/FasterRCNN4VidVRDT1

FasterRCNN 4 VidVRD Task1 Video Obj Detection

Primary LanguagePythonMIT LicenseMIT

Faster-RCNN Pytorch

Overview

This repo is the 1st task of VidVRD: Video Object Detection.

The 2nd stage trunk project: Video Relation Prediction

The Grand Challenge MM2019

Authorship

This project is based on faster-rcnn.pytorch

Modified some parts to be the 1st step of Video VRD project.

FasterRCNN_Tutorial

Benchmarking

Benchmarking

Prepare

source activate pytorch
pip install -r requirements.txt
# Compile the cuda dependencies
cd lib
bash make.sh    # mayb u need 2 modify 'CUDA_ARCH' 2 suit u gpu version

Train

VOC 2007

Download pretrained models:

vgg16

resnet101

bash prepare_voc2007.sh
bash gpu_train.sh pascal_voc resnet101

The model will be saved in /storage/

Vidor_10k

Download Grand Challenge dataset



Modify


Check u own proj structure with tree.txt 2 modify


Test


VOC 2007


Evaluate the detection performance of a pre-trained vgg16 model on pascal_voc test set


bash gpu_test.sh


Demo


VOC 2007


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


bash gpu_demo.sh


Webcam


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


python 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.