CenterNet Fixed For Google Colab

CenterNet Fixed For Google Colab, mehrdad mohammadian

Object detection, 3D detection, and pose estimation using center point detection

🛠 CenterNet Fixed For Google Colab

+ 🤔 Do you want to run CenterNet pre-trained models in Colab without error 🐞 and make predictions?

- 🤯 BAAM, yes!

+ 😎 Read this doc and then download this jupyter notebook, to run CenterNet pre-trained models (with different backbones) on your dataset!

The Official CenterNet repo

go to the repo

Jupyter notebook

For use CenterNet in google colab please download this jupyter notebook and run it.

Note: Set your Hardware accelerator on GPU in colab.

## Options You can use the blow options for change seeting:

Basic settings:

task: ctdet, ddd, multi_pose, exdet, default=’ctdet’

--dataset: coco, kitti, coco_hp, pascal, default=’coco’

--exp_id: default=’default’

--test: store_true

--debug: default=0

--demo: path to image/ image folders/ video or webcam

--load_model: path to pretrained model

--resume: resume an experiment. Reloaded the optimizer parameter and set load_model to model_last.pth in the exp dir if load_model is empty


See the for compare the diffrent backbones results.