MODEL_ZOO.md 42.4 KB
Newer Older
Kai Chen's avatar
Kai Chen committed
1
2
3
4
5
6
7
8
9
10
11
# Benchmark and Model Zoo

## Environment

### Hardware

- 8 NVIDIA Tesla V100 GPUs
- Intel Xeon 4114 CPU @ 2.20GHz

### Software environment

Kai Chen's avatar
Kai Chen committed
12
- Python 3.6 / 3.7
Kai Chen's avatar
Kai Chen committed
13
- PyTorch 1.1
Kai Chen's avatar
Kai Chen committed
14
15
16
17
- CUDA 9.0.176
- CUDNN 7.0.4
- NCCL 2.1.15

Kai Chen's avatar
Kai Chen committed
18
19
20
## Mirror sites

We use AWS as the main site to host our model zoo, and maintain a mirror on aliyun.
Kai Chen's avatar
Kai Chen committed
21
You can replace `https://s3.ap-northeast-2.amazonaws.com/open-mmlab` with `https://open-mmlab.oss-cn-beijing.aliyuncs.com` in model urls.
Kai Chen's avatar
Kai Chen committed
22
23
24

## Common settings

myownskyW7's avatar
myownskyW7 committed
25
- All FPN baselines and RPN-C4 baselines were trained using 8 GPU with a batch size of 16 (2 images per GPU). Other C4 baselines were trained using 8 GPU with a batch size of 8 (1 image per GPU).
Kai Chen's avatar
Kai Chen committed
26
27
28
29
- All models were trained on `coco_2017_train`, and tested on the `coco_2017_val`.
- We use distributed training and BN layer stats are fixed.
- We adopt the same training schedules as Detectron. 1x indicates 12 epochs and 2x indicates 24 epochs, which corresponds to slightly less iterations than Detectron and the difference can be ignored.
- All pytorch-style pretrained backbones on ImageNet are from PyTorch model zoo.
30
31
- For fair comparison with other codebases, we report the GPU memory as the maximum value of `torch.cuda.max_memory_allocated()` for all 8 GPUs. Note that this value is usually less than what `nvidia-smi` shows.
- We report the inference time as the overall time including data loading, network forwarding and post processing.
Kai Chen's avatar
Kai Chen committed
32
33
34
35


## Baselines

36
More models with different backbones will be added to the model zoo.
Kai Chen's avatar
Kai Chen committed
37
38
39

### RPN

myownskyW7's avatar
myownskyW7 committed
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
|    Backbone     |  Style  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (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) |
Kai Chen's avatar
Kai Chen committed
56
57
58

### Faster R-CNN

myownskyW7's avatar
myownskyW7 committed
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
|    Backbone     |  Style  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (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) |
75
76
77
78
|   HRNetV2p-W18   | pytorch |   1x    |    -     |          -          |       -        |  36.1  |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/faster_rcnn_hrnetv2p_w18_1x_20190522-e368c387.pth)    |
|   HRNetV2p-W18   | pytorch |   2x    |    -     |          -          |       -        |  38.3  |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/faster_rcnn_hrnetv2p_w18_2x_20190810-9c8615d5.pth) |
|   HRNetV2p-W32   | pytorch |   1x    |    -     |          -          |       -        |  39.5  |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/faster_rcnn_hrnetv2p_w32_1x_20190522-d22f1fef.pth)    |
|   HRNetV2p-W32   | pytorch |   2x    |    -     |          -          |       -        |  40.6  |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/faster_rcnn_hrnetv2p_w32_2x_20190810-24e8912a.pth) |
79
80
81
|   HRNetV2p-W48   | pytorch |   1x    |    -     |          -          |       -        |  40.9  |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/faster_rcnn_hrnetv2p_w48_1x_20190820-5c6d0903.pth)    |
|   HRNetV2p-W48   | pytorch |   2x    |    -     |          -          |       -        |  41.5  |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/faster_rcnn_hrnetv2p_w48_2x_20190820-79fb8bfc.pth) |

