Skip to content

Latest commit

 

History

History
153 lines (100 loc) · 5.64 KB

README.MD

File metadata and controls

153 lines (100 loc) · 5.64 KB

A Pythonic, Extensible and Minimal Implemention of Faster RCNN Without Harming Performance

Introduction

This project is a Simplified Faster R-CNN implementation mostly based on chainercv and Other projects . It aims to:

  • Simplify the code (Simple is better than complex)
  • Make the code more straight forward (Flat is better than nested)
  • Match the performance reported in origin paper (Speed Counts and mAP Matters)

Performance

  • mAP

VGG16 train on trainval and test on test, Note, the training show great randomness, you may need to train more epoch to reach the highest mAP. However, it should be easy to reach the lowerboud. It's also reported that train it with more epochs may

Implementation mAP
origin paper 0.699
using caffe pretrained model (enable with--caffe-pretrain) 0.702-0.712
using torchvision pretrained model 0.693-0.701
model converted from chainercv (reported 0.706) 0.7053
  • Speed
Implementation GPU Inference Trainining
origin paper K40 5 fps NA
This TITAN Xp 12 fps^*^ 5-6 fps
pytorch-faster-rcnn TITAN Xp NA 5-6fps^**^

* include reading images from disk, preprocessing, etc. see eval in train.py for more detail.

** it depends on the environment.

NOTE that you should make sure you install cupy correctly to reach the benchmark.

Install Prerequisites

  • install PyTorch >=0.3 with GPU (code are gpu-only), refer to official website

  • install cupy, you can install via pip install but it's better to read the docs and make sure the environ is correctly set

  • install other dependencies: pip install -r requirements.txt

  • Optional but recommended： build nms_gpu_post: cd model/utils/nmspython3 build.py build_ext --inplace

  • start vidom for visualize

nohup python3 -m visdom.server &

If you're in China and have encounter problem with visdom (i.e. timeout, blank screen), you may refer to visdom issue, and a temporay solution provided by me

Demo

download pretrained model from [..............................................]

see demo.ipynb for detail

Train

Data

Pascal VOC2007

  1. Download the training, validation, test data and VOCdevkit

    wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar

  2. Extract all of these tars into one directory named VOCdevkit

    tar xvf VOCtrainval_06-Nov-2007.tar
tar xvf VOCtest_06-Nov-2007.tar
tar xvf VOCdevkit_08-Jun-2007.tar

  3. It should have this basic structure

    $VOCdevkit/                           # development kit
$VOCdevkit/VOCcode/                   # VOC utility code
$VOCdevkit/VOC2007                    # image sets, annotations, etc.
# ... and several other directories ...

  4. specifiy the voc_data_dir in config.py, or pass it to program using argument like '--voc-data-dir=/path/to/VOCdevkit/VOC2007/' .

COCO

TBD

preprare caffe-pretrained vgg16

if you want to use caffe-pretrain model, you can run:

python misc/convert_caffe_pretrain.py

then you should speicified where caffe-pretraind model vgg16_caffe.pth stored in config.py

if you want to use torchvision pretrained model, you may skip this.

begin traininig

make checkpoints/ # make dir for storing snapshots
python3 train.py train --env='fasterrcnn-caffe' --plot-every=100 --caffe-pretrain

you may refer to config.py for more argument.

Some Key arguments:

  • --caffe-pretrain=True: use caffe pretrain model or use torchvision pretrained model(Default: torchvison)
  • --plot-every=n: visulize predict, loss etc every n batches.
  • --env: visdom env for visulization
  • --voc_data_dir: where the VOC data stored
  • --use-drop: use dropout in roi head, default without dropout
  • --use-adam: use adam instead of SGD, default SGD
  • --load-path: pretrained model path, default None, if it's specified, the pretrained model would be loaded.

Troubleshooting

  • visdom
  • dataloader/ulimit
  • cupy
  • vgg

TODO

[] training on coco [] resnet [] replace cupy with THTensor+cffi?

Acknowledge

This work builds on many excellent works, which include: