【03】google Colab ｜pytorch TensorBoard add_image 代码实战 免费GPU google Colaboratory 使用教程

0 前言

接着上一篇：【02】google Colab ｜pytorch Dataset类代码实战 免费GPU google Colaboratory 使用教程

这次要说的是pytorch TensorBoard add_image 代码实战，还是在google Colab （免费GPU）上操作。
b站操作视频：

1 数据集下载

蚂蚁蜜蜂/练手数据集：链接: https://pan.baidu.com/s/1jZoTmoFzaTLWh4lKBHVbEA 密码: 5suq

2 代码与结果

# Mount google drive
from google.colab import drive
drive.flush_and_unmount()
drive.mount('/content/drive', force_remount=False)

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

writer = SummaryWriter('logs')

image_path = './drive/MyDrive/AI/practice_dataset/train/ants_image/1030023514_aad5c608f9.jpg'
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
print(img_array.shape)

writer.add_image('test',img_array,1,dataformats='HWC')
writer.close()

image_path = './drive/MyDrive/AI/practice_dataset/train/ants_image/1269756697_0bce92cdab.jpg'
img_PIL = Image.open(image_path)
img_array = np.array(img_PIL)
print(img_array.shape)

writer.add_image('test',img_array,2,dataformats='HWC')
writer.close()

3 参考

https://www.bilibili.com/video/BV1hE411t7RN?p=9