diff --git a/MODEL_ZOO.md b/MODEL_ZOO.md
index 3d2eaae6bf4d822b29b1473067f4dd92d18d9ed3..118bcd4c89f7b233614341e9eb7ce1e47cc90418 100644
--- a/MODEL_ZOO.md
+++ b/MODEL_ZOO.md
@@ -72,6 +72,10 @@ More models with different backbones will be added to the model zoo.
| 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](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) |
### Mask R-CNN
@@ -91,6 +95,10 @@ More models with different backbones will be added to the model zoo.
| 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) |
+| 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) |
### Fast R-CNN (with pre-computed proposals)
@@ -147,6 +155,9 @@ More models with different backbones will be added to the model zoo.
| 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) |
+| 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) |
### Cascade Mask R-CNN
@@ -163,6 +174,9 @@ More models with different backbones will be added to the model zoo.
| 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) |
+| 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) |
**Notes:**
@@ -172,11 +186,14 @@ More models with different backbones will be added to the model zoo.
| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (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.amazonaws.com/open-mmlab/mmdetection/models/htc/htc_r50_fpn_1x_20190408-878c1712.pth) |
+| 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) |
| 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) |
-| 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) |
+| 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) |
| 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) |
+| 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) |
**Notes:**
diff --git a/configs/hrnet/README.md b/configs/hrnet/README.md
index 0d80f63580b6439a900a78bb559f3822ddfe1658..fa1be2f8d23c87a2cf0ea3898b094678720ac356 100644
--- a/configs/hrnet/README.md
+++ b/configs/hrnet/README.md
@@ -22,33 +22,71 @@
## Results and Models
-Faster R-CNN
-| Backbone|#Params|GFLOPs|Lr sched|mAP|Download|
-| :--:|:--:|:--:|:--:|:--:|:--:|
-| HRNetV2-W18 |26.2M|159.1| 1x | 36.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/faster_rcnn_hrnetv2_w18_fpn_1x_20190522-e368c387.pth)|
-| HRNetV2-W18 |26.2M|159.1| 20-23-24e | 38.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/faster_rcnn_hrnetv2_w18_fpn_20_23_24e_20190522-ed3c0293.pth)|
-| HRNetV2-W32 |45.0M|245.3| 1x | 39.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/faster_rcnn_hrnetv2_w32_fpn_1x_20190522-d22f1fef.pth)|
-| HRNetV2-W32 |45.0M|245.3| 20-23-24e | 40.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/faster_rcnn_hrnetv2_w32_fpn_20_23_24e_20190522-2d67a5eb.pth)|
-| HRNetV2-W40 |60.5M|314.9| 1x | 40.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/faster_rcnn_hrnetv2_w40_fpn_1x_20190522-30502318.pth)|
-| HRNetV2-W40 |60.5M|314.9| 20-23-24e | 41.4 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/faster_rcnn_hrnetv2_w40_fpn_20_23_24e_20190522-050a7c7f.pth)|
+### Faster R-CNN
+| Backbone | Style | Lr schd | box AP | Download |
+| :-------------: | :-----: | :-----: | :----: | :-----------------: |
+| 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) |
-Mask R-CNN
-|Backbone|Lr sched|mask mAP|box mAP|Download|
-|:--:|:--:|:--:|:--:|:--:|
-| HRNetV2-W18 | 1x | 34.2 | 37.3 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/mask_rcnn_hrnetv2_w18_fpn_1x_20190522-c8ad459f.pth)|
-| HRNetV2-W18 | 20-23-24e | 35.7 | 39.2 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/mask_rcnn_hrnetv2_w18_fpn_20_23_24e_20190522-5c11b7f2.pth)|
-| HRNetV2-W32 | 1x | 36.8 | 40.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/mask_rcnn_hrnetv2_w32_fpn_1x_20190522-374aaa00.pth)|
-| HRNetV2-W32 | 20-23-24e | 37.6 | 42.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/mask_rcnn_hrnetv2_w32_fpn_20_23_24e_20190522-4dd02a79.pth)|
+### Mask R-CNN
+
+| Backbone | Style | Lr schd | box AP | mask AP | Download |
+| :-------------: | :-----: | :-----: | :----: | :----: | :-----------------: |
+| 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) |
+
+
+### Cascade R-CNN
+
+| Backbone | Style | Lr schd | box AP | Download |
+| :-------------: | :-----: | :-----: | :----: | :-----------------: |
+| 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)|
+
+
+### Cascade Mask R-CNN
+
+| Backbone | Style | Lr schd | box AP | mask AP | Download |
+| :-------------: | :-----: | :-----: | :----: | :----: | :-----------------: |
+| 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) |
+
+
+### Hybrid Task Cascade (HTC)
+
+| Backbone | Style | Lr schd | box AP | mask AP | Download |
+| :-------------: | :-----: | :-----: | :----: | :----: | :-----------------: |
+| 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) |
+| 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) |
+| X-101-64x4d-FPN | pytorch | 28e | 46.8 | 40.7 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/htc_x101_64x4d_28e_20190810-d7c19dc0.pth) |
+
+
+### FCOS
+
+| Backbone | Style | GN | MS train | Lr schd | box AP | Download |
+|:---------:|:-------:|:-------:|:--------:|:-------:|:------:|:--------:|
+|HRNetV2p-W18| pytorch | Y | N | 1x | 35.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/fcos_hrnetv2p_w18_1x_20190810-87a17998.pth) |
+|HRNetV2p-W18| pytorch | Y | N | 2x | 38.2 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/fcos_hrnetv2p_w18_2x_20190810-dfd60a7b.pth) |
+|HRNetV2p-W32| pytorch | Y | N | 1x | 37.7 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/fcos_hrnetv2p_w32_1x_20190810-62014622.pth) |
+|HRNetV2p-W32| pytorch | Y | N | 2x | 40.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/fcos_hrnetv2p_w32_2x_20190810-8e987ec1.pth) |
+|HRNetV2p-W18| pytorch | Y | Y | 2x | 38.1 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/fcos_hrnetv2p_w18_mstrain_2x_20190810-eb846b2c.pth) |
+|HRNetV2p-W32| pytorch | Y | Y | 2x | 41.4 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/fcos_hrnetv2p_w32_mstrain_2x_20190810-96127bf8.pth) |
+|HRNetV2p-W48| pytorch | Y | Y | 2x | 42.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/hrnet/fcos_hrnetv2p_w48_mstrain_2x_20190810-f7dc8801.pth) |
-Cascade R-CNN
-|Backbone|Lr sched|mAP|Download|
-|:--:|:--:|:--:|:--:|
-| HRNetV2-W32 | 20e | 43.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/hrnet/cascade_rcnn_hrnetv2_w32_fpn_20e_20190522-55bec4ee.pth)|
**Note:**
+- The `28e` schedule in HTC indicates decreasing the lr at 24 and 27 epochs, with a total of 28 epochs.
- HRNetV2 ImageNet pretrained models are in [HRNets for Image Classification](https://github.com/HRNet/HRNet-Image-Classification).
diff --git a/configs/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e.py b/configs/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e.py
new file mode 100644
index 0000000000000000000000000000000000000000..06e0c169ac56de0cead56c9570b41374250f8e7c
--- /dev/null
+++ b/configs/hrnet/cascade_mask_rcnn_hrnetv2p_w32_20e.py
@@ -0,0 +1,280 @@
+# model settings
+model = dict(
+ type='CascadeRCNN',
+ num_stages=3,
+ pretrained='open-mmlab://msra/hrnetv2_w32',
+ backbone=dict(
+ type='HRNet',
+ extra=dict(
+ stage1=dict(
+ num_modules=1,
+ num_branches=1,
+ block='BOTTLENECK',
+ num_blocks=(4, ),
+ num_channels=(64, )),
+ stage2=dict(
+ num_modules=1,
+ num_branches=2,
+ block='BASIC',
+ num_blocks=(4, 4),
+ num_channels=(32, 64)),
+ stage3=dict(
+ num_modules=4,
+ num_branches=3,
+ block='BASIC',
+ num_blocks=(4, 4, 4),
+ num_channels=(32, 64, 128)),
+ stage4=dict(
+ num_modules=3,
+ num_branches=4,
+ block='BASIC',
+ num_blocks=(4, 4, 4, 4),
+ num_channels=(32, 64, 128, 256)))),
+ neck=dict(
+ type='HRFPN',
+ in_channels=[32, 64, 128, 256],
+ out_channels=256),
+ rpn_head=dict(
+ type='RPNHead',
+ in_channels=256,
+ feat_channels=256,
+ anchor_scales=[8],
+ anchor_ratios=[0.5, 1.0, 2.0],
+ anchor_strides=[4, 8, 16, 32, 64],
+ target_means=[.0, .0, .0, .0],
+ target_stds=[1.0, 1.0, 1.0, 1.0],
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+ bbox_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ bbox_head=[
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=81,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(
+ type='SmoothL1Loss',
+ beta=1.0,
+ loss_weight=1.0)),
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=81,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.05, 0.05, 0.1, 0.1],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(
+ type='SmoothL1Loss',
+ beta=1.0,
+ loss_weight=1.0)),
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=81,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.033, 0.033, 0.067, 0.067],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(
+ type='SmoothL1Loss',
+ beta=1.0,
+ loss_weight=1.0))
+ ],
+ mask_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ mask_head=dict(
+ type='FCNMaskHead',
+ num_convs=4,
+ in_channels=256,
+ conv_out_channels=256,
+ num_classes=81,
+ loss_mask=dict(
+ type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)))
+# model training and testing settings
+train_cfg = dict(
+ rpn=dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False),
+ allowed_border=0,
+ pos_weight=-1,
+ debug=False),
+ rpn_proposal=dict(
+ nms_across_levels=False,
+ nms_pre=2000,
+ nms_post=2000,
+ max_num=2000,
+ nms_thr=0.7,
+ min_bbox_size=0),
+ rcnn=[
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.6,
+ neg_iou_thr=0.6,
+ min_pos_iou=0.6,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.7,
+ min_pos_iou=0.7,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False)
+ ],
+ stage_loss_weights=[1, 0.5, 0.25])
+test_cfg = dict(
+ rpn=dict(
+ nms_across_levels=False,
+ nms_pre=1000,
+ nms_post=1000,
+ max_num=1000,
+ nms_thr=0.7,
+ min_bbox_size=0),
+ rcnn=dict(
+ score_thr=0.05,
+ nms=dict(type='nms', iou_thr=0.5),
+ max_per_img=100,
+ mask_thr_binary=0.5),
+ keep_all_stages=False)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+data = dict(
+ imgs_per_gpu=2,
+ workers_per_gpu=2,
+ train=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_train2017.json',
+ img_prefix=data_root + 'train2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0.5,
+ with_mask=True,
+ with_crowd=True,
+ with_label=True),
+ val=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_val2017.json',
+ img_prefix=data_root + 'val2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=True,
+ with_crowd=True,
+ with_label=True),
+ test=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_val2017.json',
+ img_prefix=data_root + 'val2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=True,
+ with_label=False,
+ test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+ policy='step',
+ warmup='linear',
+ warmup_iters=500,
+ warmup_ratio=1.0 / 3,
+ step=[16, 19])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+ interval=50,
+ hooks=[
+ dict(type='TextLoggerHook'),
+ # dict(type='TensorboardLoggerHook')
+ ])
+# yapf:enable
+# runtime settings
+total_epochs = 20
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/cascade_mask_rcnn_hrnetv2p_w32_20e'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/hrnet/fcos_hrnetv2p_w32_gn_1x_4gpu.py b/configs/hrnet/fcos_hrnetv2p_w32_gn_1x_4gpu.py
new file mode 100644
index 0000000000000000000000000000000000000000..d7a68177ad9fc6cc2ce3d9303df390182dd26184
--- /dev/null
+++ b/configs/hrnet/fcos_hrnetv2p_w32_gn_1x_4gpu.py
@@ -0,0 +1,145 @@
+# model settings
+model = dict(
+ type='FCOS',
+ pretrained='open-mmlab://msra/hrnetv2_w32',
+ backbone=dict(
+ type='HRNet',
+ extra=dict(
+ stage1=dict(
+ num_modules=1,
+ num_branches=1,
+ block='BOTTLENECK',
+ num_blocks=(4,),
+ num_channels=(64,)),
+ stage2=dict(
+ num_modules=1,
+ num_branches=2,
+ block='BASIC',
+ num_blocks=(4, 4),
+ num_channels=(32, 64)),
+ stage3=dict(
+ num_modules=4,
+ num_branches=3,
+ block='BASIC',
+ num_blocks=(4, 4, 4),
+ num_channels=(32, 64, 128)),
+ stage4=dict(
+ num_modules=3,
+ num_branches=4,
+ block='BASIC',
+ num_blocks=(4, 4, 4, 4),
+ num_channels=(32, 64, 128, 256)))),
+ neck=dict(
+ type='HRFPN',
+ in_channels=[32, 64, 128, 256],
+ out_channels=256,
+ stride=2,
+ num_outs=5),
+ bbox_head=dict(
+ type='FCOSHead',
+ num_classes=81,
+ in_channels=256,
+ stacked_convs=4,
+ feat_channels=256,
+ strides=[8, 16, 32, 64, 128],
+ loss_cls=dict(
+ type='FocalLoss',
+ use_sigmoid=True,
+ gamma=2.0,
+ alpha=0.25,
+ loss_weight=1.0),
+ loss_bbox=dict(type='IoULoss', loss_weight=1.0),
+ loss_centerness=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)))
+# training and testing settings
+train_cfg = dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.4,
+ min_pos_iou=0,
+ ignore_iof_thr=-1),
+ allowed_border=-1,
+ pos_weight=-1,
+ debug=False)
+test_cfg = dict(
+ nms_pre=1000,
+ min_bbox_size=0,
+ score_thr=0.05,
+ nms=dict(type='nms', iou_thr=0.5),
+ max_per_img=100)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+ mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
+data = dict(
+ imgs_per_gpu=4,
+ workers_per_gpu=4,
+ train=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_train2017.json',
+ img_prefix=data_root + 'train2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0.5,
+ with_mask=False,
+ with_crowd=False,
+ with_label=True),
+ val=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_val2017.json',
+ img_prefix=data_root + 'val2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=False,
+ with_crowd=False,
+ with_label=True),
+ test=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_val2017.json',
+ img_prefix=data_root + 'val2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=False,
+ with_crowd=False,
+ with_label=False,
+ test_mode=True))
+# optimizer
+optimizer = dict(
+ type='SGD',
+ lr=0.01,
+ momentum=0.9,
+ weight_decay=0.0001,
+ paramwise_options=dict(bias_lr_mult=2., bias_decay_mult=0.))
