MODEL_ZOO.md
This file documents a large collection of baselines trained with Detectron, primarily in late December 2017. We refer to these results as the 12_2017_baselines. All configurations for these baselines are located in the configs/12_2017_baselines directory. The tables below provide results and useful statistics about training and inference. Links to the trained models as well as their output are provided. Unless noted differently below (see "Notes" under each table), the following common settings are used for all training and inference runs.
coco_2014_train and coco_2014_valminusminival, which is exactly equivalent to the recently defined coco_2017_train dataset.coco_2014_minival dataset, which is exactly equivalent to the recently defined coco_2017_val dataset..md5sum to the URL to download the file's md5 hash.We use three training schedules, indicated by the lr schd column in the tables below.
coco_2014_train union coco_2014_valminusminival (or equivalently, coco_2017_train).All training schedules also use a 500 iteration linear learning rate warm up. When changing the minibatch size between 8 and 16 images, we adjust the number of SGD iterations and the base learning rate according to the principles outlined in our paper Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour.
All models available for download through this document are licensed under the Creative Commons Attribution-ShareAlike 3.0 license.
The backbone models pretrained on ImageNet are available in the format used by Detectron. Unless otherwise noted, these models are trained on the standard ImageNet-1k dataset.
Training and inference logs are available for most models in the model zoo.
Notes:
coco_2014_train; "2" is coco_2014_valminusminival; and "3" is coco_2014_minival.Notes:
Notes:
Notes: none
Notes:
Our keypoint detection baselines differ from our box and mask baselines in a couple of details:
coco_2014_train union coco_2014_valminusminival that contain at least one person with keypoint annotations (all other images are discarded from the training set).coco_2014_minival dataset).Notes:
coco_2014_train; "2" is coco_2014_valminusminival; and "3" is coco_2014_minival. These include all images, not just the ones with valid keypoint annotations.Notes:
Notes: