Pytorch中使用tensorboard學習筆記(10) 添加低維映射add_embedding

參考連結: add_embedding

參考連結: pytorch 中使用tensorboard，詳解writer.add_embedding函數的作用（一）

代碼展示:

from torch.utils.tensorboard import SummaryWriter
import keyword
import torch
writer = SummaryWriter()
meta = []
while len(meta)<100:
    meta = meta+keyword.kwlist # get some strings
meta = meta[:100]

for i, v in enumerate(meta):
    meta[i] = v+str(i)

label_img = torch.rand(100, 3, 10, 32)
for i in range(100):
    label_img[i]*=i/100.0

writer.add_embedding(torch.randn(100, 5), metadata=meta, label_img=label_img)
# writer.add_embedding(torch.randn(100, 5), label_img=label_img)
# writer.add_embedding(torch.randn(100, 5), metadata=meta)
writer.close()


# tensorboard --logdir=runs
           

運作結果(浏覽器的頁面需要重新整理一下):