Kai Chen's avatar
Kai Chen committed
82
83
84

### Mask R-CNN

myownskyW7's avatar
myownskyW7 committed
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
|    Backbone     |  Style  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP |                                                             Download                                                             |
| :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :-----: | :------------------------------------------------------------------------------------------------------------------------------: |
|     R-50-C4     |  caffe  |   1x    |    -     |          -          |      8.1       |  35.9  |  31.5   |      [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_caffe_c4_1x-02a4ad3b.pth)       |
|     R-50-C4     |  caffe  |   2x    |   4.2    |        0.43         |      8.1       |  37.9  |  32.9   |      [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_caffe_c4_2x-d150973a.pth)       |
|     R-50-C4     | pytorch |   1x    |    -     |          -          |      7.9       |  35.1  |  31.2   |         [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_c4_1x-a83bdd40.pth)          |
|     R-50-C4     | pytorch |   2x    |    -     |          -          |      8.0       |  37.2  |  32.5   |         [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_c4_2x-3cf169a9.pth)          |
|    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.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_1x_20181010-069fa190.pth)     |
|    R-50-FPN     | pytorch |   2x    |    -     |          -          |       -        |  38.5  |  35.1   |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r50_fpn_2x_20181010-41d35c05.pth)     |
|    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.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_1x_20181129-34ad1961.pth)    |
|    R-101-FPN    | pytorch |   2x    |    -     |          -          |       -        |  40.3  |  36.5   |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_r101_fpn_2x_20181129-a254bdfc.pth)    |
| X-101-32x4d-FPN | pytorch |   1x    |   7.1    |        0.759        |      8.3       |  41.1  |  37.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_32x4d_fpn_1x_20181218-44e635cc.pth) |
| X-101-32x4d-FPN | pytorch |   2x    |    -     |          -          |       -        |  41.4  |  37.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_32x4d_fpn_2x_20181218-f023dffa.pth) |
| X-101-64x4d-FPN | pytorch |   1x    |   10.0   |        1.102        |      6.5       |  42.1  |  38.0   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_64x4d_fpn_1x_20181218-cb159987.pth) |
| X-101-64x4d-FPN | pytorch |   2x    |    -     |          -          |       -        |  42.0  |  37.7   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/mask_rcnn_x101_64x4d_fpn_2x_20181218-ea936e44.pth) |
101
102
103
104
|   HRNetV2p-W18   | pytorch |   1x    |    -     |          -          |       -        |  37.3  |  34.2   |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/mask_rcnn_hrnetv2p_w18_1x_20190522-c8ad459f.pth)    |
|   HRNetV2p-W18   | pytorch |   2x    |    -     |          -          |       -        |  39.2  |  35.7   |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/mask_rcnn_hrnetv2p_w18_2x_20190810-1e4747eb.pth)   |
|   HRNetV2p-W32   | pytorch |   1x    |    -     |          -          |       -        |  40.7  |  36.8   |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/mask_rcnn_hrnetv2p_w32_1x_20190522-374aaa00.pth)    |
|   HRNetV2p-W32   | pytorch |   2x    |    -     |          -          |       -        |  41.7  |  37.5   |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/mask_rcnn_hrnetv2p_w32_2x_20190810-773eca75.pth) |
105
106
|   HRNetV2p-W48   | pytorch |   1x    |    -     |          -          |       -        |  42.4  |  38.1   |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/mask_rcnn_hrnetv2p_w48_1x_20190820-0923d1ad.pth) |
|   HRNetV2p-W48   | pytorch |   2x    |    -     |          -          |       -        |  42.9  |  38.3   |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/mask_rcnn_hrnetv2p_w48_2x_20190820-70df51b2.pth) |
Kai Chen's avatar
Kai Chen committed
107

Kai Chen's avatar
Kai Chen committed
108
### Fast R-CNN (with pre-computed proposals)
Kai Chen's avatar
Kai Chen committed
109

myownskyW7's avatar
myownskyW7 committed
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
| Backbone  |  Style  |  Type  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP |                                                            Download                                                             |
| :-------: | :-----: | :----: | :-----: | :------: | :-----------------: | :------------: | :----: | :-----: | :-----------------------------------------------------------------------------------------------------------------------------: |
|  R-50-C4  |  caffe  | Faster |   1x    |    -     |          -          |      6.7       |  35.0  |    -    |      [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_caffe_c4_1x-0ef9a60b.pth)      |
|  R-50-C4  |  caffe  | Faster |   2x    |   3.8    |        0.34         |      6.6       |  36.4  |    -    |         [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_c4_2x-657a9fc6.pth)         |
|  R-50-C4  | pytorch | Faster |   1x    |    -     |          -          |      6.3       |  34.2  |    -    |         [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_c4_1x-2bc00ca9.pth)         |
|  R-50-C4  | pytorch | Faster |   2x    |    -     |          -          |      6.1       |  35.8  |    -    |      [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_caffe_c4_2x-9171d0fc.pth)      |
| 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.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_fpn_1x_20181010-08160859.pth)    |
|  R-50-C4  |  caffe  |  Mask  |   1x    |    -     |          -          |      8.1       |  35.9  |  31.5   |   [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_caffe_c4_1x-b43f7f3c.pth)    |
|  R-50-C4  |  caffe  |  Mask  |   2x    |   4.2    |        0.43         |      8.1       |  37.9  |  32.9   |   [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_caffe_c4_2x-e3580184.pth)    |
|  R-50-C4  | pytorch |  Mask  |   1x    |    -     |          -          |      7.9       |  35.1  |  31.2   |      [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_c4_1x-bc7fa8c8.pth)       |
|  R-50-C4  | pytorch |  Mask  |   2x    |    -     |          -          |      8.0       |  37.2  |  32.5   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_fpn_2x_20181010-5048cb03.pth)  |
| R-50-FPN  | pytorch | Faster |   2x    |    -     |          -          |       -        |  37.1  |    -    |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r50_fpn_2x_20181010-d263ada5.pth)    |
| 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.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r101_fpn_1x_20181129-ffaa2eb0.pth)    |
| R-101-FPN | pytorch | Faster |   2x    |    -     |          -          |       -        |  38.8  |    -    |   [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_rcnn_r101_fpn_2x_20181129-9dba92ce.pth)    |
| 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.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_fpn_1x_20181010-e030a38f.pth)  |
| R-50-FPN  | pytorch |  Mask  |   2x    |    -     |          -          |       -        |  37.9  |  34.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r50_fpn_2x_20181010-5048cb03.pth)  |
| 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.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r101_fpn_1x_20181129-2273fa9b.pth) |
| R-101-FPN | pytorch |  Mask  |   2x    |    -     |          -          |       -        |  39.9  |  36.4   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fast_mask_rcnn_r101_fpn_2x_20181129-bf63ec5e.pth) |
Kai Chen's avatar
Kai Chen committed
132

Kai Chen's avatar
Kai Chen committed
133
### RetinaNet
Kai Chen's avatar
Kai Chen committed
134

myownskyW7's avatar
myownskyW7 committed
135
136
137
138
|    Backbone     |  Style  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (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.amazonaws.com/open-mmlab/mmdetection/models/retinanet_r50_fpn_1x_20181125-7b0c2548.pth)     |
Cao Yuhang's avatar
Cao Yuhang committed
139
|    R-50-FPN     | pytorch |   2x    |    -     |          -          |       -        |  36.4  |    [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/retinanet_r50_fpn_2x_20190616-75574209.pth)     |
myownskyW7's avatar
myownskyW7 committed
140
141
142
143
144
145
146
|    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.amazonaws.com/open-mmlab/mmdetection/models/retinanet_r101_fpn_1x_20181129-f016f384.pth)    |
|    R-101-FPN    | pytorch |   2x    |    -     |          -          |       -        |  38.1  |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_r101_fpn_2x_20181129-72c14526.pth)    |
| X-101-32x4d-FPN | pytorch |   1x    |   6.7    |        0.632        |      9.3       |  39.0  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_32x4d_fpn_1x_20190501-967812ba.pth) |
| X-101-32x4d-FPN | pytorch |   2x    |    -     |          -          |       -        |  39.3  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_32x4d_fpn_2x_20181218-8596452d.pth) |
| X-101-64x4d-FPN | pytorch |   1x    |   9.6    |        0.993        |      7.0       |  40.0  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_64x4d_fpn_1x_20181218-a0a22662.pth) |
| X-101-64x4d-FPN | pytorch |   2x    |    -     |          -          |       -        |  39.6  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/retinanet_x101_64x4d_fpn_2x_20181218-5e88d045.pth) |
Kai Chen's avatar
Kai Chen committed
147

Kai Chen's avatar
Kai Chen committed
148
149
### Cascade R-CNN

myownskyW7's avatar
myownskyW7 committed
150
151
152
153
154
155
156
157
158
159
160
161
162
|    Backbone     |  Style  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP |                                                              Download                                                               |
| :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :---------------------------------------------------------------------------------------------------------------------------------: |
|     R-50-C4     |  caffe  |   1x    |   8.7    |        0.92         |      5.0       |  38.7  |      [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r50_caffe_c4_1x-7c85c62b.pth)       |
|    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.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r50_fpn_1x_20190501-3b6211ab.pth)     |
|    R-50-FPN     | pytorch |   20e   |    -     |          -          |       -        |  41.1  |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r50_fpn_20e_20181123-db483a09.pth)    |
|    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.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r101_fpn_1x_20181129-d64ebac7.pth)    |
|    R-101-FPN    | pytorch |   20e   |    -     |          -          |       -        |  42.5  |   [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_r101_fpn_20e_20181129-b46dcede.pth)    |
| X-101-32x4d-FPN | pytorch |   1x    |   7.2    |        0.770        |      8.9       |  43.6  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_32x4d_fpn_1x_20190501-af628be5.pth) |
| X-101-32x4d-FPN | pytorch |   20e   |    -     |          -          |       -        |  44.0  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_32x4d_fpn_2x_20181218-28f73c4c.pth) |
| X-101-64x4d-FPN | pytorch |   1x    |   10.0   |        1.133        |      6.7       |  44.5  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_64x4d_fpn_1x_20181218-e2dc376a.pth) |
| X-101-64x4d-FPN | pytorch |   20e   |    -     |          -          |       -        |  44.7  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_rcnn_x101_64x4d_fpn_2x_20181218-5add321e.pth) |
163
164
165
|   HRNetV2p-W18   | pytorch |   20e   |    -     |          -          |       -        |  41.2  | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/cascade_rcnn_hrnetv2p_w18_20e_20190810-132012d0.pth) |
|   HRNetV2p-W32   | pytorch |   20e   |    -     |          -          |       -        |  43.7  | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/cascade_rcnn_hrnetv2p_w32_20e_20190522-55bec4ee.pth)|
|   HRNetV2p-W48   | pytorch |   20e   |    -     |          -          |       -        |  44.6  | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/cascade_rcnn_hrnetv2p_w48_20e_20190810-f40ed8e1.pth) |
Kai Chen's avatar
Kai Chen committed
166
167
168

### Cascade Mask R-CNN

myownskyW7's avatar
myownskyW7 committed
169
170
171
172
173
174
175
176
177
178
179
180
181
|    Backbone     |  Style  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (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.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r50_caffe_c4_1x-f72cc254.pth)       |
|    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.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r50_fpn_1x_20181123-88b170c9.pth)     |
|    R-50-FPN     | pytorch |   20e   |    -     |          -          |       -        |  42.3  |  36.6   |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r50_fpn_20e_20181123-6e0c9713.pth)     |
|    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.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r101_fpn_1x_20181129-64f00602.pth)     |
|    R-101-FPN    | pytorch |   20e   |    -     |          -          |       -        |  43.3  |  37.6   |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_r101_fpn_20e_20181129-cb85151d.pth)    |
| X-101-32x4d-FPN | pytorch |   1x    |   8.4    |        0.976        |      6.6       |  44.4  |  38.2   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_32x4d_fpn_1x_20181218-1d944c89.pth)  |
| X-101-32x4d-FPN | pytorch |   20e   |    -     |          -          |       -        |  44.7  |  38.6   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_32x4d_fpn_20e_20181218-761a3473.pth) |
| X-101-64x4d-FPN | pytorch |   1x    |   11.4   |        1.33         |      5.3       |  45.4  |  39.1   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_64x4d_fpn_1x_20190501-827e0a70.pth)  |
| X-101-64x4d-FPN | pytorch |   20e   |    -     |          -          |       -        |  45.7  |  39.4   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/cascade_mask_rcnn_x101_64x4d_fpn_20e_20181218-630773a7.pth) |
182
183
184
|   HRNetV2p-W18   | pytorch |   20e   |    -     |          -          |       -        |  41.9  |  36.4   | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/cascade_mask_rcnn_hrnetv2p_w18_20e_20190810-054fb7bf.pth) |
|   HRNetV2p-W32   | pytorch |   20e   |    -     |          -          |       -        |  44.5  |  38.5   | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e_20190810-76f61cd0.pth) |
|   HRNetV2p-W48   | pytorch |   20e   |    -     |          -          |       -        |  46.0  |  39.5   | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/cascade_mask_rcnn_hrnetv2p_w48_20e_20190810-d04a1415.pth) |
Kai Chen's avatar
Kai Chen committed
185

pangjm's avatar
pangjm committed
186
187
**Notes:**

Kai Chen's avatar
Kai Chen committed
188
- The `20e` schedule in Cascade (Mask) R-CNN indicates decreasing the lr at 16 and 19 epochs, with a total of 20 epochs.
Kai Chen's avatar
Kai Chen committed
189

190
191
### Hybrid Task Cascade (HTC)

myownskyW7's avatar
myownskyW7 committed
192
193
|    Backbone     |  Style  | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | mask AP |                                                            Download                                                             |
| :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :-----: | :-----------------------------------------------------------------------------------------------------------------------------: |
194
|    R-50-FPN     | pytorch |   1x    |   7.4    |        0.936        |      4.1       |  42.1  |  37.3   |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_r50_fpn_1x_20190408-878c1712.pth)     |
myownskyW7's avatar
myownskyW7 committed
195
|    R-50-FPN     | pytorch |   20e   |    -     |          -          |       -        |  43.2  |  38.1   |    [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_r50_fpn_20e_20190408-c03b7015.pth)     |
196
|    R-101-FPN    | pytorch |   20e   |   9.3    |        1.051        |      4.0       |  44.9  |  39.4   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_r101_fpn_20e_20190408-a2e586db.pth)    |
myownskyW7's avatar
myownskyW7 committed
197
198
| X-101-32x4d-FPN | pytorch |   20e   |   5.8    |        0.769        |      3.8       |  46.1  |  40.3   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_x101_32x4d_fpn_20e_20190408-9eae4d0b.pth) |
| X-101-64x4d-FPN | pytorch |   20e   |   7.5    |        1.120        |      3.5       |  46.9  |  40.8   | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_x101_64x4d_fpn_20e_20190408-497f2561.pth) |
199
200
201
|   HRNetV2p-W18   | pytorch |   20e   |    -     |          -          |       -        |  43.1  |  37.9   | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/htc_hrnetv2p_w18_20e_20190810-d70072af.pth) |
|   HRNetV2p-W32   | pytorch |   20e   |    -     |          -          |       -        |  45.3  |  39.6   | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/htc_hrnetv2p_w32_20e_20190810-82f9ef5a.pth) |
|   HRNetV2p-W48   | pytorch |   20e   |    -     |          -          |       -        |  46.8  | 40.7    | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/htc_hrnetv2p_w48_20e_20190810-f6d2c3fd.pth) |
202
|   HRNetV2p-W48   | pytorch |   28e   |    -     |          -          |       -        |  47.0  |  41.0   | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/htc_hrnetv2p_w48_28e_20190810-a4274b38.pth) |
Kai Chen's avatar
Kai Chen committed
203
204
205

**Notes:**

Kai Chen's avatar
Kai Chen committed
206
- Please refer to [Hybrid Task Cascade](https://github.com/open-mmlab/mmdetection/blob/master/configs/htc) for details and more a powerful model (50.7/43.9).
207

Kai Chen's avatar
Kai Chen committed
208
209
### SSD

myownskyW7's avatar
myownskyW7 committed
210
211
212
213
| Backbone | Size  | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP |                                                             Download                                                              |
| :------: | :---: | :---: | :-----: | :------: | :-----------------: | :------------: | :----: | :-------------------------------------------------------------------------------------------------------------------------------: |
|  VGG16   |  300  | caffe |  120e   |   3.5    |        0.256        |  25.9 / 34.6   |  25.7  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ssd300_coco_vgg16_caffe_120e_20181221-84d7110b.pth) |
|  VGG16   |  512  | caffe |  120e   |   7.6    |        0.412        |  20.7 / 25.4   |  29.3  | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/ssd512_coco_vgg16_caffe_120e_20181221-d48b0be8.pth) |
Kai Chen's avatar
Kai Chen committed
214
215
216
217
218

**Notes:**

- `cudnn.benchmark` is set as `True` for SSD training and testing.
- Inference time is reported for batch size = 1 and batch size = 8.
Kai Chen's avatar
Kai Chen committed
219
- The speed on COCO and VOC are different due to model parameters and nms.
Kai Chen's avatar
Kai Chen committed
220

Kai Chen's avatar
Kai Chen committed
221
222
### Group Normalization (GN)

Kai Chen's avatar
Kai Chen committed
223
Please refer to [Group Normalization](https://github.com/open-mmlab/mmdetection/blob/master/configs/gn) for details.
Kai Chen's avatar
Kai Chen committed
224

Kai Chen's avatar
Kai Chen committed
225
### Weight Standardization
Kai Chen's avatar
Kai Chen committed
226

Kai Chen's avatar
Kai Chen committed
227
Please refer to [Weight Standardization](https://github.com/open-mmlab/mmdetection/blob/master/configs/gn+ws) for details.
Kai Chen's avatar
Kai Chen committed
228

Kai Chen's avatar
Kai Chen committed
229
### Deformable Convolution v2
Kai Chen's avatar
Kai Chen committed
230

Kai Chen's avatar
Kai Chen committed
231
Please refer to [Deformable Convolutional Networks](https://github.com/open-mmlab/mmdetection/blob/master/configs/dcn) for details.
Kai Chen's avatar
Kai Chen committed
232

GothicAi's avatar
GothicAi committed
233
234
235
236
### Instaboost

Please refer to [Instaboost](https://github.com/open-mmlab/mmdetection/blob/master/configs/instaboost) for details.

237
238
### Libra R-CNN

Kai Chen's avatar
Kai Chen committed
239
Please refer to [Libra R-CNN](https://github.com/open-mmlab/mmdetection/blob/master/configs/libra_rcnn) for details.
240

241
242
### Guided Anchoring

Kai Chen's avatar
Kai Chen committed
243
Please refer to [Guided Anchoring](https://github.com/open-mmlab/mmdetection/blob/master/configs/guided_anchoring) for details.
244

Kai Chen's avatar
Kai Chen committed
245
246
### FCOS

Kai Chen's avatar
Kai Chen committed
247
Please refer to [FCOS](https://github.com/open-mmlab/mmdetection/blob/master/configs/fcos) for details.
Kai Chen's avatar
Kai Chen committed
248

Tao Kong's avatar
Tao Kong committed
249
250
### FoveaBox

Kai Chen's avatar
Kai Chen committed
251
Please refer to [FoveaBox](https://github.com/open-mmlab/mmdetection/blob/master/configs/foveabox) for details.
Tao Kong's avatar
Tao Kong committed
252

Kai Chen's avatar
Kai Chen committed
253
254
### RepPoints

Kai Chen's avatar
Kai Chen committed
255
Please refer to [RepPoints](https://github.com/open-mmlab/mmdetection/blob/master/configs/reppoints) for details.
Kai Chen's avatar
Kai Chen committed
256
257
258

### FreeAnchor

Kai Chen's avatar
Kai Chen committed
259
Please refer to [FreeAnchor](https://github.com/open-mmlab/mmdetection/blob/master/configs/free_anchor) for details.
Kai Chen's avatar
Kai Chen committed
260

Kai Chen's avatar
Kai Chen committed
261
262
### Grid R-CNN (plus)

Kai Chen's avatar
Kai Chen committed
263
Please refer to [Grid R-CNN](https://github.com/open-mmlab/mmdetection/blob/master/configs/grid_rcnn) for details.
Kai Chen's avatar
Kai Chen committed
264
265
266

### GHM

Kai Chen's avatar
Kai Chen committed
267
Please refer to [GHM](https://github.com/open-mmlab/mmdetection/blob/master/configs/ghm) for details.
Kai Chen's avatar
Kai Chen committed
268
269
270

### GCNet

Kai Chen's avatar
Kai Chen committed
271
Please refer to [GCNet](https://github.com/open-mmlab/mmdetection/blob/master/configs/gcnet) for details.
Kai Chen's avatar
Kai Chen committed
272
273

### HRNet
Kai Chen's avatar
Kai Chen committed
274
Please refer to [HRNet](https://github.com/open-mmlab/mmdetection/blob/master/configs/hrnet) for details.
Kai Chen's avatar
Kai Chen committed
275
276
277

### Mask Scoring R-CNN

Kai Chen's avatar
Kai Chen committed
278
Please refer to [Mask Scoring R-CNN](https://github.com/open-mmlab/mmdetection/blob/master/configs/ms_rcnn) for details.
Kai Chen's avatar
Kai Chen committed
279
280
281

### Train from Scratch

Kai Chen's avatar
Kai Chen committed
282
Please refer to [Rethinking ImageNet Pre-training](https://github.com/open-mmlab/mmdetection/blob/master/configs/scratch) for details.
Kai Chen's avatar
Kai Chen committed
283

Kai Chen's avatar
Kai Chen committed
284
285
286
### NAS-FPN
Please refer to [NAS-FPN](https://github.com/open-mmlab/mmdetection/blob/master/configs/nas_fpn) for details.

287
288
289
### ATSS
Please refer to [ATSS](https://github.com/open-mmlab/mmdetection/blob/master/configs/atss) for details.

Kai Chen's avatar
Kai Chen committed
290
291
### Other datasets

Kai Chen's avatar
Kai Chen committed
292
We also benchmark some methods on [PASCAL VOC](https://github.com/open-mmlab/mmdetection/blob/master/configs/pascal_voc), [Cityscapes](https://github.com/open-mmlab/mmdetection/blob/master/configs/cityscapes) and [WIDER FACE](https://github.com/open-mmlab/mmdetection/blob/master/configs/wider_face).
Kai Chen's avatar
Kai Chen committed
293
294


295
## Comparison with Detectron and maskrcnn-benchmark
Kai Chen's avatar
Kai Chen committed
296
297

We compare mmdetection with [Detectron](https://github.com/facebookresearch/Detectron)
298
and [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark). The backbone used is R-50-FPN.
Kai Chen's avatar
Kai Chen committed
299

Kai Chen's avatar
Kai Chen committed
300
301
302
303
304
305
In general, mmdetection has 3 advantages over Detectron.

