# A Pythonic, Simple and Fast Implementation of Faster RCNN
# A Simple and Fast Implementation of Faster R-CNN
## Introduction
This project is a **Simplified** Faster RCNN implementation based on [chainercv](https://github.com/chainer/chainercv) and other [projects](#Acknowledgement) . It aims to:
This project is a **Simplified** Faster R-CNN implementation based on [chainercv](https://github.com/chainer/chainercv) and other [projects](#Acknowledgement) . It aims to:
- Simplify the code (*Simple is better than complex*)
- Make the code more straightforward (*Flat is better than nested*)
- Match the performance reported in [origin paper](https://arxiv.org/abs/1506.01497)(*Speed Counts and mAP Matters*)
- Match the performance reported in [origin paper](https://arxiv.org/abs/1506.01497)(*Speed Counts and mAP Matters*)
## Performance
...
...
@@ -14,7 +14,7 @@ This project is a **Simplified** Faster RCNN implementation based on [chainercv]
VGG16 train on `trainval` and test on `test` split.
**Note**: the training shows great randomness, you may need to train more epoch and a bit of luck to reach the highest mAP. However, it should be easy to surpass the lower bound.
**Note**: the training shows great randomness, you may need a bit of luck and more epoches of training to reach the highest mAP. However, it should be easy to surpass the lower bound.
@@ -57,14 +57,14 @@ If you're in China and have encounter problem with visdom (i.e. timeout, blank s
## Demo
Download pretrained model from [google drive](https://drive.google.com/open?id=1cQ27LIn-Rig4-Uayzy_gH5-cW-NRGVzY).
Download pretrained model from [Google Drive](https://drive.google.com/open?id=1cQ27LIn-Rig4-Uayzy_gH5-cW-NRGVzY).
See [demo.ipynb](https://github.com/chenyuntc/Simplified-FasterRCNN/blob/master/demo.ipynb) for more detail.
See [demo.ipynb](https://github.com/chenyuntc/simple-faster-rcnn-pytorch/blob/master/demo.ipynb) for more detail.
## Train
### Data
### Prepare data
#### Pascal VOC2007
...
...
@@ -99,7 +99,7 @@ See [demo.ipynb](https://github.com/chenyuntc/Simplified-FasterRCNN/blob/master/
TBD
### preprare caffe-pretrained vgg16
### Prepare caffe-pretrained vgg16
If you want to use caffe-pretrain model as initial weight, you can run below to get vgg16 weights converted from caffe, which is the same as the origin paper use.
...
...
@@ -107,7 +107,7 @@ If you want to use caffe-pretrain model as initial weight, you can run below to
python misc/convert_caffe_pretrain.py
````
This would download pretrained model and converted it to the format compatible with torchvision.
This scripts would download pretrained model and converted it to the format compatible with torchvision.
Then you should specify where caffe-pretraind model `vgg16_caffe.pth` stored in `config.py` by setting `caffe_pretrain_path`
...
...
@@ -120,7 +120,7 @@ If you want to use torchvision pretrained model, you may skip this step.
### begin training
```Bash
make checkpoints/ # make dir for storing snapshots
mkdir checkpoints/ # folder for snapshots
```
```bash
...
...
@@ -139,6 +139,9 @@ Some Key arguments:
-`--use-Adam`: use Adam instead of SGD, default SGD. (You need set a very low `lr` for Adam)
-`--load-path`: pretrained model path, default `None`, if it's specified, the pretrained model would be loaded.
you may open browser, type:`http://<ip>:8097` and see the visualization of training procedure as below:
