MMDetection 基準測試 和 Model Zoo | 三
做者|open-mmlab
編譯|Flin
來源|Githubhtml
基準測試 和 Model Zoo
環境
硬件
- 8 個 NVIDIA Tesla V100 GPUs
- Intel Xeon 4114 CPU @ 2.20GHz
軟件環境
- Python 3.6 / 3.7
- PyTorch 1.1
- CUDA 9.0.176
- CUDNN 7.0.4
- NCCL 2.1.15
鏡像站點
咱們使用AWS做爲託管model zoo的主要站點,並在阿里雲上維護鏡像。
你能夠在模型網址中把https://s3.ap-northeast-2.ama...://open-mmlab.oss-cn-beijing.aliyuncs.com。git
經常使用設置
- 全部FPN基準和RPN-C4基準均使用8個GPU進行訓練,批處理大小爲16(每一個GPU 2張圖像)。其餘C4基線使用8個批處理大小爲8的GPU進行了訓練(每一個GPU 1張圖像)。
- 全部模型都在
coco_2017_train上訓練以及在coco_2017_val測試。 - 咱們使用分佈式訓練,而且BN層統計信息是固定的。
- 咱們採用與Detectron相同的訓練時間表。1x表示12個epoch,而2x表示24個epoch,這比Detectron的迭代次數略少,而且能夠忽略不計。
- ImageNet上全部pytorch樣式的預訓練主幹都來自PyTorchmodel zoo。
- 爲了與其餘代碼庫進行公平比較,咱們將GPU內存報告
torch.cuda.max_memory_allocated()爲全部8個GPU 的最大值。請注意,此值一般小於nvidia-smi顯示的值。 - 咱們將推理時間報告爲整體時間,包括數據加載,網絡轉發和後處理。
基線
具備不一樣主幹的更多模型將添加到model zoo。github
RPN
| Backbone | Style | Lr schd | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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 | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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 | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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 (有預先計算的proposals)
| Backbone | Style | 類型 | Lr schd | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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 | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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 | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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 | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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:服務器
- 20e級聯(掩碼)R-CNN中的時間表指示在第16和19個epoch減小lr,總共減小20個epoch。
混合任務級聯(HTC)
| Backbone | Style | Lr schd | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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:網絡
- 有關詳細信息和更強大的模型(50.7 / 43.9),請參閱混合任務級聯(https://github.com/open-mmlab...
SSD
| Backbone | Size | Style | Lr schd | 內存 (GB) | 訓練時間 (s/iter) | 最短期 (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:機器學習
-
cudnn.benchmark設置爲True用於SSD訓練和測試。 - 對於batch size= 1和batch size= 8,報告推理時間。
- 因爲模型參數和nms,COCO和VOC的速度有所不一樣。
組規範化(GN)
有關詳細信息,請參考組規範化(https://github.com/open-mmlab...。分佈式
權重標準化
有關詳細信息,請參考權重標準化(https://github.com/open-mmlab...。ide
可變形卷積v2
有關詳細信息,請參閱可變形卷積網絡(https://github.com/open-mmlab...。性能
CARAFE：功能的內容感知重組
有關詳細信息,請參考CARAFE(https://github.com/open-mmlab...。學習
Instaboost
有關詳細信息,請參考Instaboost(https://github.com/open-mmlab...。
Libra R-CNN
有關詳細信息,請參考Libra R-CNN(https://github.com/open-mmlab...。
Guided Anchoring
