[smalldet] add dota and xview config (#6370)

* [smalldet]add xview sliced config

* [smalldet] add Dota and xview config

* [smalldet] add xview and dota config

* [smalldet] fix path of weight

* [smalldet] add readme

configs/smalldet/README.md

+简体中文 | [English](README.md)
+
+# PP-YOLOE Smalldet 检测模型
+
+
+|    模型   |       数据集     |  SLICE_SIZE  |  OVERLAP_RATIO  | 类别数  | mAP<sup>val<br>0.5:0.95 | AP<sup>val<br>0.5 | 下载链接  | 配置文件 |
+|:---------|:---------------:|:---------------:|:---------------:|:------:|:-----------------------:|:-------------------:|:---------:| :-----: |
+|PP-YOLOE-l|   Xview  |  400 | 0.25 | 60 |  14.5 | 26.8 | [下载链接](https://bj.bcebos.com/v1/paddledet/models/ppyoloe_crn_l_xview_400_025.pdparams) | [配置文件](./ppyoloe_crn_l_80e_sliced_xview_400_025.yml) |
+|PP-YOLOE-l|   DOTA   |  500 | 0.25 | 15 |  46.8 |  72.6 | [下载链接](https://bj.bcebos.com/v1/paddledet/models/ppyoloe_crn_l_dota_500_025.pdparams) | [配置文件](./ppyoloe_crn_l_80e_sliced_DOTA_500_025.yml) |
+
+
+**注意:**
+- **SLICE_SIZE**表示使用SAHI工具切图后子图的大小(SLICE_SIZE*SLICE_SIZE)；**OVERLAP_RATIO**表示切图重叠率。
+- 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](../ppyoloe#getting-start)。

configs/smalldet/_base_/DOTA_sliced_500_025_detection.yml

+metric: COCO
+num_classes: 15
+
+TrainDataset:
+  !COCODataSet
+    image_dir: DOTA_slice_train/train_images_500_025
+    anno_path: DOTA_slice_train/train_500_025.json
+    dataset_dir: dataset/DOTA
+    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  !COCODataSet
+    image_dir: DOTA_slice_val/val_images_500_025
+    anno_path: DOTA_slice_val/val_500_025.json
+    dataset_dir: dataset/DOTA
+
+TestDataset:
+  !ImageFolder
+    anno_path: dataset/DOTA/DOTA_slice_val/val_500_025.json
+    dataset_dir: dataset/DOTA/DOTA_slice_val/val_images_500_025

configs/smalldet/_base_/xview_sliced_400_025_detection.yml

+metric: COCO
+num_classes: 60
+
+TrainDataset:
+  !COCODataSet
+    image_dir: train_images_400_025
+    anno_path: train_400_025.json
+    dataset_dir: dataset/xview/xview_slic
+    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+EvalDataset:
+  !COCODataSet
+    image_dir: val_images_400_025
+    anno_path: val_400_025.json
+    dataset_dir: dataset/xview/xview_slic
+
+TestDataset:
+  !ImageFolder
+    anno_path: dataset/xview/xview_slic/val_400_025.json
+    dataset_dir: dataset/xview/xview_slic/val_images_400_025

configs/smalldet/ppyoloe_crn_l_80e_sliced_DOTA_500_025.yml

+_BASE_: [
+  './_base_/DOTA_sliced_500_025_detection.yml',
+  '../runtime.yml',
+  '../ppyoloe/_base_/optimizer_300e.yml',
+  '../ppyoloe/_base_/ppyoloe_crn.yml',
+  '../ppyoloe/_base_/ppyoloe_reader.yml',
+]
+log_iter: 100
+snapshot_epoch: 10
+weights: output/ppyoloe_crn_l_80e_sliced_DOTA_500_025/model_final
+
+pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
+depth_mult: 1.0
+width_mult: 1.0
+
+TrainReader:
+  batch_size: 8
+
+epoch: 80
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+    - !CosineDecay
+      max_epochs: 96
+    - !LinearWarmup
+      start_factor: 0.
+      epochs: 1
+
+PPYOLOEHead:
+  static_assigner_epoch: -1
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 10000
+    keep_top_k: 500
+    score_threshold: 0.01
+    nms_threshold: 0.6

configs/smalldet/ppyoloe_crn_l_80e_sliced_xview_400_025.yml

+_BASE_: [
+  './_base_/xview_sliced_400_025_detection.yml',
+  '../runtime.yml',
+  '../ppyoloe/_base_/optimizer_300e.yml',
+  '../ppyoloe/_base_/ppyoloe_crn.yml',
+  '../ppyoloe/_base_/ppyoloe_reader.yml',
+]
+log_iter: 100
+snapshot_epoch: 10
+weights: output/ppyoloe_crn_l_80e_sliced_xview_400_025/model_final
+
+pretrain_weights: https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
+depth_mult: 1.0
+width_mult: 1.0
+
+TrainReader:
+  batch_size: 8
+
+epoch: 80
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+    - !CosineDecay
+      max_epochs: 96
+    - !LinearWarmup
+      start_factor: 0.
+      epochs: 1
+
+PPYOLOEHead:
+  static_assigner_epoch: -1
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 10000
+    keep_top_k: 500
+    score_threshold: 0.01
+    nms_threshold: 0.6