add p2 and largesize visdrone model (#6213)

* add p2 and largesize visdrone model, test=document_fix

* add size doc, test=document_fix

configs/visdrone/README.md

@@ -7,11 +7,16 @@ PaddleDetection团队提供了针对VisDrone-DET小目标数航拍场景的基
 |    模型   | COCOAPI mAP<sup>val<br>0.5:0.95 | COCOAPI mAP<sup>val<br>0.5 | COCOAPI mAP<sup>test_dev<br>0.5:0.95 | COCOAPI mAP<sup>test_dev<br>0.5 | MatlabAPI mAP<sup>test_dev<br>0.5:0.95 | MatlabAPI mAP<sup>test_dev<br>0.5 | 下载  | 配置文件 |
 |:---------|:------:|:------:| :----: | :------:| :------: | :------:| :----: | :------:|
 |PP-YOLOE-s|  23.5  |  39.9  |  19.4  |  33.6   |  23.68   |  40.66  | [下载链接](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_80e_visdrone.pdparams) | [配置文件](./ppyoloe_crn_s_80e_visdrone.yml) |
-|PP-YOLOE-l|  29.8  |  48.3  |  23.0  |  38.6   |  27.29   |  45.52  | [下载链接](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_80e_visdrone.pdparams) | [配置文件](./ppyoloe_crn_l_80e_visdrone.yml) |
+|PP-YOLOE-l|  29.2  |  47.3  |  23.5  |  39.1   |  28.00   |  46.20  | [下载链接](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_80e_visdrone.pdparams) | [配置文件](./ppyoloe_crn_l_80e_visdrone.yml) |
+|PP-YOLOE-P2-l|  30.0  |  49.2  |  24.1  |  40.9   |  28.47   |  48.16  | [下载链接](https://paddledet.bj.bcebos.com/models/ppyoloe_p2_crn_l_80e_visdrone.pdparams) | [配置文件](./ppyoloe_p2_crn_l_80e_visdrone.yml) |
+|PP-YOLOE-l largesize|  40.3  |  63.5  |  31.3  |  51.8   |  36.13   |  59.96  | [下载链接](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_80e_visdrone_largesize.pdparams) | [配置文件](./ppyoloe_crn_l_80e_visdrone_largesize.yml) |
 
 **注意:**
 - PP-YOLOE模型训练过程中使用8 GPUs进行混合精度训练，如果**GPU卡数**或者**batch size**发生了改变，你需要按照公式 **lr<sub>new</sub> = lr<sub>default</sub> * (batch_size<sub>new</sub> * GPU_number<sub>new</sub>) / (batch_size<sub>default</sub> * GPU_number<sub>default</sub>)** 调整学习率。
-- 具体使用教程请参考[ppyoloe](../configs/ppyoloe#getting-start)。
+- 具体使用教程请参考[ppyoloe](../ppyoloe#getting-start)。
+- PP-YOLOE-P2是指增加P2层(1/4下采样层)的特征，共输出4个PPYOLOEHead。
+- largesize是指使用以1600尺度为基础的多尺度训练和1920尺度预测，相应的训练batch_size也减小，以速度来换取高精度。
+- MatlabAPI测试是使用官网评测工具[VisDrone2018-DET-toolkit](https://github.com/VisDrone/VisDrone2018-DET-toolkit)。
 
 
 ## 引用

configs/visdrone/ppyoloe_crn_l_80e_visdrone.yml

@@ -18,7 +18,7 @@ TrainReader:
 
 epoch: 80
 LearningRate:
-  base_lr: 0.001
+  base_lr: 0.01
   schedulers:
     - !CosineDecay
       max_epochs: 96

configs/visdrone/ppyoloe_crn_l_80e_visdrone_largesize.yml

+_BASE_: [
+  'ppyoloe_crn_l_80e_visdrone.yml',
+]
+weights: output/ppyoloe_crn_l_80e_visdrone_largesize/model_final
+
+pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
+
+TrainReader:
+  batch_size: 2
+
+LearningRate:
+  base_lr: 0.0025
+
+
+worker_num: 2
+eval_height: &eval_height 1920
+eval_width: &eval_width 1920
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [1024, 1088, 1152, 1216, 1280, 1344, 1408, 1472, 1536, 1600, 1664, 1728, 1792, 1856, 1920], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - PadGT: {}
+  batch_size: 2
+  shuffle: true
+  drop_last: true
+  use_shared_memory: true
+  collate_batch: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 2
+
+TestReader:
+  inputs_def:
+    image_shape: [3, *eval_height, *eval_width]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+  batch_size: 1

configs/visdrone/ppyoloe_crn_s_80e_visdrone.yml

@@ -18,7 +18,7 @@ TrainReader:
 
 epoch: 80
 LearningRate:
-  base_lr: 0.001
+  base_lr: 0.01
   schedulers:
     - !CosineDecay
       max_epochs: 96

configs/visdrone/ppyoloe_p2_crn_l_80e_visdrone.yml

+_BASE_: [
+  'ppyoloe_crn_l_80e_visdrone.yml',
+]
+weights: output/ppyoloe_p2_crn_l_80e_visdrone/model_final
+
+pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
+
+TrainReader:
+  batch_size: 4
+
+LearningRate:
+  base_lr: 0.005
+
+CSPResNet:
+  return_idx: [0, 1, 2, 3]
+
+CustomCSPPAN:
+  out_channels: [768, 384, 192, 64]
+
+PPYOLOEHead:
+  fpn_strides: [32, 16, 8, 4]