Commit a25ae1d7 authored by Ross Girshick's avatar Ross Girshick
Browse files


parent e240ec2c
......@@ -27,12 +27,17 @@ If you find R-CNN useful in your research, please consider citing:
Year = {2015}
### Installation requirements
### Requirements: software
1. Requirements for Caffe and pycaffe (see: [Caffe installation instructions](
2. Additional Python packages: cython, python-opencv, easydict
1. Requirements for `Caffe` and `pycaffe` (see: [Caffe installation instructions](
2. Python packages you might not have: `cython`, `python-opencv`, `easydict`
3. [optional] MATLAB (required for PASCAL VOC evaluation only)
### Requirements: hardware
1. For training smaller networks (CaffeNet, VGG_CNN_M_1024) a good GPU (e.g., Titan, K20, K40, ...) with at least 3G of memory suffices
2. For training with VGG16, you'll need a K40 (~11G of memory)
### Installation (sufficient for the demo)
1. Clone the Fast R-CNN repository
This directory holds:
- Precomputed object proposals
- Caffe models pretrained on ImageNet
This directory holds (*after you download them*):
- Pre-computed object proposals
- Caffe models pre-trained on ImageNet
- Fast R-CNN models
- Symlinks to datasets
To download precomputed selective search proposals, run:
To download precomputed Selective Search proposals for PASCAL VOC 2007 and 2012, run:
This script will populate `data/selective_search_data`.
To download Caffe models pretrained on ImageNet, run:
To download Caffe models (CaffeNet, VGG_CNN_M_1024, VGG16) pre-trained on ImageNet, run:
This script will populate `data/imagenet_models`.
To download Fast R-CNN models, run:
To download Fast R-CNN models trained on VOC 2007, run:
This script will populate `data/fast_rcnn_models`.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment