW``, ``HWC``, ``HW``.

再使用opencv对numpy型数据进行读取
小土堆使用的是numpy.array( )对PIL图片转换。
从PIL到numpy, 需要在add_image（ ）中指定shape中每一个数字/维的含义。

from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image
# 创建一个实例
writer = SummaryWriter("logs")
img_path = "lianshou_dataset/train/ants_image/0013035.jpg"
img_PIL = Image.open(img_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)
# 再使用两个类方法，其中函数参数默认值修改看上面的函数定义。
writer.add_image("test", img_array, 1, dataformats='HWC')

for i in range(100):

    writer.add_scalar("y=2x", 2*i, i)

writer.close()

结果如下：

再对代码进行改动，改变step的步数，改成2，代码如下：

from torch.utils.tensorboard import SummaryWriter
import numpy as np
from PIL import Image
# 创建一个实例
writer = SummaryWriter("logs")
img_path = "lianshou_dataset/train/bees_image/16838648_415acd9e3f.jpg"
img_PIL = Image.open(img_path)
img_array = np.array(img_PIL)
print(type(img_array))
print(img_array.shape)
# 再使用两个类方法
writer.add_image("test", img_array, 2, dataformats='HWC')

for i in range(100):

    writer.add_scalar("y=2x", 2*i, i)

writer.close()

结果如下：

结果与小土堆的视频吻合。