add sku110k models (#7465)

* add sku110k models

* add link in ppyoloe doc

* modify directory of sku110k

* fix data config problem

configs/ppyoloe/README.md

@@ -89,6 +89,8 @@ The PaddleDetection team provides configs and weights of various feature detecti
 |Pedestrian Detection | CrowdHuman | [pphuman](../pphuman) |
 |Vehicle Detection | BDD100K, UA-DETRAC | [ppvehicle](../ppvehicle) |
 |Small Object Detection | VisDrone、DOTA、xView |  [smalldet](../smalldet) |
+|Densely Packed Object Detection | SKU110k | [application](./application) |
+|Rotated Object Detection | DOTA | [PP-YOLOE-R](../rotate/ppyoloe_r/) |
 
 
 ## Getting Start

configs/ppyoloe/README_cn.md

@@ -88,6 +88,8 @@ PaddleDetection团队提供了基于PP-YOLOE的各种垂类检测模型的配置
 |  行人检测   | CrowdHuman  |   [pphuman](../pphuman)  |
 |  车辆检测   | BDD100K、UA-DETRAC  |  [ppvehicle](../ppvehicle)   |
 |  小目标检测 | VisDrone、DOTA、xView |  [smalldet](../smalldet)   |
+| 密集目标检测 | SKU110k | [application](./application) |
+| 旋转框检测 | DOTA | [PP-YOLOE-R](../rotate/ppyoloe_r/) |
 
 
 ## 使用说明

configs/ppyoloe/application/README.md

@@ -11,6 +11,8 @@
 工业数据集使用[PKU-Market-PCB](https://robotics.pkusz.edu.cn/resources/dataset/)，该数据集用于印刷电路板（PCB）的瑕疵检测，提供了6种常见的PCB缺陷，
 处理后的COCO格式，包含图片训练集555张，测试集138张，6个类别，[PKU-Market-PCB COCO格式下载](https://bj.bcebos.com/v1/paddledet/data/PCB_coco.zip)。
 
+商超数据集[SKU110k](https://github.com/eg4000/SKU110K_CVPR19)是商品超市场景下的密集目标检测数据集，包含11,762张图片和超过170个实例。其中包括8,233张用于训练的图像、588张用于验证的图像和2,941张用于测试的图像。
+
 
 ## 实验结果：
 
@@ -31,11 +33,30 @@
 - 具体使用教程请参考[ppyoloe](../ppyoloe#getting-start)。  
 
 
+## SKU110k Model ZOO
+|     Model      | Epoch | GPU number | images/GPU |  backbone  | input shape | Box AP<sup>val<br>0.5:0.95 (maxDets=300) | Box AP<sup>test<br>0.5:0.95 (maxDets=300) | download | config |
+|:--------------:|:-----:|:-------:|:----------:|:----------:| :-------:|:-------------------------:|:---------------------------:|:---------:|:------:|
+| PP-YOLOE+_s | 80 | 8 | 8 | cspresnet-s | 960 | 57.4 | 58.8 | [download](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_sku110k.pdparams) | [config](./ppyoloe_plus_crn_s_80e_sku110k.yml) |
+| PP-YOLOE+_m | 80 | 8 | 8 | cspresnet-m | 960 | 58.2 | 59.7 | [download](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_m_80e_sku110k.pdparams) | [config](./ppyoloe_plus_crn_m_80e_sku110k.yml) |
+| PP-YOLOE+_l | 80 | 8 | 4 | cspresnet-l | 960 | 58.8 | 60.2 | [download](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_l_80e_sku110k.pdparams) | [config](./ppyoloe_plus_crn_l_80e_sku110k.yml) |
+| PP-YOLOE+_x | 80 | 8 | 4 | cspresnet-x | 960 | 59.0 | 60.3 | [download](https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_x_80e_sku110k.pdparams) | [config](./ppyoloe_plus_crn_x_80e_sku110k.yml) |
+
 