有關詳細信息,請參閱Guided Anchoring(https://github.com/open-mmlab...。
FCOS
有關詳細信息,請參閱FCOS(https://github.com/open-mmlab...。
FoveaBox
有關詳細信息,請參考FoveaBox(https://github.com/open-mmlab...。
RepPoints
有關詳細信息,請參考RepPoints(https://github.com/open-mmlab...。
FreeAnchor
有關詳細信息,請參考FreeAnchor(https://github.com/open-mmlab...。
Grid R-CNN (plus)
有關詳細信息,請參考Grid R-CNN(https://github.com/open-mmlab...。
GHM
有關詳細信息,請參閱GHM(https://github.com/open-mmlab...。
GCNet
有關詳細信息,請參考GCNet(https://github.com/open-mmlab...。
HRNet
有關詳細信息,請參考HRNet(https://github.com/open-mmlab...。
Mask Scoring R-CNN
有關詳細信息,請參考Mask Scoring R-CNN(https://github.com/open-mmlab...。
Train from Scratch
有關詳細信息,請參考 從新思考ImageNet預訓練(https://github.com/open-mmlab...。
NAS-FPN
有關詳細信息,請參閱NAS-FPN(https://github.com/open-mmlab...。
ATSS
有關詳細信息,請參考ATSS(https://github.com/open-mmlab...。
其餘數據集
咱們還對PASCAL VOC(https://github.com/open-mmlab...://github.com/open-mmlab/ mmdetection / blob / master / configs / cityscapes)和WIDER FACE(https://github.com/open-mmlab...。
與 Detectron 和 maskrcnn-benchmark 的比較
咱們將mmdetection與Detectron(https://github.com/facebookre... 和maskrcnn-benchmark(https://github.com/facebookre...。使用的主幹是R-50-FPN。
一般來講,mmdetection與Detectron相比具備3個優點。
- 更高的性能(尤爲是在mask AP方面)
- 更快的訓練速度
- 高效記憶
性能
Detectron和maskrcnn-benchmark使用Caffe風格的ResNet做爲主幹。咱們使用caffe樣式(權重從(https://github.com/facebookre... 和pytorch樣式(權重來自官方model zoo)ResNet主幹報告結果,表示爲pytorch樣式結果 / caffe樣式結果。
咱們發現,pytorch風格的ResNet一般比caffe風格的ResNet收斂慢,所以在1倍進度中致使結果略低,但2倍進度的最終結果則較高。
| 類型 | 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 / - |
訓練速度
訓練速度以s/iter爲單位。越低越好。
| 類型 | 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服務器(P100 / V100)比咱們使用的服務器稍快。mmdetection在FB的服務器上也能夠稍快一些地運行。
- 2。爲了公平比較,咱們在此處列出了caffe的結果。
推理速度
推理速度在單個GPU上以fps(img / s)進行測量。越高越好。
| 類型 | 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 |
訓練內存
| 類型 | 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 |
毫無疑問,maskrcnn基準測試和mmdetection比Detectron的存儲效率更高,而主要優勢是PyTorch自己。咱們還執行一些內存優化來推進它向前發展。
請注意,Caffe2和PyTorch具備不一樣的API,以經過不一樣的實現獲取內存使用狀況。對於全部代碼庫,nvidia-smi顯示的內存使用量均大於上表中報告的數字。
原文連接：https://mmdetection.readthedo...
歡迎關注磐創AI博客站：
http://panchuang.net/
sklearn機器學習中文官方文檔：
http://sklearn123.com/
歡迎關注磐創博客資源彙總站：
http://docs.panchuang.net/
相關文章
- 1. Caffe Model Zoo
- 2. MMDetection: 開源檢測工具箱和基準【PyTorch】
- 3. 單元測試和基準測試
- 4. ubuntu16.04安裝cuda10.1+cudnn7.6.3，測試detectron2和mmdetection
- 5. 【mmdetection 】analyze_logs.py等工具測試
- 6. mmdetection框架 測試方法
- 7. Mysql基準測試
- 8. MMDetection專欄開篇
- 9. mysql基準測試
- 10. MySQL基準測試
- 更多相關文章...
- • Maven 構建 & 項目測試 - Maven教程
- • Lua 調試(Debug) - Lua 教程
- • ☆基於Java Instrument的Agent實現
- • Kotlin學習（一）基本語法
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
