Object detection in torch
Implementation of some object detection frameworks in torch.
Note on new code
You should probably check the refactoring branch of this repository, which simplifies the code structure, and also contains an implementation of Fast-RCNN and threaded RCNN (making it much faster than standard RCNN). It will be merged to master soon.
It requires the following packages
To install them all, do
## xml luarocks install xml ## matio # OSX brew install libmatio # Ubuntu sudo apt-get install libmatio2 luarocks install matio
hdf5, follow the instructions in here
Running this code
First, clone this repo
git clone https://github.com/fmassa/object-detection.torch.git
The zeiler pretrained model is available at https://drive.google.com/open?id=0B-TTdm1WNtybdzdMUHhLc05PSE0&authuser=0.
It is supposed to be at
If you want to use your own model in SPP framework, make sure that it follows the pattern
model = nn.Sequential() model:add(features) model:add(pooling_layer) model:add(classifier)
features can be a
nn.Sequential of several convolutions and
pooling_layer is the last pooling with reshaping of the data to feed it to the classifer. See
models/zeiler.lua for an example.
To finetune the network for detection, simply run
To get an overview of the different parameters, do
th main.lua -h
The default is to consider that the dataset is present in
The default location of bounding boxes
.mat files (in RCNN format) is supposed to be in