TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10
TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10 copied to clipboard
tensorboard embedding
Hello,
In tensorboard I see the the Projector tab with the PCA and T_SNE visualizations (1024 points and 36 dimension)
How can I create the tsv and sprite to visualize my labels and images there?
I don't know how to extract the features from the Faster r-cnn inception V2 so I could create the tsv and sprite for those 1024 points, or whatever is needed for label and image visualization.
Thank you!
Save question. It would be great to have a tutorial on how to better understand the tensorboard distributions and histograms and to label the projector to make it meaningful for the classes being trained, especially when using the networks from the tensorflow model zoo. Thank you.
Hi, I'm struggling with the same problem. did you figure out how to do so?
unfortunately not yet.
not yet?