|
Fast R-CNN |
Fast R-CNN (Region-based Convolutional Network) is a clean and fast framework for object detection. Last published: May 14, 2015.
Fast R-CNN (Region-based Convolutional Network) is a clean and fast framework for object detection. Compared to traditional R-CNN, and its accelerated version SPPnet, Fast R-CNN trains networks using a multi-task loss in a single training stage. The multi-task loss simplifies learning and improves detection accuracy. Unlike SPPnet, all network layers can be updated during fine-tuning. We show that this difference has practical ramifications for very deep networks, such as VGG16, where mAP suffers when only the fully-connected layers are updated. Compared to “slow” R-CNN, Fast R-CNN is 9x faster at training VGG16 for detection, 213x faster at test-time, and achieves a significantly higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ and is available under the open-source MIT License.
Files
|
Status: LiveThis download is still available on microsoft.com. The downloads below will come directly from the Microsoft Download Center. |
| Files |
|---|
fast-rcnn.zip
|
System Requirements
Operating Systems: Windows 10, Windows 7, Windows 8
- Windows 7, Windows 8, or Windows 10
Installation Instructions
- Click Download and follow the instructions.