+optimizer_config = dict(grad_clip=None)
+# learning policy
+lr_config = dict(
+ policy='step',
+ warmup='constant',
+ warmup_iters=500,
+ warmup_ratio=1.0 / 3,
+ step=[8, 11])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+ interval=50,
+ hooks=[
+ dict(type='TextLoggerHook'),
+ # dict(type='TensorboardLoggerHook')
+ ])
+# yapf:enable
+# runtime settings
+total_epochs = 12
+device_ids = range(4)
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/fcos_hrnetv2p_w32_gn_1x_4gpu'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/configs/hrnet/htc_hrnetv2p_w32_20e.py b/configs/hrnet/htc_hrnetv2p_w32_20e.py
new file mode 100644
index 0000000000000000000000000000000000000000..3de5b4fb81bbcd97b2c0fc386d6ac207c0ab7661
--- /dev/null
+++ b/configs/hrnet/htc_hrnetv2p_w32_20e.py
@@ -0,0 +1,300 @@
+# model settings
+model = dict(
+ type='HybridTaskCascade',
+ num_stages=3,
+ pretrained='open-mmlab://msra/hrnetv2_w32',
+ interleaved=True,
+ mask_info_flow=True,
+ backbone=dict(
+ type='HRNet',
+ extra=dict(
+ stage1=dict(
+ num_modules=1,
+ num_branches=1,
+ block='BOTTLENECK',
+ num_blocks=(4, ),
+ num_channels=(64, )),
+ stage2=dict(
+ num_modules=1,
+ num_branches=2,
+ block='BASIC',
+ num_blocks=(4, 4),
+ num_channels=(32, 64)),
+ stage3=dict(
+ num_modules=4,
+ num_branches=3,
+ block='BASIC',
+ num_blocks=(4, 4, 4),
+ num_channels=(32, 64, 128)),
+ stage4=dict(
+ num_modules=3,
+ num_branches=4,
+ block='BASIC',
+ num_blocks=(4, 4, 4, 4),
+ num_channels=(32, 64, 128, 256)))),
+ neck=dict(
+ type='HRFPN',
+ in_channels=[32, 64, 128, 256],
+ out_channels=256),
+ rpn_head=dict(
+ type='RPNHead',
+ in_channels=256,
+ feat_channels=256,
+ anchor_scales=[8],
+ anchor_ratios=[0.5, 1.0, 2.0],
+ anchor_strides=[4, 8, 16, 32, 64],
+ target_means=[.0, .0, .0, .0],
+ target_stds=[1.0, 1.0, 1.0, 1.0],
+ loss_cls=dict(
+ type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
+ loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
+ bbox_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ bbox_head=[
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=81,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.1, 0.1, 0.2, 0.2],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(
+ type='SmoothL1Loss',
+ beta=1.0,
+ loss_weight=1.0)),
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=81,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.05, 0.05, 0.1, 0.1],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(
+ type='SmoothL1Loss',
+ beta=1.0,
+ loss_weight=1.0)),
+ dict(
+ type='SharedFCBBoxHead',
+ num_fcs=2,
+ in_channels=256,
+ fc_out_channels=1024,
+ roi_feat_size=7,
+ num_classes=81,
+ target_means=[0., 0., 0., 0.],
+ target_stds=[0.033, 0.033, 0.067, 0.067],
+ reg_class_agnostic=True,
+ loss_cls=dict(
+ type='CrossEntropyLoss',
+ use_sigmoid=False,
+ loss_weight=1.0),
+ loss_bbox=dict(
+ type='SmoothL1Loss',
+ beta=1.0,
+ loss_weight=1.0))
+ ],
+ mask_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+ out_channels=256,
+ featmap_strides=[4, 8, 16, 32]),
+ mask_head=dict(
+ type='HTCMaskHead',
+ num_convs=4,
+ in_channels=256,
+ conv_out_channels=256,
+ num_classes=81,
+ loss_mask=dict(
+ type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
+ semantic_roi_extractor=dict(
+ type='SingleRoIExtractor',
+ roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
+ out_channels=256,
+ featmap_strides=[8]),
+ semantic_head=dict(
+ type='FusedSemanticHead',
+ num_ins=5,
+ fusion_level=1,
+ num_convs=4,
+ in_channels=256,
+ conv_out_channels=256,
+ num_classes=183,
+ ignore_label=255,
+ loss_weight=0.2))
+# model training and testing settings
+train_cfg = dict(
+ rpn=dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.3,
+ min_pos_iou=0.3,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=256,
+ pos_fraction=0.5,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=False),
+ allowed_border=0,
+ pos_weight=-1,
+ debug=False),
+ rpn_proposal=dict(
+ nms_across_levels=False,
+ nms_pre=2000,
+ nms_post=2000,
+ max_num=2000,
+ nms_thr=0.7,
+ min_bbox_size=0),
+ rcnn=[
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.5,
+ neg_iou_thr=0.5,
+ min_pos_iou=0.5,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.6,
+ neg_iou_thr=0.6,
+ min_pos_iou=0.6,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False),
+ dict(
+ assigner=dict(
+ type='MaxIoUAssigner',
+ pos_iou_thr=0.7,
+ neg_iou_thr=0.7,
+ min_pos_iou=0.7,
+ ignore_iof_thr=-1),
+ sampler=dict(
+ type='RandomSampler',
+ num=512,
+ pos_fraction=0.25,
+ neg_pos_ub=-1,
+ add_gt_as_proposals=True),
+ mask_size=28,
+ pos_weight=-1,
+ debug=False)
+ ],
+ stage_loss_weights=[1, 0.5, 0.25])
+test_cfg = dict(
+ rpn=dict(
+ nms_across_levels=False,
+ nms_pre=1000,
+ nms_post=1000,
+ max_num=1000,
+ nms_thr=0.7,
+ min_bbox_size=0),
+ rcnn=dict(
+ score_thr=0.001,
+ nms=dict(type='nms', iou_thr=0.5),
+ max_per_img=100,
+ mask_thr_binary=0.5),
+ keep_all_stages=False)
+# dataset settings
+dataset_type = 'CocoDataset'
+data_root = 'data/coco/'
+img_norm_cfg = dict(
+ mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
+data = dict(
+ imgs_per_gpu=2,
+ workers_per_gpu=2,
+ train=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_train2017.json',
+ img_prefix=data_root + 'train2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0.5,
+ seg_prefix=data_root + 'stuffthingmaps/train2017/',
+ seg_scale_factor=1 / 8,
+ with_mask=True,
+ with_crowd=True,
+ with_label=True,
+ with_semantic_seg=True),
+ val=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_val2017.json',
+ img_prefix=data_root + 'val2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=True,
+ with_crowd=True,
+ with_label=True),
+ test=dict(
+ type=dataset_type,
+ ann_file=data_root + 'annotations/instances_val2017.json',
+ img_prefix=data_root + 'val2017/',
+ img_scale=(1333, 800),
+ img_norm_cfg=img_norm_cfg,
+ size_divisor=32,
+ flip_ratio=0,
+ with_mask=True,
+ with_label=False,
+ test_mode=True))
+# optimizer
+optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001)
+optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
+# learning policy
+lr_config = dict(
+ policy='step',
+ warmup='linear',
+ warmup_iters=500,
+ warmup_ratio=1.0 / 3,
+ step=[16, 19])
+checkpoint_config = dict(interval=1)
+# yapf:disable
+log_config = dict(
+ interval=50,
+ hooks=[
+ dict(type='TextLoggerHook'),
+ # dict(type='TensorboardLoggerHook')
+ ])
+# yapf:enable
+# runtime settings
+total_epochs = 20
+dist_params = dict(backend='nccl')
+log_level = 'INFO'
+work_dir = './work_dirs/htc_hrnetv2p_w32_20e'
+load_from = None
+resume_from = None
+workflow = [('train', 1)]
diff --git a/mmdet/models/necks/hrfpn.py b/mmdet/models/necks/hrfpn.py
index 06a8fbf4285b4a9576ef65bc881974746a1071f1..33155f0573e43dfb35d0ed80996a7c014cb4a4c1 100644
--- a/mmdet/models/necks/hrfpn.py
+++ b/mmdet/models/necks/hrfpn.py
@@ -24,6 +24,7 @@ class HRFPN(nn.Module):
norm_cfg (dict): dictionary to construct and config norm layer.
with_cp (bool): Use checkpoint or not. Using checkpoint will save some
memory while slowing down the training speed.
+ stride (int): stride of 3x3 convolutional layers
"""
def __init__(self,
@@ -33,7 +34,8 @@ class HRFPN(nn.Module):
pooling_type='AVG',
conv_cfg=None,
norm_cfg=None,
- with_cp=False):
+ with_cp=False,
+ stride=1):
super(HRFPN, self).__init__()
assert isinstance(in_channels, list)
self.in_channels = in_channels
@@ -59,6 +61,7 @@ class HRFPN(nn.Module):
out_channels,
kernel_size=3,
padding=1,
+ stride=stride,
conv_cfg=self.conv_cfg,
activation=None))