Table 1. Directory structure
| File | Description |
|---|
| train.py | Training script |
| eval.py | Evaluation |
| infer.py | Prediction using the trained model |
| visual.py | Visualization of the test results |
| image_util.py | Image preprocessing required common function |
| data_provider.py | Data processing scripts, generate training, evaluate or detect the required data |
| config/pascal_voc_conf.py | Neural network hyperparameter configuration file |
| data/label_list | Label list |
| data/prepare_voc_data.py | Prepare training PASCAL VOC data list |
The training phase requires pre-processing of the data, including clipping, sampling, etc. This is done in ```image_util.py``` and ```data_provider.py```.```config/vgg_config.py```. ```data/prepare_voc_data.py``` is used to generate a list of files, including the training set and test set, the need to use the user to download and extract data, the default use of VOC2007 and VOC2012.
## PASCAL VOC Data set
### Data Preparation
First download the data set. VOC2007\[[3](#References)\] contains both training and test data set, and VOC2012\[[4](#References)\] contains only training set. Downloaded data are stored in ```data/VOCdevkit/VOC2007``` and ```data/VOCdevkit/VOC2012```. Next, run ```data/prepare_voc_data.py``` to generate ```trainval.txt``` and ```test.txt```. The relevant function is as following:
```python
def prepare_filelist(devkit_dir, years, output_dir):
trainval_list = []
test_list = []
for year in years:
trainval, test = walk_dir(devkit_dir, year)
trainval_list.extend(trainval)
test_list.extend(test)
random.shuffle(trainval_list)
with open(osp.join(output_dir, 'trainval.txt'), 'w') as ftrainval:
for item in trainval_list:
ftrainval.write(item[0] + ' ' + item[1] + '\n')
with open(osp.join(output_dir, 'test.txt'), 'w') as ftest:
for item in test_list:
ftest.write(item[0] + ' ' + item[1] + '\n')
```
The data in ```trainval.txt``` will look like:
```
VOCdevkit/VOC2007/JPEGImages/000005.jpg VOCdevkit/VOC2007/Annotations/000005.xml
VOCdevkit/VOC2007/JPEGImages/000007.jpg VOCdevkit/VOC2007/Annotations/000007.xml
VOCdevkit/VOC2007/JPEGImages/000009.jpg VOCdevkit/VOC2007/Annotations/000009.xml
```
The first field is the relative path of the image file, and the second field is the relative path of the corresponding label file.
### To Use Pre-trained Model
We also provide a pre-trained model using VGG-16 with good performance. To use the model, download the file http://paddlepaddle.bj.bcebos.com/model_zoo/detection/ssd_model/vgg_model.tar.gz, and place it as ```vgg/vgg_model.tar.gz```。
### Training
Next, run ```python train.py``` to train the model. Note that this example only supports the CUDA GPU environment, and can not be trained using only CPU. This is mainly because the training is very slow using CPU only.
```python
paddle.init(use_gpu=True, trainer_count=4)
data_args = data_provider.Settings(
data_dir='./data',
label_file='label_list',
resize_h=cfg.IMG_HEIGHT,
resize_w=cfg.IMG_WIDTH,
mean_value=[104,117,124])
train(train_file_list='./data/trainval.txt',
dev_file_list='./data/test.txt',
data_args=data_args,
init_model_path='./vgg/vgg_model.tar.gz')
```
Below is a description about this script:
1. Call ```paddle.init``` with 4 GPUs.
2. ```data_provider.Settings()``` is to pass configuration parameters. For ```config/vgg_config.py``` setting，300x300 is a typical configuration for both the accuracy and efficiency. It can be extended to 512x512 by modifying the configuration file.
3. In ```train()```执 function, ```train_file_list``` specifies the training data list, and ```dev_file_list``` specifies the evaluation data list, and ```init_model_path``` specifies the pre-training model location.
4. During the training process will print some log information, each training a batch will output the current number of rounds, the current batch cost and mAP (mean Average Precision. Each training pass will be saved a model to the default saved directory ```checkpoints``` (Need to be created in advance).
The following shows the SDD300x300 in the VOC data set.
