作者|open-mmlab
编译|Flin
来源|Github
基准测试 和 Model Zoo
环境
硬件
- 8 个 NVIDIA Tesla V100 GPUs
- Intel Xeon 4114 CPU @ 2.20GHz
软件环境
- Python 3.6 / 3.7
- PyTorch 1.1
- CUDA 9.0.176
- CUDNN 7.0.4
- NCCL 2.1.15
镜像站点
我们使用AWS作为托管model zoo的主要站点,并在阿里云上维护镜像。
你可以在模型网址中把https://s3.ap-northeast-2.ama...://open-mmlab.oss-cn-beijing.aliyuncs.com。
常用设置
- 所有FPN基准和RPN-C4基准均使用8个GPU进行训练,批处理大小为16(每个GPU 2张图像)。其他C4基线使用8个批处理大小为8的GPU进行了训练(每个GPU 1张图像)。
- 所有模型都在
coco_2017_train上训练以及在coco_2017_val测试。 - 我们使用分布式训练,并且BN层统计信息是固定的。
- 我们采用与Detectron相同的训练时间表。1x表示12个epoch,而2x表示24个epoch,这比Detectron的迭代次数略少,并且可以忽略不计。
- ImageNet上所有pytorch样式的预训练主干都来自PyTorchmodel zoo。
- 为了与其他代码库进行公平比较,我们将GPU内存报告
torch.cuda.max_memory_allocated()为所有8个GPU 的最大值。请注意,此值通常小于nvidia-smi显示的值。 - 我们将推理时间报告为总体时间,包括数据加载,网络转发和后处理。
基线
具有不同主干的更多模型将添加到model zoo。
RPN
| Backbone | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | AR1000 | Download |
|---|---|---|---|---|---|---|---|
| R-50-C4 | caffe | 1x | - | - | 20.5 | 51.1 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | caffe | 2x | 2.2 | 0.17 | 20.3 | 52.2 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | 1x | - | - | 20.1 | 50.2 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | 2x | - | - | 20.0 | 51.1 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | caffe | 1x | 3.3 | 0.253 | 16.9 | 58.2 | - |
| R-50-FPN | pytorch | 1x | 3.5 | 0.276 | 17.7 | 57.1 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | 2x | - | - | - | 57.6 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | caffe | 1x | 5.2 | 0.379 | 13.9 | 59.4 | - |
| R-101-FPN | pytorch | 1x | 5.4 | 0.396 | 14.4 | 58.6 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | 2x | - | - | - | 59.1 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 1x | 6.6 | 0.589 | 11.8 | 59.4 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 2x | - | - | - | 59.9 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 1x | 9.5 | 0.955 | 8.3 | 59.8 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 2x | - | - | - | 60.0 | model(https://s3.ap-northeast-2.ama... |
Faster R-CNN
| Backbone | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | Download |
|---|---|---|---|---|---|---|---|
| R-50-C4 | caffe | 1x | - | - | 9.5 | 34.9 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | caffe | 2x | 4.0 | 0.39 | 9.3 | 36.5 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | 1x | - | - | 9.3 | 33.9 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | 2x | - | - | 9.4 | 35.9 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | caffe | 1x | 3.6 | 0.333 | 13.5 | 36.6 | - |
| R-50-FPN | pytorch | 1x | 3.8 | 0.353 | 13.6 | 36.4 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | 2x | - | - | - | 37.7 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | caffe | 1x | 5.5 | 0.465 | 11.5 | 38.8 | - |
| R-101-FPN | pytorch | 1x | 5.7 | 0.474 | 11.9 | 38.5 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | 2x | - | - | - | 39.4 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 1x | 6.9 | 0.672 | 10.3 | 40.1 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 2x | - | - | - | 40.4 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 1x | 9.8 | 1.040 | 7.3 | 41.3 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 2x | - | - | - | 40.7 | model(https://s3.ap-northeast-2.ama... |
| HRNetV2p-W18 | pytorch | 1x | - | - | - | 36.1 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W18 | pytorch | 2x | - | - | - | 38.3 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W32 | pytorch | 1x | - | - | - | 39.5 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W32 | pytorch | 2x | - | - | - | 40.6 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 1x | - | - | - | 40.9 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 2x | - | - | - | 41.5 | model(https://open-mmlab.s3.ap-nort... |
Mask R-CNN
| Backbone | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | mask AP | Download |
|---|---|---|---|---|---|---|---|---|
| R-50-C4 | caffe | 1x | - | - | 8.1 | 35.9 | 31.5 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | caffe | 2x | 4.2 | 0.43 | 8.1 | 37.9 | 32.9 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | 1x | - | - | 7.9 | 35.1 | 31.2 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | 2x | - | - | 8.0 | 37.2 | 32.5 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | caffe | 1x | 3.8 | 0.430 | 10.2 | 37.4 | 34.3 | - |
| R-50-FPN | pytorch | 1x | 3.9 | 0.453 | 10.6 | 37.3 | 34.2 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | 2x | - | - | - | 38.5 | 35.1 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | caffe | 1x | 5.7 | 0.534 | 9.4 | 39.9 | 36.1 | - |
| R-101-FPN | pytorch | 1x | 5.8 | 0.571 | 9.5 | 39.4 | 35.9 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | 2x | - | - | - | 40.3 | 36.5 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 1x | 7.1 | 0.759 | 8.3 | 41.1 | 37.1 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 2x | - | - | - | 41.4 | 37.1 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 1x | 10.0 | 1.102 | 6.5 | 42.1 | 38.0 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 2x | - | - | - | 42.0 | 37.7 | model(https://s3.ap-northeast-2.ama... |
| HRNetV2p-W18 | pytorch | 1x | - | - | - | 37.3 | 34.2 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W18 | pytorch | 2x | - | - | - | 39.2 | 35.7 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W32 | pytorch | 1x | - | - | - | 40.7 | 36.8 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W32 | pytorch | 2x | - | - | - | 41.7 | 37.5 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 1x | - | - | - | 42.4 | 38.1 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 2x | - | - | - | 42.9 | 38.3 | model(https://open-mmlab.s3.ap-nort... |
Fast R-CNN (有预先计算的proposals)
| Backbone | Style | 类型 | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | mask AP | Download |
|---|---|---|---|---|---|---|---|---|---|
| R-50-C4 | caffe | Faster | 1x | - | - | 6.7 | 35.0 | - | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | caffe | Faster | 2x | 3.8 | 0.34 | 6.6 | 36.4 | - | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | Faster | 1x | - | - | 6.3 | 34.2 | - | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | Faster | 2x | - | - | 6.1 | 35.8 | - | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | caffe | Faster | 1x | 3.3 | 0.242 | 18.4 | 36.6 | - | - |
| R-50-FPN | pytorch | Faster | 1x | 3.5 | 0.250 | 16.5 | 35.8 | - | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | caffe | Mask | 1x | - | - | 8.1 | 35.9 | 31.5 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | caffe | Mask | 2x | 4.2 | 0.43 | 8.1 | 37.9 | 32.9 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | Mask | 1x | - | - | 7.9 | 35.1 | 31.2 | model(https://s3.ap-northeast-2.ama... |
| R-50-C4 | pytorch | Mask | 2x | - | - | 8.0 | 37.2 | 32.5 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | Faster | 2x | - | - | - | 37.1 | - | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | caffe | Faster | 1x | 5.2 | 0.355 | 14.4 | 38.6 | - | - |
| R-101-FPN | pytorch | Faster | 1x | 5.4 | 0.388 | 13.2 | 38.1 | - | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | Faster | 2x | - | - | - | 38.8 | - | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | caffe | Mask | 1x | 3.4 | 0.328 | 12.8 | 37.3 | 34.5 | - |
| R-50-FPN | pytorch | Mask | 1x | 3.5 | 0.346 | 12.7 | 36.8 | 34.1 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | Mask | 2x | - | - | - | 37.9 | 34.8 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | caffe | Mask | 1x | 5.2 | 0.429 | 11.2 | 39.4 | 36.1 | - |
| R-101-FPN | pytorch | Mask | 1x | 5.4 | 0.462 | 10.9 | 38.9 | 35.8 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | Mask | 2x | - | - | - | 39.9 | 36.4 | model(https://s3.ap-northeast-2.ama... |
RetinaNet
| Backbone | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | Download |
|---|---|---|---|---|---|---|---|
| R-50-FPN | caffe | 1x | 3.4 | 0.285 | 12.5 | 35.8 | - |
| R-50-FPN | pytorch | 1x | 3.6 | 0.308 | 12.1 | 35.6 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | 2x | - | - | - | 36.4 | model(https://open-mmlab.s3.ap-nort... |
| R-101-FPN | caffe | 1x | 5.3 | 0.410 | 10.4 | 37.8 | - |
| R-101-FPN | pytorch | 1x | 5.5 | 0.429 | 10.9 | 37.7 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | 2x | - | - | - | 38.1 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 1x | 6.7 | 0.632 | 9.3 | 39.0 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 2x | - | - | - | 39.3 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 1x | 9.6 | 0.993 | 7.0 | 40.0 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 2x | - | - | - | 39.6 | model(https://s3.ap-northeast-2.ama... |
Cascade R-CNN
| Backbone | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | Download |
|---|---|---|---|---|---|---|---|
| R-50-C4 | caffe | 1x | 8.7 | 0.92 | 5.0 | 38.7 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | caffe | 1x | 3.9 | 0.464 | 10.9 | 40.5 | - |
| R-50-FPN | pytorch | 1x | 4.1 | 0.455 | 11.9 | 40.4 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | 20e | - | - | - | 41.1 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | caffe | 1x | 5.8 | 0.569 | 9.6 | 42.4 | - |
| R-101-FPN | pytorch | 1x | 6.0 | 0.584 | 10.3 | 42.0 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | 20e | - | - | - | 42.5 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 1x | 7.2 | 0.770 | 8.9 | 43.6 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 20e | - | - | - | 44.0 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 1x | 10.0 | 1.133 | 6.7 | 44.5 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 20e | - | - | - | 44.7 | model(https://s3.ap-northeast-2.ama... |
| HRNetV2p-W18 | pytorch | 20e | - | - | - | 41.2 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W32 | pytorch | 20e | - | - | - | 43.7 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 20e | - | - | - | 44.6 | model(https://open-mmlab.s3.ap-nort... |
Cascade Mask R-CNN
| Backbone | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | mask AP | Download |
|---|---|---|---|---|---|---|---|---|
| R-50-C4 | caffe | 1x | 9.1 | 0.99 | 4.5 | 39.3 | 32.8 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | caffe | 1x | 5.1 | 0.692 | 7.6 | 40.9 | 35.5 | - |
| R-50-FPN | pytorch | 1x | 5.3 | 0.683 | 7.4 | 41.2 | 35.7 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | 20e | - | - | - | 42.3 | 36.6 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | caffe | 1x | 7.0 | 0.803 | 7.2 | 43.1 | 37.2 | - |
| R-101-FPN | pytorch | 1x | 7.2 | 0.807 | 6.8 | 42.6 | 37.0 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | 20e | - | - | - | 43.3 | 37.6 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 1x | 8.4 | 0.976 | 6.6 | 44.4 | 38.2 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 20e | - | - | - | 44.7 | 38.6 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 1x | 11.4 | 1.33 | 5.3 | 45.4 | 39.1 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 20e | - | - | - | 45.7 | 39.4 | model(https://s3.ap-northeast-2.ama... |
| HRNetV2p-W18 | pytorch | 20e | - | - | - | 41.9 | 36.4 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W32 | pytorch | 20e | - | - | - | 44.5 | 38.5 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 20e | - | - | - | 46.0 | 39.5 | model(https://open-mmlab.s3.ap-nort... |
注意s:
- 20e级联(掩码)R-CNN中的时间表指示在第16和19个epoch减少lr,总共减少20个epoch。
混合任务级联(HTC)
| Backbone | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | mask AP | Download |
|---|---|---|---|---|---|---|---|---|
| R-50-FPN | pytorch | 1x | 7.4 | 0.936 | 4.1 | 42.1 | 37.3 | model(https://s3.ap-northeast-2.ama... |
| R-50-FPN | pytorch | 20e | - | - | - | 43.2 | 38.1 | model(https://s3.ap-northeast-2.ama... |
| R-101-FPN | pytorch | 20e | 9.3 | 1.051 | 4.0 | 44.9 | 39.4 | model(https://s3.ap-northeast-2.ama... |
| X-101-32x4d-FPN | pytorch | 20e | 5.8 | 0.769 | 3.8 | 46.1 | 40.3 | model(https://s3.ap-northeast-2.ama... |
| X-101-64x4d-FPN | pytorch | 20e | 7.5 | 1.120 | 3.5 | 46.9 | 40.8 | model(https://s3.ap-northeast-2.ama... |
| HRNetV2p-W18 | pytorch | 20e | - | - | - | 43.1 | 37.9 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W32 | pytorch | 20e | - | - | - | 45.3 | 39.6 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 20e | - | - | - | 46.8 | 40.7 | model(https://open-mmlab.s3.ap-nort... |
| HRNetV2p-W48 | pytorch | 28e | - | - | - | 47.0 | 41.0 | model(https://open-mmlab.s3.ap-nort... |
注意:
- 有关详细信息和更强大的模型(50.7 / 43.9),请参阅混合任务级联(https://github.com/open-mmlab...
