MMDetection 基准测试 和 Model Zoo | 三

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.amazonaws.com/open-mmlab替换为https://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GP​​U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.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_caffe_c4_1x-ea7d3428.pth)
R-50-C4	caffe	2x	2.2	0.17	20.3	52.2	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_caffe_c4_2x-c6d5b958.pth)
R-50-C4	pytorch	1x	-	-	20.1	50.2	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_c4_1x-eb38972b.pth)
R-50-C4	pytorch	2x	-	-	20.0	51.1	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_c4_2x-3d4c1e14.pth)
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.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_fpn_1x_20181010-4a9c0712.pth)
R-50-FPN	pytorch	2x	-	-	-	57.6	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r50_fpn_2x_20181010-88a4a471.pth)
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.amazonaws.com/open-mmlab/mmdetection/models/rpn_r101_fpn_1x_20181129-f50da4bd.pth)
R-101-FPN	pytorch	2x	-	-	-	59.1	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_r101_fpn_2x_20181129-e42c6c9a.pth)
X-101-32x4d-FPN	pytorch	1x	6.6	0.589	11.8	59.4	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_32x4d_fpn_1x_20181218-7e379d26.pth)
X-101-32x4d-FPN	pytorch	2x	-	-	-	59.9	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_32x4d_fpn_2x_20181218-0510af40.pth)
X-101-64x4d-FPN	pytorch	1x	9.5	0.955	8.3	59.8	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_64x4d_fpn_1x_20181218-c1a24f1f.pth)
X-101-64x4d-FPN	pytorch	2x	-	-	-	60.0	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/rpn_x101_64x4d_fpn_2x_20181218-c22bdd70.pth)

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.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_caffe_c4_1x-75ecfdfa.pth)
R-50-C4	caffe	2x	4.0	0.39	9.3	36.5	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_caffe_c4_2x-71c67f27.pth)
R-50-C4	pytorch	1x	-	-	9.3	33.9	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_c4_1x-642cf91f.pth)
R-50-C4	pytorch	2x	-	-	9.4	35.9	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_c4_2x-6e4fdf4f.pth)
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.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth)
R-50-FPN	pytorch	2x	-	-	-	37.7	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r50_fpn_2x_20181010-443129e1.pth)
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.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r101_fpn_1x_20181129-d1468807.pth)
R-101-FPN	pytorch	2x	-	-	-	39.4	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_r101_fpn_2x_20181129-73e7ade7.pth)
X-101-32x4d-FPN	pytorch	1x	6.9	0.672	10.3	40.1	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_32x4d_fpn_1x_20181218-ad81c133.pth)
X-101-32x4d-FPN	pytorch	2x	-	-	-	40.4	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_32x4d_fpn_2x_20181218-0ed58946.pth)
X-101-64x4d-FPN	pytorch	1x	9.8	1.040	7.3	41.3	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_64x4d_fpn_1x_20181218-c9c69c8f.pth)
X-101-64x4d-FPN	pytorch	2x	-	-	-	40.7	model(https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/faster_rcnn_x101_64x4d_fpn_2x_20181218-fe94f9b8.pth)
HRNetV2p-W18	pytorch	1x	-	-	-	36.1	model(