-
Thanks for sharing your code!
I wrote a [pytorch version of hourglass network](https://github.com/bearpaw/pytorch-pose). Hope this could be helpful for who are not familiar with Torch. Many codes f…
-
## Description
Images with greater resolution than 450 for each axis were not used for the training even if a 256x256 resizing was applied before being given to the hourglass network. Regarding the…
-
Due to the hourglass network has multiple output (According to "intermediate supervision", the number of hourglass block is equal to the number of output block), suppose that I use hourglass network a…
-
References user story #1
## TODO:
- [ ] :question: Answer question `Task3_Q1` on Canvas
- [ ] :bust_in_silhouette: Assign yourself to this task (this will prompt the [WorkflowLearning GitHub App]…
-
I want the original image size output, I resized , and the size is original size 1920*1080, but it has something wrong on hourglass net, because the size is not always even number，maybe odd number，so…
-
## Context
In this [paper](https://dl.acm.org/doi/abs/10.1007/978-3-030-87589-3_42), the hourglass network was trained on multiple subject samples with a variable number of intervertebral discs : b…
-
## Description
This issue is meant to discuss about strategies to improve the performances of the hourglass network.
-
Hi,
I am interested in testing your network on my own images.
According to your answer on other questions here, one should use _Stacked Hourglass_ to get predictions in 2D. That I have done and s…
-
read from the paper , it seems that the network trained end-to-end, i wonder how the intermediate loss used: is all the loss added together at the last loss layer and do bp or every single hourglass t…
-
References user story #1
## TODO:
- [ ] :question: Answer question `Task4_Q1` on Canvas
- [ ] :bust_in_silhouette: Assign yourself to this task (this will prompt the [WorkflowLearning GitHub App]…