Hint from TensorLayer
- This implementation is from
https://github.com/deepsense-ai/roi-pooling, date: 31 Aug 2017.
- To install this, you have to clone TensorLayer from Github instead of pip install.
- Remember to modify the
CUDA_LIBin Makefile before running
python setup.py installin this folder.
- Make sure
RoI pooling in TensorFlow
This repo contains the implementation of Region of Interest pooling as a custom TensorFlow operation. The CUDA code responsible for the computations was largely taken from the original Caffe implementation by Ross Girshick.
To compile and use
roi_pooling layer you need to have:
Only official TensorFlow releases are currently supported. If you're using a custom built TensorFlow compiled with a different GCC version (e.g. 5.X) you may need to modify the makefile to enable the new ABI version.
Since it uses compilation
$ git clone email@example.com:deepsense-io/roi-pooling.git $ cd roi-pooling $ python setup.py install
Right now we provide only GPU implementation (no CPU at this time).
After successful installation you can use the operation like this:
from roi_pooling.roi_pooling_ops import roi_pooling # here obtain feature map and regions of interest rpooling = roi_pooling(feature_map, rois, 7, 7) # continue the model
Working example in Jupyter Notebook: examples/roi_pooling_minimal_example.ipynb