14 KiB
Model Zoo and Baselines
Introduction
We provide baselines trained with Detectron2 DensePose. The corresponding
configuration files can be found in the configs directory.
All models were trained on COCO train2014 + valminusminival2014 and
evaluated on COCO minival2014. For the details on common settings in which
baselines were trained, please check Detectron 2 Model Zoo.
License
All models available for download through this document are licensed under the Creative Commons Attribution-ShareAlike 3.0 license
COCO DensePose Baselines with DensePose-RCNN
Legacy Models
Baselines trained using schedules from Güler et al, 2018
| Name | lr sched |
train time (s/iter) |
inference time (s/im) |
train mem (GB) |
box AP |
dp. AP GPS |
dp. AP GPSm |
model id | download |
|---|---|---|---|---|---|---|---|---|---|
| R_50_FPN_s1x_legacy | s1x | 0.307 | 0.051 | 3.2 | 58.1 | 52.1 | 54.9 | 164832157 | model | metrics |
| R_101_FPN_s1x_legacy | s1x | 0.390 | 0.063 | 4.3 | 59.5 | 53.2 | 56.1 | 164832182 | model | metrics |
Improved Baselines, Original Fully Convolutional Haad
These models use an improved training schedule and Panoptic FPN head from Kirillov et al, 2019.
| Name | lr sched |
train time (s/iter) |
inference time (s/im) |
train mem (GB) |
box AP |
dp. AP GPS |
dp. AP GPSm |
model id | download |
|---|---|---|---|---|---|---|---|---|---|
| R_50_FPN_s1x | s1x | 0.359 | 0.066 | 4.5 | 61.2 | 63.7 | 65.3 | 165712039 | model | metrics |
| R_101_FPN_s1x | s1x | 0.428 | 0.079 | 5.8 | 62.3 | 64.5 | 66.4 | 165712084 | model | metrics |
Improved Baselines, DeepLabV3 Head
These models use an improved training schedule, Panoptic FPN head from Kirillov et al, 2019 and DeepLabV3 head from Chen et al, 2017.
| Name | lr sched |
train time (s/iter) |
inference time (s/im) |
train mem (GB) |
box AP |
dp. AP GPS |
dp. AP GPSm |
model id | download |
|---|---|---|---|---|---|---|---|---|---|
| R_50_FPN_DL_s1x | s1x | 0.392 | 0.070 | 6.7 | 61.1 | 65.6 | 66.8 | 165712097 | model | metrics |
| R_101_FPN_DL_s1x | s1x | 0.478 | 0.083 | 7.0 | 62.3 | 66.3 | 67.7 | 165712116 | model | metrics |
Baselines with Confidence Estimation
These models perform additional estimation of confidence in regressed UV coodrinates, along the lines of Neverova et al., 2019.
| Name | lr sched |
train time (s/iter) |
inference time (s/im) |
train mem (GB) |
box AP |
dp. AP GPS |
dp. AP GPSm |
model id | download |
|---|---|---|---|---|---|---|---|---|---|
| R_50_FPN_WC1_s1x | s1x | 0.353 | 0.064 | 4.6 | 60.5 | 64.2 | 65.6 | 173862049 | model | metrics |
| R_50_FPN_WC2_s1x | s1x | 0.364 | 0.066 | 4.8 | 60.7 | 64.2 | 65.7 | 173861455 | model | metrics |
| R_50_FPN_DL_WC1_s1x | s1x | 0.397 | 0.068 | 6.7 | 61.1 | 65.8 | 67.1 | 173067973 | model | metrics |
| R_50_FPN_DL_WC2_s1x | s1x | 0.410 | 0.070 | 6.8 | 60.8 | 65.6 | 66.7 | 173859335 | model | metrics |
| R_101_FPN_WC1_s1x | s1x | 0.435 | 0.076 | 5.7 | 62.5 | 64.9 | 66.5 | 171402969 | model | metrics |
| R_101_FPN_WC2_s1x | s1x | 0.450 | 0.078 | 5.7 | 62.3 | 64.8 | 66.6 | 173860702 | model | metrics |
| R_101_FPN_DL_WC1_s1x | s1x | 0.479 | 0.081 | 7.9 | 62.0 | 66.2 | 67.4 | 173858525 | model | metrics |
| R_101_FPN_DL_WC2_s1x | s1x | 0.491 | 0.082 | 7.6 | 61.7 | 65.9 | 67.3 | 173294801 | model | metrics |
Old Baselines
It is still possible to use some baselines from DensePose 1. Below are evaluation metrics for the baselines recomputed in the current framework:
| Model | bbox AP | AP | AP50 | AP75 | APm | APl |
|---|---|---|---|---|---|---|
ResNet50_FPN_s1x-e2e |
54.673 | 48.894 | 84.963 | 50.717 | 43.132 | 50.433 |
ResNet101_FPN_s1x-e2e |
56.032 | 51.088 | 86.250 | 55.057 | 46.542 | 52.563 |
Note: these scores are close, but not strictly equal to the ones reported in the DensePose 1 Model Zoo, which is due to small incompatibilities between the frameworks.