Hello,
I am following PyTorch provided code from the official site to see embedding images on tensorbaord.
import torch
from torch.utils.tensorboard import SummaryWriter
import tensorflow as tf
import tensorboard as tb
tf.io.gfile = tb.compat.tensorflow_stub.io.gfile
writer = SummaryWriter('logs/experiments')
meta = []
while len(meta)<100:
meta = meta+keyword.kwlist # get some strings
meta = meta[:100]
for i, v in enumerate(meta):
#print(i)
meta[i] = v+str(i)
label_img = torch.rand(100, 3, 32, 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)
However, when I am doing it for CIFAR10 dataset, labels are displaying, but images are not displaying correctly.
the images are displaying like this:
I want to visualize images correctly. I really appreciate any help you can provide.