update readme

README.md

@@ -58,14 +58,14 @@ Results and models are available in the [Model zoo](MODEL_ZOO.md).
 
 |                    | ResNet   | ResNeXt  | SENet    | VGG      |
 |--------------------|:--------:|:--------:|:--------:|:--------:|
-| RPN                | ✓        | ☐        | ☐        | ✗        |
-| Fast R-CNN         | ✓        | ☐        | ☐        | ✗        |
-| Faster R-CNN       | ✓        | ☐        | ☐        | ✗        |
-| Mask R-CNN         | ✓        | ☐        | ☐        | ✗        |
-| Cascade R-CNN      | ✓        | ☐        | ☐        | ✗        |
-| Cascade Mask R-CNN | ✓        | ☐        | ☐        | ✗        |
+| RPN                | ✓        | ✓        | ☐        | ✗        |
+| Fast R-CNN         | ✓        | ✓        | ☐        | ✗        |
+| Faster R-CNN       | ✓        | ✓        | ☐        | ✗        |
+| Mask R-CNN         | ✓        | ✓        | ☐        | ✗        |
+| Cascade R-CNN      | ✓        | ✓        | ☐        | ✗        |
+| Cascade Mask R-CNN | ✓        | ✓        | ☐        | ✗        |
 | SSD                | ✗        | ✗        | ✗        | ☐        |
-| RetinaNet          | ✓        | ☐        | ☐        | ✗        |
+| RetinaNet          | ✓        | ✓        | ☐        | ✗        |
 
 ## Installation
 

mmdet/models/backbones/resnet.py

@@ -86,7 +86,11 @@ class Bottleneck(nn.Module):
             self.conv1_stride = stride
             self.conv2_stride = 1
         self.conv1 = nn.Conv2d(
-            inplanes, planes, kernel_size=1, stride=self.conv1_stride, bias=False)
+            inplanes,
+            planes,
+            kernel_size=1,
+            stride=self.conv1_stride,
+            bias=False)
         self.conv2 = nn.Conv2d(
             planes,
             planes,

mmdet/models/backbones/resnext.py

 import math
 
 import torch.nn as nn
-import torch.utils.checkpoint as cp
 
 from .resnet import ResNet
 from .resnet import Bottleneck as _Bottleneck