- Batch Normalization layers in backbones are replaced by Affine Channel layers.
- Batch Normalization layers in backbones are replaced by Affine Channel layers.
- Unless otherwise noted, all ResNet backbones adopt the [ResNet-B](https://arxiv.org/pdf/1812.01187) variant..
- Unless otherwise noted, all ResNet backbones adopt the [ResNet-B](https://arxiv.org/pdf/1812.01187) variant..
- For RCNN and RetinaNet models, only horizontal flipping data augmentation was used in the training phase and no augmentations were used in the testing phase.
- For RCNN and RetinaNet models, only horizontal flipping data augmentation was used in the training phase and no augmentations were used in the testing phase.
-**Inf time (fps)**: the inference time is measured with fps (image/s) on a single GPU (Tesla V100) with cuDNN 7.5 by running 'tools/eval.py' on all validation set, which including data loadding, network forward and post processing. The batch size is 1.
## Training Schedules
## Training Schedules
...
@@ -30,50 +32,50 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
...
@@ -30,50 +32,50 @@ The backbone models pretrained on ImageNet are available. All backbone models ar
### Faster & Mask R-CNN
### Faster & Mask R-CNN
| Backbone | Type | Image/gpu | Lr schd | Box AP | Mask AP | Download |
| Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download |
**NOTE**: MobileNet-SSD is trained in 2 GPU with totoal batch size as 64 and trained 120 epoches. VGG-SSD is trained in 4 GPU with total batch size as 32 and trained 240 epoches. SSD training data augmentations: randomly color distortion,
**NOTE**: MobileNet-SSD is trained in 2 GPU with totoal batch size as 64 and trained 120 epoches. VGG-SSD is trained in 4 GPU with total batch size as 32 and trained 240 epoches. SSD training data augmentations: randomly color distortion,
