Faster R-CNN

open-mmlab / mmdetection

Last updated on Feb 23, 2021
Faster R-CNN (R-101-FPN, 1x, caffe)
Memory (M) 5700.0
Backbone Layers 101
File Size 232.24 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, FPN, RoIPool, ResNet
lr sched 1x
Memory (M) 5700.0
Backbone Layers 101
SHOW MORE
SHOW LESS
Faster R-CNN (R-101-FPN, 1x, pytorch)
Memory (M) 6000.0
inference time (s/im) 0.0641
File Size 232.23 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, FPN, RoIPool, ResNet
lr sched 1x
Memory (M) 6000.0
Backbone Layers 101
inference time (s/im) 0.0641
SHOW MORE
SHOW LESS
Faster R-CNN (R-101-FPN, 2x, pytorch)
lr sched 2x
Backbone Layers 101
File Size 232.24 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, FPN, RoIPool, ResNet
lr sched 2x
Backbone Layers 101
SHOW MORE
SHOW LESS
Faster R-CNN (R-50-DC5, 1x, caffe)
lr sched 1x
Backbone Layers 50
File Size 632.11 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, RoIPool, ResNet
lr sched 1x
Backbone Layers 50
SHOW MORE
SHOW LESS
Faster R-CNN (R-50-FPN)
Parameters
Backbone Layers 50
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, FPN, RoIPool, ResNet
Backbone Layers 50
train time (s/iter) -
SHOW MORE
SHOW LESS
Faster R-CNN (R-50-FPN, 1x, caffe)
Memory (M) 3800.0
Backbone Layers 50
File Size 159.54 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, FPN, RoIPool, ResNet
lr sched 1x
Memory (M) 3800.0
Backbone Layers 50
SHOW MORE
SHOW LESS
Faster R-CNN (R-50-FPN, 1x, pytorch)
Memory (M) 4000.0
inference time (s/im) 0.04673
File Size 159.54 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, FPN, RoIPool, ResNet
lr sched 1x
Memory (M) 4000.0
Backbone Layers 50
inference time (s/im) 0.04673
SHOW MORE
SHOW LESS
Faster R-CNN (R-50-FPN, 2x, pytorch)
lr sched 2x
Backbone Layers 50
File Size 159.54 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, Convolution, FPN, RoIPool, ResNet
lr sched 2x
Backbone Layers 50
SHOW MORE
SHOW LESS
Faster R-CNN (X-101-32x4d-FPN, 1x, pytorch)
Memory (M) 7200.0
inference time (s/im) 0.07246
File Size 230.94 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, FPN, RoIPool
lr sched 1x
Memory (M) 7200.0
Backbone Layers 101
inference time (s/im) 0.07246
SHOW MORE
SHOW LESS
Faster R-CNN (X-101-32x4d-FPN, 2x, pytorch)
lr sched 2x
Backbone Layers 101
File Size 230.94 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, FPN, RoIPool
lr sched 2x
Backbone Layers 101
SHOW MORE
SHOW LESS
Faster R-CNN (X-101-64x4d-FPN, 1x, pytorch)
Memory (M) 10300.0
inference time (s/im) 0.10638
File Size 381.02 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, FPN, RoIPool
lr sched 1x
Memory (M) 10300.0
Backbone Layers 101
inference time (s/im) 0.10638
SHOW MORE
SHOW LESS
Faster R-CNN (X-101-64x4d-FPN, 2x, pytorch)
lr sched 2x
Backbone Layers 101
File Size 381.02 MB
Training Data MS COCO
Training Resources 8x NVIDIA V100 GPUs
Training Time
Architecture Softmax, RPN, ResNeXt, Convolution, FPN, RoIPool
lr sched 2x
Backbone Layers 101
SHOW MORE
SHOW LESS
README.md

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Introduction

[ALGORITHM]

@inproceedings{ren2015faster,
  title={Faster r-cnn: Towards real-time object detection with region proposal networks},
  author={Ren, Shaoqing and He, Kaiming and Girshick, Ross and Sun, Jian},
  booktitle={Advances in neural information processing systems},
  year={2015}
}

Results and models

Backbone Style Lr schd Mem (GB) Inf time (fps) AR1000 Config Download
R-50-FPN caffe 1x 3.5 22.6 58.7 config model | log
R-50-FPN pytorch 1x 3.8 22.3 58.2 config model | log
R-50-FPN pytorch 2x - - 58.6 config model | log
R-101-FPN caffe 1x 5.4 17.3 60.0 config model | log
R-101-FPN pytorch 1x 5.8 16.5 59.7 config model | log
R-101-FPN pytorch 2x - - 60.2 config model | log
X-101-32x4d-FPN pytorch 1x 7.0 13.0 60.6 config model | log
X-101-32x4d-FPN pytorch 2x - - 61.1 config model | log
X-101-64x4d-FPN pytorch 1x 10.1 9.1 61.0 config model | log
X-101-64x4d-FPN pytorch 2x - - 61.5 config model | log

Results

Object Detection on COCO minival

Object Detection on COCO minival
MODEL BOX AP
Faster R-CNN (X-101-64x4d-FPN, 1x, pytorch) 42.1
Faster R-CNN (X-101-64x4d-FPN, 2x, pytorch) 41.6
Faster R-CNN (X-101-32x4d-FPN, 1x, pytorch) 41.2
Faster R-CNN (X-101-32x4d-FPN, 2x, pytorch) 41.2
Faster R-CNN (R-50-FPN) 40.4
Faster R-CNN (R-101-FPN, 1x, caffe) 39.8
Faster R-CNN (R-101-FPN, 2x, pytorch) 39.8
Faster R-CNN (R-101-FPN, 1x, pytorch) 39.4
Faster R-CNN (R-50-FPN, 2x, pytorch) 38.4
Faster R-CNN (R-50-FPN, 1x, caffe) 37.8
Faster R-CNN (R-50-FPN, 1x, pytorch) 37.4
Faster R-CNN (R-50-DC5, 1x, caffe) 37.2
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy