Skip to content

FasterRCNN-FPN (ResNet50) to detect and track bees. Trained on manually curated images.

Notifications You must be signed in to change notification settings

jdubpark/beetect

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Beetect

Detecting and tracking honeybees

Watch the sample video ran on the trained model.

Recommended paths:

NVIDIA docker

follow: https://github.com/NVIDIA/nvidia-docker

Simple PyTorch GPU installation through NGC and Docker

follow: https://ngc.nvidia.com/catalog/containers/nvidia:pytorch

Steps for installing Horovod

https://github.com/horovod/horovod

Install Open MPI

follow: https://www.open-mpi.org/software/ompi/v4.0/

For OS X: https://stackoverflow.com/questions/42703861/how-to-use-mpi-on-mac-os-x brew install openmpi CFLAGS=-mmacosx-version-min=10.9 pip install horovod

Check that g++-4.9 or above is installed for PyTorch

For Linux: conda install -c anaconda gxx_linux-64

Install Horovod pip package

MacOS: CFLAGS=-mmacosx-version-min=10.9 pip install horovod

GPU: follow https://github.com/horovod/horovod/blob/master/docs/gpus.rst

About

FasterRCNN-FPN (ResNet50) to detect and track bees. Trained on manually curated images.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages