Skip to content

Pytorch Faster RCNN

Faster RCNN Fine-Tune Implementation in Pytorch.

How to use ?

  1. git clone the repo 
    git clone https://github.com/oke-aditya/pytorch_fasterrcnn.git
  2. Install PyTorch and torchvision for your system.

Simply edit the config file to set your hyper parameters.

  1. Keep the training and validation csv file as follows

NOTE

Do not use target as 0 class. It is reserved as background.

image_id xtl ytl xbr ybr      target
1        xmin ymin xmax ymax   1
1        xmin ymin xmax ymax   2
2        xmin ymin xmax ymax   3

  1. Simply edit the config file to set your hyper parameters

  2. Run the train.py file

Features: -

  • It works for multiple class object detection.

Backbones Supported: -

  • Note that backbones are pretrained on imagenet.

  • Following backbones are supported

  • vgg11, vgg13, vgg16, vgg19

  • resnet18, resnet34, resnet50, resnet101, resnet152
  • renext101
  • mobilenet_v2

Sample Outputs

Helmet Detector

Helmet Detection

Mask Detector

Mask Detection

If you like the implemenation or have taken an inspiration do give a star :-)