- 8 NVIDIA V100 GPUs
- PyTorch version: 1.0.0a0+dd2c487
- CUDA 9.2
- CUDNN 7.1
- NCCL 2.2.13-1
All the baselines were trained using the exact same experimental setup as in Detectron. We initialize the detection models with ImageNet weights from Caffe2, the same as used by Detectron.
The pre-trained models are available in the link in the model id.
| backbone | type | lr sched | im / gpu | train mem(GB) | train time (s/iter) | total train time(hr) | inference time(s/im) | box AP | mask AP | model id |
|---|---|---|---|---|---|---|---|---|---|---|
| R-50-C4 | Fast | 1x | 1 | 5.8 | 0.4036 | 20.2 | 0.17130 | 34.8 | - | 6358800 |
| R-50-FPN | Fast | 1x | 2 | 4.4 | 0.3530 | 8.8 | 0.12580 | 36.8 | - | 6358793 |
| R-101-FPN | Fast | 1x | 2 | 7.1 | 0.4591 | 11.5 | 0.143149 | 39.1 | - | 6358804 |
| X-101-32x8d-FPN | Fast | 1x | 1 | 7.6 | 0.7007 | 35.0 | 0.209965 | 41.2 | - | 6358717 |
| R-50-C4 | Mask | 1x | 1 | 5.8 | 0.4520 | 22.6 | 0.17796 + 0.028 | 35.6 | 31.5 | 6358801 |
| R-50-FPN | Mask | 1x | 2 | 5.2 | 0.4536 | 11.3 | 0.12966 + 0.034 | 37.8 | 34.2 | 6358792 |
| R-101-FPN | Mask | 1x | 2 | 7.9 | 0.5665 | 14.2 | 0.15384 + 0.034 | 40.1 | 36.1 | 6358805 |
| X-101-32x8d-FPN | Mask | 1x | 1 | 7.8 | 0.7562 | 37.8 | 0.21739 + 0.034 | 42.2 | 37.8 | 6358718 |
For person keypoint detection:
| backbone | type | lr sched | im / gpu | train mem(GB) | train time (s/iter) | total train time(hr) | inference time(s/im) | box AP | keypoint AP | model id |
|---|---|---|---|---|---|---|---|---|---|---|
| R-50-FPN | Keypoint | 1x | 2 | 5.7 | 0.3771 | 9.4 | 0.10941 | 53.7 | 64.3 | 9981060 |
We provided pre-trained models for selected FBNet models.
- All the models are trained from scratched with BN using the training schedule specified below.
- Evaluation is performed on a single