add ppyolo_voc (#1497)

* add ppyolo_voc

configs/ppyolo/README.md

@@ -84,6 +84,16 @@ PP-YOLO improved performance and speed of YOLOv3 with following methods:
 |:----------------------------:|:----------:|:----------:| :---------: | :-----------------------: | :--------: | :----------:| :------------------: | :------------: | :------: | :-----: |
 | PP-YOLO_MobileNetV3_small    |     4      |      32    |     75%     | PP-YOLO_MobileNetV3_large |   4.1MB    |     320     |         14.4         |      21.5      | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_mobilenet_v3_small.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_mobilenet_v3_small.yml)                   |
 
+### PP-YOLO on Pascal VOC
+
+PP-YOLO trained on Pascal VOC dataset as follows:
+
+|       Model        | GPU number | images/GPU |  backbone  | input shape | Box AP50<sup>val</sup> | download | config  |
+|:------------------:|:----------:|:----------:|:----------:| :----------:| :--------------------: | :------: | :-----: |
+| PP-YOLO            |     8      |      12    | ResNet50vd |     608     |          84.9          | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_voc.yml)                   |
+| PP-YOLO            |     8      |      12    | ResNet50vd |     416     |          84.3          | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_voc.yml)                   |
+| PP-YOLO            |     8      |      12    | ResNet50vd |     320     |          82.2          | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_voc.yml)                   |
+
 ## Getting Start
 
 ### 1. Training

configs/ppyolo/README_cn.md

@@ -77,6 +77,16 @@ PP-YOLO从如下方面优化和提升YOLOv3模型的精度和速度：
 - PP-YOLO_MobileNetV3 模型训练过程中使用4GPU，每GPU batch size为32进行训练，如训练GPU数和batch size不使用上述配置，须参考[FAQ](../../docs/FAQ.md)调整学习率和迭代次数。
 - PP-YOLO_MobileNetV3 模型推理速度测试环境配置为麒麟990芯片单线程。
 
+### Pascal VOC数据集上的PP-YOLO
+
+PP-YOLO在Pascal VOC数据集上训练模型如下:
+
+|       模型         | GPU个数 | 每GPU图片个数 |  骨干网络  |   输入尺寸  | Box AP50<sup>val</sup> | 模型下载 | 配置文件 |
+|:------------------:|:-------:|:-------------:|:----------:| :----------:| :--------------------: | :------: | :-----: |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     608     |          84.9          | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_voc.yml)                   |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     416     |          84.3          | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_voc.yml)                   |
+| PP-YOLO            |    8    |       12      | ResNet50vd |     320     |          82.2          | [model](https://paddlemodels.bj.bcebos.com/object_detection/ppyolo_voc.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/configs/ppyolo/ppyolo_voc.yml)                   |
+
 ## 使用说明
 
 ### 1. 训练

configs/ppyolo/ppyolo_voc.yml

+architecture: YOLOv3
+use_gpu: true
+max_iters: 70000
+log_smooth_window: 20
+log_iter: 20
+save_dir: output
+snapshot_iter: 10000
+metric: VOC
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_ssld_pretrained.tar
+weights: output/ppyolo/model_final
+num_classes: 20
+use_fine_grained_loss: true
+use_ema: true
+ema_decay: 0.9998
+
+YOLOv3:
+  backbone: ResNet
+  yolo_head: YOLOv3Head
+  use_fine_grained_loss: true
+
+ResNet:
+  norm_type: sync_bn
+  freeze_at: 0
+  freeze_norm: false
+  norm_decay: 0.
+  depth: 50
+  feature_maps: [3, 4, 5]
+  variant: d
+  dcn_v2_stages: [5]
+
+YOLOv3Head:
+  anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]]
+  anchors: [[10, 13], [16, 30], [33, 23],
+            [30, 61], [62, 45], [59, 119],
+            [116, 90], [156, 198], [373, 326]]
+  norm_decay: 0.
+  coord_conv: true
+  iou_aware: true
+  iou_aware_factor: 0.4
+  scale_x_y: 1.05
+  spp: true
+  yolo_loss: YOLOv3Loss
+  nms: MatrixNMS
+  drop_block: true
+
+YOLOv3Loss:
+  ignore_thresh: 0.7
+  scale_x_y: 1.05
+  label_smooth: false
+  use_fine_grained_loss: true
+  iou_loss: IouLoss
+  iou_aware_loss: IouAwareLoss
+
+IouLoss:
+  loss_weight: 2.5
+  max_height: 608
+  max_width: 608
+
+IouAwareLoss:
+  loss_weight: 1.0
+  max_height: 608
+  max_width: 608
+
+MatrixNMS:
+    background_label: -1
+    keep_top_k: 100
+    normalized: false
+    score_threshold: 0.01
+    post_threshold: 0.01
+
+LearningRate:
+  base_lr: 0.00333
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 56000
+    - 62000
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2
+
+_READER_: 'ppyolo_reader.yml'
+TrainReader:
+  dataset:
+    !VOCDataSet
+    dataset_dir: dataset/voc
+    anno_path: trainval.txt
+    use_default_label: true
+    with_background: false
+  mixup_epoch: 350
+  batch_size: 12
+
+EvalReader:
+  inputs_def:
+    fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']
+    num_max_boxes: 50
+  dataset:
+    !VOCDataSet
+    dataset_dir: dataset/voc
+    anno_path: test.txt
+    use_default_label: true
+    with_background: false
+
+TestReader:
+  dataset:
+    !ImageFolder
+    use_default_label: true
+    with_background: false