search

xingyizhou / CenterNet

Object detection, 3D detection, and pose estimation using center point detection:
MIT License
7.24k stars 1.92k forks source link

Issue about using Hourglass as backbone #406

Open seekFire opened 4 years ago

seekFire commented 4 years ago

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 as backbone, which output should be regarded as the final output in test stage?

I noticed that in "large_hourglass.py", the output of the class "exkp"(inherited by class "HourglassNet") is multiple; while in "base_trainer.py", the class "ModuleWithLoss" return "output[-1]", does this mean that you only use the last output of hourglass to train the network? Shouldn't we use all output to train, and the last output to test?

xingyizhou commented 4 years ago

We do use all output to train and the last output to test.

seekFire commented 4 years ago

@xingyizhou Okay! Thank you very much!