Update README.md

README.md

@@ -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](http://caffe.berkeleyvision.org/installation.html))
-2. Additional Python packages: cython, python-opencv, easydict
+1. Requirements for `Caffe` and `pycaffe` (see: [Caffe installation instructions](http://caffe.berkeleyvision.org/installation.html))
+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

data/README.md

-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:
 
 ```
-./tools/scripts/fetch_selective_search_data.sh
+./data/scripts/fetch_selective_search_data.sh
 ```
 
 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:
 
 ```
-./tools/scripts/fetch_imagenet_models.sh
+./data/scripts/fetch_imagenet_models.sh
 ```
 
 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:
 
 ```
-./tools/scripts/fetch_fast_rcnn_models.sh
+./data/scripts/fetch_fast_rcnn_models.sh
 ```
 
 This script will populate `data/fast_rcnn_models`.