+**注意:**
+- SKU110k系列模型训练过程中使用8 GPUs进行训练，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。
+- SKU110k数据集使用**maxDets=300**的mAP值作为评估指标。
+- 具体使用教程请参考[ppyoloe](../ppyoloe#getting-start)。
 
 
 ## 引用
 ```
+@inproceedings{goldman2019dense,
+ author    = {Eran Goldman and Roei Herzig and Aviv Eisenschtat and Jacob Goldberger and Tal Hassner},
+ title     = {Precise Detection in Densely Packed Scenes},
+ booktitle = {Proc. Conf. Comput. Vision Pattern Recognition (CVPR)},
+ year      = {2019}
+}
+
 @article{Exdark,
 title={Getting to Know Low-light Images with The Exclusively Dark Dataset},
 author={Loh, Yuen Peng and Chan, Chee Seng},

configs/ppyoloe/application/_base_/sku110k.yml

+metric: COCO
+num_classes: 1
+
+TrainDataset:
+  !COCODataSet
+    image_dir: images
+    anno_path: annotations/annotations_train.json
+    dataset_dir: dataset/SKU110K_fixed
+    data_fields: ['image', 'gt_bbox', 'gt_class', 'difficult']
+
+EvalDataset:
+  !COCODataSet
+    image_dir: images
+    anno_path: annotations/annotations_val.json
+    dataset_dir: dataset/SKU110K_fixed
+    allow_empty: true
+
+TestDataset:
+  !ImageFolder
+    anno_path: annotations/annotations_test.json
+    dataset_dir: dataset/SKU110K_fixed

configs/ppyoloe/application/ppyoloe_plus_crn_l_80e_sku110k.yml

+_BASE_: [
+  './_base_/sku110k.yml',
+  '../../runtime.yml'
+]
+
+log_iter: 10
+snapshot_epoch: 20
+weights: output/ppyoloe_plus_crn_s_80e_coco/model_final
+
+pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/ppyoloe_crn_l_obj365_pretrained.pdparams
+depth_mult: 1.0
+width_mult: 1.0
+
+
+# arch
+architecture: YOLOv3
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+custom_black_list: ['reduce_mean']
+
+YOLOv3:
+  backbone: CSPResNet
+  neck: CustomCSPPAN
+  yolo_head: PPYOLOEHead
+  post_process: ~
+
+CSPResNet:
+  layers: [3, 6, 6, 3]
+  channels: [64, 128, 256, 512, 1024]
+  return_idx: [1, 2, 3]
+  use_large_stem: True
+  use_alpha: True
+
+CustomCSPPAN:
+  out_channels: [768, 384, 192]
+  stage_num: 1
+  block_num: 3
+  act: 'swish'
+  spp: true
+  use_alpha: True
+
+PPYOLOEHead:
+  fpn_strides: [32, 16, 8]
+  grid_cell_scale: 5.0
+  grid_cell_offset: 0.5
+  static_assigner_epoch: -1
+  use_varifocal_loss: True
+  loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
+  static_assigner:
+    name: ATSSAssigner
+    topk: 9
+  assigner:
+    name: TaskAlignedAssigner
+    topk: 13
+    alpha: 1.0
+    beta: 6.0
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 3000
+    keep_top_k: 1000
+    score_threshold: 0.01
+    nms_threshold: 0.7
+
+
+# reader
+worker_num: 8
+eval_height: &eval_height 960
+eval_width: &eval_width 960
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [3000, 1800], keep_ratio: True, interp: 2}
+    - RandomDistort: {}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800, 832, 864, 896, 928, 960, 992, 1024, 1056, 1088, 1120, 1152], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+    - PadGT: {}
+  batch_size: 4
+  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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - 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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+  batch_size: 1
+
+
+# optimizer
+epoch: 80
+
+LearningRate:
+  base_lr: 0.002
+  schedulers:
+    - !CosineDecay
+      max_epochs: 96
+    - !LinearWarmup
+      start_factor: 0.
+      epochs: 5
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/application/ppyoloe_plus_crn_m_80e_sku110k.yml

+_BASE_: [
+  './_base_/sku110k.yml',
+  '../../runtime.yml'
+]
+
+log_iter: 10
+snapshot_epoch: 20
+weights: output/ppyoloe_plus_crn_s_80e_coco/model_final
+
+pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/ppyoloe_crn_m_obj365_pretrained.pdparams
+depth_mult: 0.67
+width_mult: 0.75
+
+
+# arch
+architecture: YOLOv3
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+custom_black_list: ['reduce_mean']
+
+YOLOv3:
+  backbone: CSPResNet
+  neck: CustomCSPPAN
+  yolo_head: PPYOLOEHead
+  post_process: ~
+
+CSPResNet:
+  layers: [3, 6, 6, 3]
+  channels: [64, 128, 256, 512, 1024]
+  return_idx: [1, 2, 3]
+  use_large_stem: True
+  use_alpha: True
+
+CustomCSPPAN:
+  out_channels: [768, 384, 192]
+  stage_num: 1
+  block_num: 3
+  act: 'swish'
+  spp: true
+  use_alpha: True
+
+PPYOLOEHead:
+  fpn_strides: [32, 16, 8]
+  grid_cell_scale: 5.0
+  grid_cell_offset: 0.5
+  static_assigner_epoch: -1
+  use_varifocal_loss: True
+  loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
+  static_assigner:
+    name: ATSSAssigner
+    topk: 9
+  assigner:
+    name: TaskAlignedAssigner
+    topk: 13
+    alpha: 1.0
+    beta: 6.0
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 3000
+    keep_top_k: 1000
+    score_threshold: 0.01
+    nms_threshold: 0.7
+
+
+# reader
+worker_num: 8
+eval_height: &eval_height 960
+eval_width: &eval_width 960
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [3000, 1800], keep_ratio: True, interp: 2}
+    - RandomDistort: {}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800, 832, 864, 896, 928, 960, 992, 1024, 1056, 1088, 1120, 1152], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+    - PadGT: {}
+  batch_size: 8
+  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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - 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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+  batch_size: 1
+
+
+# optimizer
+epoch: 80
+
+LearningRate:
+  base_lr: 0.004
+  schedulers:
+    - !CosineDecay
+      max_epochs: 96
+    - !LinearWarmup
+      start_factor: 0.
+      epochs: 5
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/application/ppyoloe_plus_crn_s_80e_sku110k.yml

+_BASE_: [
+  './_base_/sku110k.yml',
+  '../../runtime.yml'
+]
+
+log_iter: 10
+snapshot_epoch: 20
+weights: output/ppyoloe_plus_crn_s_80e_coco/model_final
+
+pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/ppyoloe_crn_s_obj365_pretrained.pdparams
+depth_mult: 0.33
+width_mult: 0.50
+
+
+# arch
+architecture: YOLOv3
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+custom_black_list: ['reduce_mean']
+
+YOLOv3:
+  backbone: CSPResNet
+  neck: CustomCSPPAN
+  yolo_head: PPYOLOEHead
+  post_process: ~
+
+CSPResNet:
+  layers: [3, 6, 6, 3]
+  channels: [64, 128, 256, 512, 1024]
+  return_idx: [1, 2, 3]
+  use_large_stem: True
+  use_alpha: True
+
+CustomCSPPAN:
+  out_channels: [768, 384, 192]
+  stage_num: 1
+  block_num: 3
+  act: 'swish'
+  spp: true
+  use_alpha: True
+
+PPYOLOEHead:
+  fpn_strides: [32, 16, 8]
+  grid_cell_scale: 5.0
+  grid_cell_offset: 0.5
+  static_assigner_epoch: -1
+  use_varifocal_loss: True
+  loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
+  static_assigner:
+    name: ATSSAssigner
+    topk: 9
+  assigner:
+    name: TaskAlignedAssigner
+    topk: 13
+    alpha: 1.0
+    beta: 6.0
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 3000
+    keep_top_k: 1000
+    score_threshold: 0.01
+    nms_threshold: 0.7
+
+
+# reader
+worker_num: 8
+eval_height: &eval_height 960
+eval_width: &eval_width 960
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [3000, 1800], keep_ratio: True, interp: 2}
+    - RandomDistort: {}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800, 832, 864, 896, 928, 960, 992, 1024, 1056, 1088, 1120, 1152], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+    - PadGT: {}
+  batch_size: 8
+  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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - 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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+  batch_size: 1
+
+
+# optimizer
+epoch: 80
+
+LearningRate:
+  base_lr: 0.004
+  schedulers:
+    - !CosineDecay
+      max_epochs: 96
+    - !LinearWarmup
+      start_factor: 0.
+      epochs: 5
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/application/ppyoloe_plus_crn_x_80e_sku110k.yml

+_BASE_: [
+  './_base_/sku110k.yml',
+  '../../runtime.yml'
+]
+
+log_iter: 10
+snapshot_epoch: 20
+weights: output/ppyoloe_plus_crn_s_80e_coco/model_final
+
+pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/ppyoloe_crn_x_obj365_pretrained.pdparams
+depth_mult: 1.33
+width_mult: 1.25
+
+
+# arch
+architecture: YOLOv3
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+custom_black_list: ['reduce_mean']
+
+YOLOv3:
+  backbone: CSPResNet
+  neck: CustomCSPPAN
+  yolo_head: PPYOLOEHead
+  post_process: ~
+
+CSPResNet:
+  layers: [3, 6, 6, 3]
+  channels: [64, 128, 256, 512, 1024]
+  return_idx: [1, 2, 3]
+  use_large_stem: True
+  use_alpha: True
+
+CustomCSPPAN:
+  out_channels: [768, 384, 192]
+  stage_num: 1
+  block_num: 3
+  act: 'swish'
+  spp: true
+  use_alpha: True
+
+PPYOLOEHead:
+  fpn_strides: [32, 16, 8]
+  grid_cell_scale: 5.0
+  grid_cell_offset: 0.5
+  static_assigner_epoch: -1
+  use_varifocal_loss: True
+  loss_weight: {class: 1.0, iou: 2.5, dfl: 0.5}
+  static_assigner:
+    name: ATSSAssigner
+    topk: 9
+  assigner:
+    name: TaskAlignedAssigner
+    topk: 13
+    alpha: 1.0
+    beta: 6.0
+  nms:
+    name: MultiClassNMS
+    nms_top_k: 3000
+    keep_top_k: 1000
+    score_threshold: 0.01
+    nms_threshold: 0.7
+
+
+# reader
+worker_num: 8
+eval_height: &eval_height 960
+eval_width: &eval_width 960
+eval_size: &eval_size [*eval_height, *eval_width]
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [3000, 1800], keep_ratio: True, interp: 2}
+    - RandomDistort: {}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize: {target_size: [480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800, 832, 864, 896, 928, 960, 992, 1024, 1056, 1088, 1120, 1152], random_size: True, random_interp: True, keep_ratio: False}
+    - NormalizeImage: {mean: [0., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+    - PadGT: {}
+  batch_size: 4
+  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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - 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., 0., 0.], std: [1., 1., 1.], norm_type: none}
+    - Permute: {}
+  batch_size: 1
+
+
+# optimizer
+epoch: 80
+
+LearningRate:
+  base_lr: 0.002
+  schedulers:
+    - !CosineDecay
+      max_epochs: 96
+    - !LinearWarmup
+      start_factor: 0.
+      epochs: 5
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2