EMCP's Faster R CNN Implementation

This repository represents my best attempts at recreating the work of this repo https://github.com/jwyang/faster-rcnn.pytorch

prerequisites

These are not hard requirements BUT it is what has been tested / confirmed

• python 3.10+
• Pytorch 1.13+
• CUDA 11.7 or higher

Data Preparation

• COCO: Please also follow the instructions in py-faster-rcnn to prepare the data.

Pretrained Model

• ResNet101: Dropbox

Download it into data/pretrained_model/

Compilation

Install all the python dependencies using pip:

pip3 install torch torchvision torchaudio
pip3 install -r requirements.txt

Train your model

Before training, set the right directory to save and load the trained models. Change the arguments "save_dir" and "load_dir" in training.py and test_net.py to adapt to your environment.

To train a faster R-CNN model with vgg16 on pascal_voc, simply run:

CUDA_VISIBLE_DEVICES=$GPU_ID python training.py \
                   --dataset pascal_voc --net vgg16 \
                   --bs $BATCH_SIZE --nw $WORKER_NUMBER \
                   --lr $LEARNING_RATE --lr_decay_step $DECAY_STEP \
                   --cuda

where 'bs' is the batch size with default 1. Alternatively, to train with resnet101 on pascal_voc, simple run:

 CUDA_VISIBLE_DEVICES=$GPU_ID python training.py \
                    --dataset pascal_voc --net res101 \
                    --bs $BATCH_SIZE --nw $WORKER_NUMBER \
                    --lr $LEARNING_RATE --lr_decay_step $DECAY_STEP \
                    --cuda

Above, BATCH_SIZE and WORKER_NUMBER can be set adaptively according to your GPU memory size. On Titan Xp with 12G memory, it can be up to 4.

If you have multiple (say 8) Titan Xp GPUs, then just use them all! Try:

python training.py --dataset pascal_voc --net vgg16 \
                       --bs 24 --nw 8 \
                       --lr $LEARNING_RATE --lr_decay_step $DECAY_STEP \
                       --cuda --mGPUs

Change dataset to "coco" or 'vg' if you want to train on COCO or Visual Genome.

Test

If you want to evaluate the detection performance of a pre-trained vgg16 model on pascal_voc test set, simply run

python scoring.py --dataset pascal_voc --net vgg16 \
                   --checksession $SESSION --checkepoch $EPOCH --checkpoint $CHECKPOINT \
                   --cuda

Specify the specific model session, epoch and checkpoint, e.g., SESSION=1, EPOCH=6, CHECKPOINT=416.

Demo

If you want to run detection on your own images with a pre-trained model, download the pretrained model listed in above tables or train your own models at first, then add images to folder $ROOT/images, and then run

python scoring-demo.py --net vgg16 \
               --checksession $SESSION --checkepoch $EPOCH --checkpoint $CHECKPOINT \
               --cuda --load_dir path/to/model/directoy

Then you will find the detection results in folder $ROOT/images.

Note the default demo.py merely support pascal_voc categories. You need to change the line to adapt your own model.

Below are some detection results:

Webcam Demo

You can use a webcam in a real-time demo by running

python scoring-demo.py --net vgg16 \
               --checksession $SESSION --checkepoch $EPOCH --checkpoint $CHECKPOINT \
               --cuda --load_dir path/to/model/directoy \
               --webcam $WEBCAM_ID

The demo is stopped by clicking the image window and then pressing the 'q' key.

Citation

@inproceedings{jjfaster2rcnn,
    Author = {Jianwei Yang and Jiasen Lu and Dhruv Batra and Devi Parikh},
    Title = {A Faster Pytorch Implementation of Faster R-CNN},
    Journal = {https://github.com/jwyang/faster-rcnn.pytorch},
    Year = {2017}
}

@inproceedings{renNIPS15fasterrcnn,
    Author = {Shaoqing Ren and Kaiming He and Ross Girshick and Jian Sun},
    Title = {Faster {R-CNN}: Towards Real-Time Object Detection
             with Region Proposal Networks},
    Booktitle = {Advances in Neural Information Processing Systems ({NIPS})},
    Year = {2015}
}