Created by Ross Girshick at Microsoft Research, Redmond.
1. Requirements for Caffe and pycaffe
### Introduction
*Fast R-CNN* 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 fine-tuning run.
The multi-task loss simplifies and speeds up training.
Unlike SPPnet, all network layers can be learned 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 fine-tuned.
Compared to "slow" R-CNN, Fast R-CNN is 9x faster at training VGG16 for detection, 213x faster for detection, 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 was initially described in an [arXiv tech report](http://arxiv.org/abs/todo).
### Citing Fast R-CNN
If you find R-CNN useful in your research, please consider citing:
@article{girshick15fastrcnn,
Author = {Ross Girshick},
Title = {Fast R-CNN},
Journal = {arXiv preprint arXiv:todo},
Year = {2015}
}
### License
Fast R-CNN is released under the MIT License (refer to the LICENSE file for details).
### Installation requirements
1. Requirements for Caffe and pycaffe (see: [Caffe installation instructions](http://caffe.berkeleyvision.org/installation.html))
The demo performs detection using a VGG16 network trained for detection on PASCAL VOC 2012. The object proposals are pre-computed in order to reduce installation requirements.
### Beyond the demo: installation for training and testing models
1. Download the training, validation, test data and VOCdevkit
This will populate the `$FRCN_ROOT/data` folder with `selective_selective_data`.
### Download pre-trained ImageNet models
Pre-trained ImageNet models can be downloaded for the three networks described in the paper: CaffeNet (model **S**), VGG_CNN_M_1024 (model **M**), and VGG16 (model **L**).
```Shell
cd $FRCN_ROOT
./data/scripts/fetch_imagenet_models.sh
```
These models are all available in the [Caffe Model Zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo), but are provided here for your convenience.
Test output is written underneath `$FRCNN/output`.
### Usage
**Train** a Fast R-CNN detector. For example, train a VGG16 network on VOC 2007 trainval:
Scripts to reproduce the experiments in the paper (up to stochastic variation) are provided in `$FRCN_ROOT/experiments/scripts`. Log files for experiments are located in `experiments/logs`.