[Refactor]: refactor configs of FP16 models (#6592)

* refactor configs of fp16 * update * update * update
open-mmlab · Nov 25, 2021 · 6c5be93 · 6c5be93
1 parent 09f1794
commit 6c5be93
Show file tree

Hide file tree

Showing 18 changed files with 184 additions and 199 deletions.
diff --git a/configs/dcn/README.md b/configs/dcn/README.md
@@ -43,6 +43,8 @@
 | R-50-FPN         | Cascade Mask | pytorch | dconv(c3-c5)  | -      | 1x      | 6.0  | 10.0  | 44.4 | 38.6 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/dcn/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco_20200202-42e767a2.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco_20200202_010309.log.json) |
 | R-101-FPN        | Cascade Mask | pytorch | dconv(c3-c5)  | -      | 1x      | 8.0  | 8.6  | 45.8 | 39.7 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/dcn/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco_20200204-df0c5f10.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco_20200204_134006.log.json) |
 | X-101-32x4d-FPN        | Cascade Mask | pytorch | dconv(c3-c5)  | -      | 1x      | 9.2 |   | 47.3 | 41.1 | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/dcn/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco-e75f90c8.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco-20200606_183737.log.json) |
+| R-50-FPN (FP16)      | Mask         | pytorch | dconv(c3-c5) | -      | 1x      | 3.0      |                | 41.9   | 37.5    |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/fp16/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/fp16/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco_20210520_180247-c06429d2.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/fp16/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco_20210520_180247.log.json)  |
+| R-50-FPN (FP16)      | Mask         | pytorch | mdconv(c3-c5)| -      | 1x      | 3.1      |                | 42.0   | 37.6    |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/fp16/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/fp16/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco_20210520_180434-cf8fefa5.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/fp16/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco_20210520_180434.log.json)  |
 
 **Notes:**
 

diff --git a/..._rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco.py → ..._rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco.py b/..._rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco.py → ..._rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco.py
diff --git a/...rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco.py → ...rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco.py b/...rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco.py → ...rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco.py
diff --git a/configs/dcn/metafile.yml b/configs/dcn/metafile.yml
@@ -10,7 +10,7 @@ Collections:
         - Deformable Convolution
     Paper:
       URL: https://arxiv.org/abs/1811.11168
-      Title: 'Deformable ConvNets v2: More Deformable, Better Results'
+      Title: "Deformable ConvNets v2: More Deformable, Better Results"
     README: configs/dcn/README.md
     Code:
       URL: https://github.com/open-mmlab/mmdetection/blob/v2.0.0/mmdet/ops/dcn/deform_conv.py#L15
@@ -178,7 +178,7 @@ Models:
       - Task: Instance Segmentation
         Dataset: COCO
         Metrics:
-          mask AP:  37.4
+          mask AP: 37.4
     Weights: https://download.openmmlab.com/mmdetection/v2.0/dcn/mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco_20200203-4d9ad43b.pth
 
   - Name: mask_rcnn_r50_fpn_mdconv_c3-c5_1x_coco
@@ -202,9 +202,51 @@ Models:
       - Task: Instance Segmentation
         Dataset: COCO
         Metrics:
-          mask AP:  37.1
+          mask AP: 37.1
     Weights: https://download.openmmlab.com/mmdetection/v2.0/dcn/mask_rcnn_r50_fpn_mdconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_mdconv_c3-c5_1x_coco_20200203-ad97591f.pth
 
+  - Name: mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco
+    In Collection: Deformable Convolutional Networks
+    Config: configs/dcn/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco.py
+    Metadata:
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+        - Mixed Precision Training
+      Training Memory (GB): 3.0
+      Epochs: 12
+    Results:
+      - Task: Object Detection
+        Dataset: COCO
+        Metrics:
+          box AP: 41.9
+      - Task: Instance Segmentation
+        Dataset: COCO
+        Metrics:
+          mask AP: 37.5
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/fp16/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco_20210520_180247-c06429d2.pth
+
+  - Name: mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco
+    In Collection: Deformable Convolutional Networks
+    Config: configs/dcn/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco.py
+    Metadata:
+      Training Memory (GB): 3.1
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+        - Mixed Precision Training
+      Epochs: 12
+    Results:
+      - Task: Object Detection
+        Dataset: COCO
+        Metrics:
+          box AP: 42.0
+      - Task: Instance Segmentation
+        Dataset: COCO
+        Metrics:
+          mask AP: 37.6
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/fp16/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco/mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco_20210520_180434-cf8fefa5.pth
+
   - Name: mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco
     In Collection: Deformable Convolutional Networks
     Config: configs/dcn/mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco.py
@@ -226,7 +268,7 @@ Models:
       - Task: Instance Segmentation
         Dataset: COCO
         Metrics:
-          mask AP:  38.9
+          mask AP: 38.9
     Weights: https://download.openmmlab.com/mmdetection/v2.0/dcn/mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco/mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco_20200216-a71f5bce.pth
 
