Saif Khan

Pose Estimation Model Metrics: Inconsistencies between PeekingDuck Docs and TensorFlow Website

2

Hello PeekingDuck team, I have recently explored the PeekingDuck framework and noticed some inconsistencies in the reported metrics for pose estimation models, particularly MoveNet and PoseNet when comparing them with...

Hello, I have been going through your repository and noticed that the reported inference times for both the CPM and Hourglass models are the same, as shown in the README....

I am not sure what exactly granularity means in `torchstat`. As far as I can tell, nothing really changes and when I was trying to look at the class implementations...

[Bug] Cannot replicate reported CIFAR-100 results for multiple models

1

### Branch main branch (mmpretrain version) ### Describe the bug I am trying to train some models (ResNet-50, MobileNetV2) from scratch on CIFAR-100 using the configuration files provided in mmpretrain...

Hi, I have a question about how long the network was trained. In the paper, it says > Training takes 1 to 3 days, depending on the exact setting. but...

Display module parameter info

1

The [`torchstat`](https://github.com/Swall0w/torchstat) package has functions to compute the number of parameters and FLOPs for torch modules. I think it should be easy to use that to add an option to...