- **Higher performance** (especially in terms of mask AP)
- **Faster training speed**
- **Memory efficient**

Kai Chen's avatar
Kai Chen committed
306
307
### Performance

308
Detectron and maskrcnn-benchmark use caffe-style ResNet as the backbone.
Kai Chen's avatar
Kai Chen committed
309
310
311
312
313
We report results using both caffe-style (weights converted from
[here](https://github.com/facebookresearch/Detectron/blob/master/MODEL_ZOO.md#imagenet-pretrained-models))
and pytorch-style (weights from the official model zoo) ResNet backbone,
indicated as *pytorch-style results* / *caffe-style results*.

314
315
316
317
We find that pytorch-style ResNet usually converges slower than caffe-style ResNet,
thus leading to slightly lower results in 1x schedule, but the final results
of 2x schedule is higher.

Kai Chen's avatar
Kai Chen committed
318
319
320
321
322
<table>
  <tr>
    <th>Type</th>
    <th>Lr schd</th>
    <th>Detectron</th>
323
    <th>maskrcnn-benchmark</th>
Kai Chen's avatar
Kai Chen committed
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
    <th>mmdetection</th>
  </tr>
  <tr>
    <td rowspan="2">RPN</td>
    <td>1x</td>
    <td>57.2</td>
    <td>-</td>
    <td>57.1 / 58.2</td>
  </tr>
  <tr>
    <td>2x</td>
    <td>-</td>
    <td>-</td>
    <td>57.6 / -</td>
  </tr>
  <tr>
    <td rowspan="2">Faster R-CNN</td>
    <td>1x</td>
    <td>36.7</td>
343
    <td>36.8</td>
344
    <td>36.4 / 36.6</td>
Kai Chen's avatar
Kai Chen committed
345
346
347
348
349
350
351
352
353
354
355
  </tr>
  <tr>
    <td>2x</td>
    <td>37.9</td>
    <td>-</td>
    <td>37.7 / -</td>
  </tr>
  <tr>
    <td rowspan="2">Mask R-CNN</td>
    <td>1x</td>
    <td>37.7 &amp; 33.9</td>
356
    <td>37.8 &amp; 34.2</td>
357
    <td>37.3 &amp; 34.2 / 37.4 &amp; 34.3</td>
Kai Chen's avatar
Kai Chen committed
358
359
360
361
362
  </tr>
  <tr>
    <td>2x</td>
    <td>38.6 &amp; 34.5</td>
    <td>-</td>
363
    <td>38.5 &amp; 35.1 / -</td>
Kai Chen's avatar
Kai Chen committed
364
  </tr>
Kai Chen's avatar
Kai Chen committed
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
  <tr>
    <td rowspan="2">Fast R-CNN</td>
    <td>1x</td>
    <td>36.4</td>
    <td>-</td>
    <td>35.8 / 36.6</td>
  </tr>
  <tr>
    <td>2x</td>
    <td>36.8</td>
    <td>-</td>
    <td>37.1 / -</td>
  </tr>
  <tr>
    <td rowspan="2">Fast R-CNN (w/mask)</td>
    <td>1x</td>
    <td>37.3 &amp; 33.7</td>
    <td>-</td>
    <td>36.8 &amp; 34.1 / 37.3 &amp; 34.5</td>
  </tr>
  <tr>
    <td>2x</td>
    <td>37.7 &amp; 34.0</td>
    <td>-</td>
    <td>37.9 &amp; 34.8 / -</td>
  </tr>
Kai Chen's avatar
Kai Chen committed
391
392
</table>

Kai Chen's avatar
Kai Chen committed
393
### Training Speed
Kai Chen's avatar
Kai Chen committed
394

Kai Chen's avatar
Kai Chen committed
395
The training speed is measure with s/iter. The lower, the better.
Kai Chen's avatar
Kai Chen committed
396
397
398
399
400