SSD
| Backbone | Size | Style | Lr schd | 内存 (GB) | 训练时间 (s/iter) | 最短时间 (fps) | box AP | Download |
|---|---|---|---|---|---|---|---|---|
| VGG16 | 300 | caffe | 120e | 3.5 | 0.256 | 25.9 / 34.6 | 25.7 | model(https://s3.ap-northeast-2.ama... |
| VGG16 | 512 | caffe | 120e | 7.6 | 0.412 | 20.7 / 25.4 | 29.3 | model(https://s3.ap-northeast-2.ama... |
注意:
-
cudnn.benchmark设置为True用于SSD训练和测试。 - 对于batch size= 1和batch size= 8,报告推理时间。
- 由于模型参数和nms,COCO和VOC的速度有所不同。
组规范化(GN)
有关详细信息,请参考组规范化(https://github.com/open-mmlab...。
权重标准化
有关详细信息,请参考权重标准化(https://github.com/open-mmlab...。
可变形卷积v2
有关详细信息,请参阅可变形卷积网络(https://github.com/open-mmlab...。
CARAFE：功能的内容感知重组
有关详细信息,请参考CARAFE(https://github.com/open-mmlab...。
Instaboost
有关详细信息,请参考Instaboost(https://github.com/open-mmlab...。
Libra R-CNN
有关详细信息,请参考Libra R-CNN(https://github.com/open-mmlab...。
Guided Anchoring
有关详细信息,请参阅Guided Anchoring(https://github.com/open-mmlab...。
FCOS
有关详细信息,请参阅FCOS(https://github.com/open-mmlab...。
FoveaBox
有关详细信息,请参考FoveaBox(https://github.com/open-mmlab...。
RepPoints
有关详细信息,请参考RepPoints(https://github.com/open-mmlab...。
FreeAnchor
有关详细信息,请参考FreeAnchor(https://github.com/open-mmlab...。
Grid R-CNN (plus)
有关详细信息,请参考Grid R-CNN(https://github.com/open-mmlab...。
GHM
有关详细信息,请参阅GHM(https://github.com/open-mmlab...。
GCNet
有关详细信息,请参考GCNet(https://github.com/open-mmlab...。
HRNet
有关详细信息,请参考HRNet(https://github.com/open-mmlab...。
Mask Scoring R-CNN
有关详细信息,请参考Mask Scoring R-CNN(https://github.com/open-mmlab...。
Train from Scratch
有关详细信息,请参考 重新思考ImageNet预训练(https://github.com/open-mmlab...。
NAS-FPN
有关详细信息,请参阅NAS-FPN(https://github.com/open-mmlab...。
ATSS
有关详细信息,请参考ATSS(https://github.com/open-mmlab...。
其他数据集
我们还对PASCAL VOC(https://github.com/open-mmlab...://github.com/open-mmlab/ mmdetection / blob / master / configs / cityscapes)和WIDER FACE(https://github.com/open-mmlab...。
与 Detectron 和 maskrcnn-benchmark 的比较
我们将mmdetection与Detectron(https://github.com/facebookre... 和maskrcnn-benchmark(https://github.com/facebookre...。使用的主干是R-50-FPN。
通常来说,mmdetection与Detectron相比具有3个优势。
- 更高的性能(尤其是在mask AP方面)
- 更快的训练速度
- 高效记忆
性能