   - Name: cascade_rcnn_r50_fpn_dconv_c3-c5_1x_coco
@@ -290,7 +332,7 @@ Models:
       - Task: Instance Segmentation
         Dataset: COCO
         Metrics:
-          mask AP:  38.6
+          mask AP: 38.6
     Weights: https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_r50_fpn_dconv_c3-c5_1x_coco_20200202-42e767a2.pth
 
   - Name: cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco
@@ -314,7 +356,7 @@ Models:
       - Task: Instance Segmentation
         Dataset: COCO
         Metrics:
-          mask AP:  39.7
+          mask AP: 39.7
     Weights: https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_r101_fpn_dconv_c3-c5_1x_coco_20200204-df0c5f10.pth
 
   - Name: cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco
@@ -331,5 +373,5 @@ Models:
       - Task: Instance Segmentation
         Dataset: COCO
         Metrics:
-          mask AP:  41.1
+          mask AP: 41.1
     Weights: https://download.openmmlab.com/mmdetection/v2.0/dcn/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco/cascade_mask_rcnn_x101_32x4d_fpn_dconv_c3-c5_1x_coco-e75f90c8.pth
diff --git a/configs/faster_rcnn/README.md b/configs/faster_rcnn/README.md
@@ -22,6 +22,7 @@
 |    R-50-DC5     |  caffe  |   1x    | -        | -              | 37.2   | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/faster_rcnn/faster_rcnn_r50_caffe_dc5_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_1x_coco/faster_rcnn_r50_caffe_dc5_1x_coco_20201030_151909-531f0f43.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_dc5_1x_coco/faster_rcnn_r50_caffe_dc5_1x_coco_20201030_151909.log.json) |
 |    R-50-FPN     |  caffe  |   1x    | 3.8      |                | 37.8   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_caffe_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_1x_coco/faster_rcnn_r50_caffe_fpn_1x_coco_bbox_mAP-0.378_20200504_180032-c5925ee5.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_caffe_fpn_1x_coco/faster_rcnn_r50_caffe_fpn_1x_coco_20200504_180032.log.json) |
 |    R-50-FPN     | pytorch |   1x    | 4.0      | 21.4           | 37.4   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130_204655.log.json) |
+| R-50-FPN (FP16)     | pytorch | 1x      | 3.4      | 28.8           | 37.5   |[config](https://github.com/open-mmlab/mmdetection/tree/master/configs/fp16/faster_rcnn_r50_fpn_fp16_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/fp16/faster_rcnn_r50_fpn_fp16_1x_coco/faster_rcnn_r50_fpn_fp16_1x_coco_20200204-d4dc1471.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/fp16/faster_rcnn_r50_fpn_fp16_1x_coco/faster_rcnn_r50_fpn_fp16_1x_coco_20200204_143530.log.json) |
 |    R-50-FPN     | pytorch |   2x    | -        | -              | 38.4   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_2x_coco/faster_rcnn_r50_fpn_2x_coco_bbox_mAP-0.384_20200504_210434-a5d8aa15.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_2x_coco/faster_rcnn_r50_fpn_2x_coco_20200504_210434.log.json) |
 |    R-101-FPN    |  caffe  |   1x    | 5.7      |                | 39.8   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r101_caffe_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_caffe_fpn_1x_coco/faster_rcnn_r101_caffe_fpn_1x_coco_bbox_mAP-0.398_20200504_180057-b269e9dd.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_caffe_fpn_1x_coco/faster_rcnn_r101_caffe_fpn_1x_coco_20200504_180057.log.json) |
 |    R-101-FPN    | pytorch |   1x    | 6.0      | 15.6           | 39.4   | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_1x_coco/faster_rcnn_r101_fpn_1x_coco_20200130-f513f705.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r101_fpn_1x_coco/faster_rcnn_r101_fpn_1x_coco_20200130_204655.log.json) |

diff --git a/configs/faster_rcnn/faster_rcnn_r50_fpn_fp16_1x_coco.py b/configs/faster_rcnn/faster_rcnn_r50_fpn_fp16_1x_coco.py
@@ -0,0 +1,3 @@
+_base_ = './faster_rcnn_r50_fpn_1x_coco.py'
+# fp16 settings
+fp16 = dict(loss_scale=512.)
diff --git a/configs/faster_rcnn/metafile.yml b/configs/faster_rcnn/metafile.yml
@@ -13,7 +13,7 @@ Collections:
         - RoIPool
     Paper:
       URL: https://arxiv.org/abs/1506.01497
-      Title: 'Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks'
+      Title: "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks"
     README: configs/faster_rcnn/README.md
     Code:
       URL: https://github.com/open-mmlab/mmdetection/blob/v2.0.0/mmdet/models/detectors/faster_rcnn.py#L6
@@ -65,18 +65,42 @@ Models:
           box AP: 37.4
     Weights: https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth
 
+  - Name: faster_rcnn_r50_fpn_fp16_1x_coco
+    In Collection: Faster R-CNN
+    Config: configs/faster_rcnn/faster_rcnn_r50_fpn_fp16_1x_coco.py
+    Metadata:
+      Training Memory (GB): 3.4
+      Training Techniques:
+        - SGD with Momentum
+        - Weight Decay
+        - Mixed Precision Training
+      inference time (ms/im):
+        - value: 34.72
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP16
+          resolution: (800, 1333)
+      Epochs: 12
+    Results:
+      - Task: Object Detection
+        Dataset: COCO
+        Metrics:
+          box AP: 37.5
+    Weights: https://download.openmmlab.com/mmdetection/v2.0/fp16/faster_rcnn_r50_fpn_fp16_1x_coco/faster_rcnn_r50_fpn_fp16_1x_coco_20200204-d4dc1471.pth
+
   - Name: faster_rcnn_r50_fpn_2x_coco
     In Collection: Faster R-CNN
     Config: configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.py
     Metadata:
       Training Memory (GB): 4.0
       inference time (ms/im):
-         - value: 46.73
-           hardware: V100
-           backend: PyTorch
-           batch size: 1
-           mode: FP32
-           resolution: (800, 1333)
+        - value: 46.73
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
       Epochs: 24
     Results:
       - Task: Object Detection
@@ -104,12 +128,12 @@ Models:
     Metadata:
       Training Memory (GB): 6.0
       inference time (ms/im):
-         - value: 64.1
-           hardware: V100
-           backend: PyTorch
-           batch size: 1
-           mode: FP32
-           resolution: (800, 1333)
+        - value: 64.1
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
       Epochs: 12
     Results:
       - Task: Object Detection
@@ -124,12 +148,12 @@ Models:
     Metadata:
       Training Memory (GB): 6.0
       inference time (ms/im):
-         - value: 64.1
-           hardware: V100
-           backend: PyTorch
-           batch size: 1
-           mode: FP32
-           resolution: (800, 1333)
+        - value: 64.1
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
       Epochs: 24
     Results:
       - Task: Object Detection
@@ -144,12 +168,12 @@ Models:
     Metadata:
       Training Memory (GB): 7.2
       inference time (ms/im):
-         - value: 72.46
-           hardware: V100
-           backend: PyTorch
-           batch size: 1
-           mode: FP32
-           resolution: (800, 1333)
+        - value: 72.46
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
       Epochs: 12
     Results:
       - Task: Object Detection
@@ -164,12 +188,12 @@ Models:
     Metadata:
       Training Memory (GB): 7.2
       inference time (ms/im):
-         - value: 72.46
-           hardware: V100
-           backend: PyTorch
-           batch size: 1
-           mode: FP32
-           resolution: (800, 1333)
+        - value: 72.46
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
       Epochs: 24
     Results:
       - Task: Object Detection
@@ -184,12 +208,12 @@ Models:
     Metadata:
       Training Memory (GB): 10.3
       inference time (ms/im):
-         - value: 106.38
-           hardware: V100
-           backend: PyTorch
-           batch size: 1
-           mode: FP32
-           resolution: (800, 1333)
+        - value: 106.38
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
       Epochs: 12
     Results:
       - Task: Object Detection
@@ -204,12 +228,12 @@ Models:
     Metadata:
       Training Memory (GB): 10.3
       inference time (ms/im):
-         - value: 106.38
-           hardware: V100
-           backend: PyTorch
-           batch size: 1
-           mode: FP32
-           resolution: (800, 1333)
+        - value: 106.38
+          hardware: V100
+          backend: PyTorch
+          batch size: 1
+          mode: FP32
+          resolution: (800, 1333)
       Epochs: 24
     Results:
       - Task: Object Detection

diff --git a/configs/fp16/README.md b/configs/fp16/README.md
diff --git a/configs/fp16/faster_rcnn_r50_fpn_fp16_1x_coco.py b/configs/fp16/faster_rcnn_r50_fpn_fp16_1x_coco.py
diff --git a/configs/fp16/mask_rcnn_r50_fpn_fp16_1x_coco.py b/configs/fp16/mask_rcnn_r50_fpn_fp16_1x_coco.py