Skip to content
#

pretrained-weights

Here are 52 public repositories matching this topic...

NatanBagrov
NatanBagrov commented Mar 14, 2022

Describe the bug

When training a detection model, e.g. SSD Lite MobileNet, the mAP shown in SG (TensorBoard) is much higher than the mAP returned via COCO-API

To Reproduce

Steps to reproduce the behavior:

  1. Branch https://github.com/Deci-AI/super-gradients/tree/ssd_mobilenet
  2. Run train_from_recipe.py with coco_ssd_lite_mobilenet_v2.yaml or coco_ssd_mobilenet_v1.yaml
  3. (
good first issue

A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.

  • Updated May 19, 2022
  • C++

Improve this page

Add a description, image, and links to the pretrained-weights topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the pretrained-weights topic, visit your repo's landing page and select "manage topics."

Learn more