<table>
  <tr>
    <th>Type</th>
    <th>Detectron (P100<sup>1</sup>)</th>
401
402
    <th>maskrcnn-benchmark (V100)</th>
    <th>mmdetection (V100<sup>2</sup>)</th>
Kai Chen's avatar
Kai Chen committed
403
404
405
406
407
  </tr>
  <tr>
    <td>RPN</td>
    <td>0.416</td>
    <td>-</td>
408
    <td>0.253</td>
Kai Chen's avatar
Kai Chen committed
409
410
411
412
  </tr>
  <tr>
    <td>Faster R-CNN</td>
    <td>0.544</td>
413
414
    <td>0.353</td>
    <td>0.333</td>
Kai Chen's avatar
Kai Chen committed
415
416
417
418
  </tr>
  <tr>
    <td>Mask R-CNN</td>
    <td>0.889</td>
419
420
    <td>0.454</td>
    <td>0.430</td>
Kai Chen's avatar
Kai Chen committed
421
  </tr>
Kai Chen's avatar
Kai Chen committed
422
423
424
425
  <tr>
    <td>Fast R-CNN</td>
    <td>0.285</td>
    <td>-</td>
426
    <td>0.242</td>
Kai Chen's avatar
Kai Chen committed
427
428
429
430
431
  </tr>
  <tr>
    <td>Fast R-CNN (w/mask)</td>
    <td>0.377</td>
    <td>-</td>
432
    <td>0.328</td>
Kai Chen's avatar
Kai Chen committed
433
  </tr>
Kai Chen's avatar
Kai Chen committed
434
435
</table>

436
\*1. Facebook's Big Basin servers (P100/V100) is slightly faster than the servers we use. mmdetection can also run slightly faster on FB's servers.
Kai Chen's avatar
Kai Chen committed
437

438
\*2. For fair comparison, we list the caffe-style results here.
Kai Chen's avatar
Kai Chen committed
439

Kai Chen's avatar
Kai Chen committed
440
441
442
443
444
445
446
447
448

### Inference Speed

The inference speed is measured with fps (img/s) on a single GPU. The higher, the better.

<table>
  <tr>
    <th>Type</th>
    <th>Detectron (P100)</th>
449
450
    <th>maskrcnn-benchmark (V100)</th>
    <th>mmdetection (V100)</th>
Kai Chen's avatar
Kai Chen committed
451
452
453
454
455
  </tr>
  <tr>
    <td>RPN</td>
    <td>12.5</td>
    <td>-</td>
456
    <td>16.9</td>
Kai Chen's avatar
Kai Chen committed
457
458
459
460
  </tr>
  <tr>
    <td>Faster R-CNN</td>
    <td>10.3</td>
461
    <td>7.9</td>
462
    <td>13.5</td>
Kai Chen's avatar
Kai Chen committed
463
464
465
466
  </tr>
  <tr>
    <td>Mask R-CNN</td>
    <td>8.5</td>
467
    <td>7.7</td>
468
    <td>10.2</td>
Kai Chen's avatar
Kai Chen committed
469
  </tr>
Kai Chen's avatar
Kai Chen committed
470
471
472
  <tr>
    <td>Fast R-CNN</td>
    <td>12.5</td>
473
474
    <td>-</td>
    <td>18.4</td>
Kai Chen's avatar
Kai Chen committed
475
476
477
478
  </tr>
  <tr>
    <td>Fast R-CNN (w/mask)</td>
    <td>9.9</td>
479
480
    <td>-</td>
    <td>12.8</td>
Kai Chen's avatar
Kai Chen committed
481
  </tr>
Kai Chen's avatar
Kai Chen committed
482
483
</table>

Kai Chen's avatar
Kai Chen committed
484
485
### Training memory

486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
<table>
  <tr>
    <th>Type</th>
    <th>Detectron</th>
    <th>maskrcnn-benchmark</th>
    <th>mmdetection</th>
  </tr>
  <tr>
    <td>RPN</td>
    <td>6.4</td>
    <td>-</td>
    <td>3.3</td>
  </tr>
  <tr>
    <td>Faster R-CNN</td>
    <td>7.2</td>
    <td>4.4</td>
    <td>3.6</td>
  </tr>
  <tr>
    <td>Mask R-CNN</td>
    <td>8.6</td>
    <td>5.2</td>
    <td>3.8</td>
  </tr>
  <tr>
    <td>Fast R-CNN</td>
    <td>6.0</td>
    <td>-</td>
    <td>3.3</td>
  </tr>
  <tr>
    <td>Fast R-CNN (w/mask)</td>
    <td>7.9</td>
    <td>-</td>
    <td>3.4</td>
  </tr>
</table>

There is no doubt that maskrcnn-benchmark and mmdetection is more memory efficient than Detectron,
and the main advantage is PyTorch itself. We also perform some memory optimizations to push it forward.

Note that Caffe2 and PyTorch have different apis to obtain memory usage with different implementations.
For all codebases, `nvidia-smi` shows a larger memory usage than the reported number in the above table.