Detectron和maskrcnn-benchmark使用Caffe风格的ResNet作为主干。我们使用caffe样式(权重从(https://github.com/facebookre... 和pytorch样式(权重来自官方model zoo)ResNet主干报告结果,表示为pytorch样式结果 / caffe样式结果。
我们发现,pytorch风格的ResNet通常比caffe风格的ResNet收敛慢,因此在1倍进度中导致结果略低,但2倍进度的最终结果则较高。
| 类型 | Lr schd | Detectron | maskrcnn-benchmark | mmdetection |
|---|---|---|---|---|
| RPN | 1x | 57.2 | - | 57.1 / 58.2 |
| 2x | - | - | 57.6 / - | |
| Faster R-CNN | 1x | 36.7 | 36.8 | 36.4 / 36.6 |
| 2x | 37.9 | - | 37.7 / - | |
| Mask R-CNN | 1x | 37.7 & 33.9 | 37.8 & 34.2 | 37.3 & 34.2 / 37.4 & 34.3 |
| 2x | 38.6 & 34.5 | - | 38.5 & 35.1 / - | |
| Fast R-CNN | 1x | 36.4 | - | 35.8 / 36.6 |
| 2x | 36.8 | - | 37.1 / - | |
| Fast R-CNN (w/mask) | 1x | 37.3 & 33.7 | - | 36.8 & 34.1 / 37.3 & 34.5 |
| 2x | 37.7 & 34.0 | - | 37.9 & 34.8 / - |
训练速度
训练速度以s/iter为单位。越低越好。
| 类型 | Detectron (P1001) | maskrcnn-benchmark (V100) | mmdetection (V1002) |
|---|---|---|---|
| RPN | 0.416 | - | 0.253 |
| Faster R-CNN | 0.544 | 0.353 | 0.333 |
| Mask R-CNN | 0.889 | 0.454 | 0.430 |
| Fast R-CNN | 0.285 | - | 0.242 |
| Fast R-CNN (w/mask) | 0.377 | - | 0.328 |
- 1。Facebook的Big Basin服务器(P100 / V100)比我们使用的服务器稍快。mmdetection在FB的服务器上也可以稍快一些地运行。
- 2。为了公平比较,我们在此处列出了caffe的结果。
推理速度
推理速度在单个GPU上以fps(img / s)进行测量。越高越好。
| 类型 | Detectron (P100) | maskrcnn-benchmark (V100) | mmdetection (V100) |
|---|---|---|---|
| RPN | 12.5 | - | 16.9 |
| Faster R-CNN | 10.3 | 7.9 | 13.5 |
| Mask R-CNN | 8.5 | 7.7 | 10.2 |
| Fast R-CNN | 12.5 | - | 18.4 |
| Fast R-CNN (w/mask) | 9.9 | - | 12.8 |
训练内存
| 类型 | Detectron | maskrcnn-benchmark | mmdetection |
|---|---|---|---|
| RPN | 6.4 | - | 3.3 |
| Faster R-CNN | 7.2 | 4.4 | 3.6 |
| Mask R-CNN | 8.6 | 5.2 | 3.8 |
| Fast R-CNN | 6.0 | - | 3.3 |
| Fast R-CNN (w/mask) | 7.9 | - | 3.4 |
毫无疑问,maskrcnn基准测试和mmdetection比Detectron的存储效率更高,而主要优点是PyTorch本身。我们还执行一些内存优化来推动它向前发展。
请注意,Caffe2和PyTorch具有不同的API,以通过不同的实现获取内存使用情况。对于所有代码库,nvidia-smi显示的内存使用量均大于上表中报告的数字。
原文链接：https://mmdetection.readthedo...
欢迎关注磐创AI博客站：
http://panchuang.net/
sklearn机器学习中文官方文档：
http://sklearn123.com/
欢迎关注磐创博客资源汇总站：
http://docs.panchuang.net/
**粗体** _斜体_ [链接](http://example.com) `代码` - 列表 > 引用。你还可以使用@来通知其他用户。