siton bug

configs/ppyolo/ppyolo_mbv3_small_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_mbv3_small.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 10
+weights: output/ppyolo_mbv3_small_coco/model_final
+
+TrainReader:
+  inputs_def:
+    num_max_boxes: 90
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize:
+        target_size: [224, 256, 288, 320, 352, 384, 416, 448, 480, 512]
+        random_size: True
+        random_interp: True
+        keep_ratio: False
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 90}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
+    - Permute: {}
+    - Gt2YoloTarget:
+        anchor_masks: [[3, 4, 5], [0, 1, 2]]
+        anchors: [[11, 18], [34, 47], [51, 126], [115, 71], [120, 195], [254, 235]]
+        downsample_ratios: [32, 16]
+        iou_thresh: 0.25
+        num_classes: 80
+  batch_size: 32
+  mixup_epoch: 200
+  shuffle: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], 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: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 320, 320]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [320, 320], 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
+
+epoch: 270
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 162
+    - 216
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyolo/ppyolo_r18vd_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r18vd.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 10
+weights: output/ppyolo_r18vd_coco/model_final
+
+TrainReader:
+  sample_transforms:
+    - Decode: {}
+    - Mixup: {alpha: 1.5, beta: 1.5}
+    - RandomDistort: {}
+    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
+    - RandomCrop: {}
+    - RandomFlip: {}
+  batch_transforms:
+    - BatchRandomResize:
+        target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
+        random_size: True
+        random_interp: True
+        keep_ratio: False
+    - NormalizeBox: {}
+    - PadBox: {num_max_boxes: 50}
+    - BboxXYXY2XYWH: {}
+    - NormalizeImage:
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        is_scale: True
+    - Permute: {}
+    - Gt2YoloTarget:
+        anchor_masks: [[3, 4, 5], [0, 1, 2]]
+        anchors: [[10, 14], [23, 27], [37, 58], [81, 82], [135, 169], [344, 319]]
+        downsample_ratios: [32, 16]
+
+  batch_size: 32
+  mixup_epoch: 500
+  shuffle: true
+
+EvalReader:
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [512, 512], 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: 8
+
+TestReader:
+  inputs_def:
+    image_shape: [3, 512, 512]
+  sample_transforms:
+    - Decode: {}
+    - Resize: {target_size: [512, 512], 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
+
+epoch: 270
+
+LearningRate:
+  base_lr: 0.004
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 162
+    - 216
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyolo/ppyolo_r50vd_dcn_1x_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 16
+weights: output/ppyolo_r50vd_dcn_1x_coco/model_final

configs/ppyolo/ppyolo_r50vd_dcn_1x_minicoco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 8
+use_ema: true
+weights: output/ppyolo_r50vd_dcn_1x_minicoco/model_final
+
+TrainReader:
+  batch_size: 12
+
+TrainDataset:
+  !COCODataSet
+    image_dir: train2017
+    # refer to https://github.com/giddyyupp/coco-minitrain
+    anno_path: annotations/instances_minitrain2017.json
+    dataset_dir: dataset/coco
+    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd']
+
+epoch: 192
+
+LearningRate:
+  base_lr: 0.005
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 153
+    - 173
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyolo/ppyolo_r50vd_dcn_2x_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_2x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 16
+weights: output/ppyolo_r50vd_dcn_2x_coco/model_final

configs/ppyolo/ppyolo_r50vd_dcn_voc.yml

+_BASE_: [
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 83
+weights: output/ppyolo_r50vd_dcn_voc/model_final
+
+TrainReader:
+  mixup_epoch: 350
+  batch_size: 12
+
+# set collate_batch to false because ground-truth info is needed
+# on voc dataset and should not collate data in batch when batch size
+# is larger than 1.
+EvalReader:
+  collate_batch: false
+
+epoch: 583
+
+LearningRate:
+  base_lr: 0.00333
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 466
+    - 516
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyolo/ppyolo_test.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_r50vd_dcn.yml',
+  './_base_/optimizer_1x.yml',
+  './_base_/ppyolo_reader.yml',
+]
+
+snapshot_epoch: 16
+
+EvalDataset:
+  !COCODataSet
+    image_dir: test2017
+    anno_path: annotations/image_info_test-dev2017.json
+    dataset_dir: dataset/coco

configs/ppyolo/ppyolo_tiny_650e_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolo_tiny.yml',
+  './_base_/optimizer_650e.yml',
+  './_base_/ppyolo_tiny_reader.yml',
+]
+
+snapshot_epoch: 1
+weights: output/ppyolo_tiny_650e_coco/model_final

configs/ppyolo/ppyolov2_r101vd_dcn_365e_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolov2_r50vd_dcn.yml',
+  './_base_/optimizer_365e.yml',
+  './_base_/ppyolov2_reader.yml',
+]
+
+snapshot_epoch: 8
+weights: output/ppyolov2_r101vd_dcn_365e_coco/model_final
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/ResNet101_vd_ssld_pretrained.pdparams
+
+ResNet:
+  depth: 101
+  variant: d
+  return_idx: [1, 2, 3]
+  dcn_v2_stages: [3]
+  freeze_at: -1
+  freeze_norm: false
+  norm_decay: 0.

configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/ppyolov2_r50vd_dcn.yml',
+  './_base_/optimizer_365e.yml',
+  './_base_/ppyolov2_reader.yml',
+]
+
+snapshot_epoch: 8
+weights: output/ppyolov2_r50vd_dcn_365e_coco/model_final

configs/ppyolo/ppyolov2_r50vd_dcn_voc.yml

+_BASE_: [
+  '../datasets/voc.yml',
+  '../runtime.yml',
+  './_base_/ppyolov2_r50vd_dcn.yml',
+  './_base_/optimizer_365e.yml',
+  './_base_/ppyolov2_reader.yml',
+]
+
+snapshot_epoch: 83
+weights: output/ppyolov2_r50vd_dcn_voc/model_final
+
+TrainReader:
+  mixup_epoch: 350
+  batch_size: 12
+
+# set collate_batch to false because ground-truth info is needed
+# on voc dataset and should not collate data in batch when batch size
+# is larger than 1.
+EvalReader:
+  collate_batch: false
+
+epoch: 583
+
+LearningRate:
+  base_lr: 0.00333
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones:
+    - 466
+    - 516
+  - !LinearWarmup
+    start_factor: 0.
+    steps: 4000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/README_legacy.md

+# PP-YOLOE Legacy Model Zoo (2022.03)
+
+## Legacy Model Zoo
+|          Model           | Epoch | GPU number | images/GPU |  backbone  | input shape | Box AP<sup>val<br>0.5:0.95 | Box AP<sup>test<br>0.5:0.95 | Params(M) | FLOPs(G) | V100 FP32(FPS) | V100 TensorRT FP16(FPS) | download | config  |
+|:------------------------:|:-------:|:-------:|:--------:|:----------:| :-------:| :------------------: | :-------------------: |:---------:|:--------:|:---------------:| :---------------------: | :------: | :------: |
+| PP-YOLOE-s                  | 400 |     8      |    32    | cspresnet-s |     640     |       43.4        |        43.6         |   7.93    |  17.36   |   208.3   |  333.3   | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](./ppyoloe_crn_s_400e_coco.yml)                   |
+| PP-YOLOE-s                  | 300 |     8      |    32    | cspresnet-s |     640     |       43.0        |        43.2         |   7.93    |  17.36   |   208.3   |  333.3   | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](./ppyoloe_crn_s_300e_coco.yml)                   |
+| PP-YOLOE-m                  | 300 |     8      |    28    | cspresnet-m |     640     |       49.0        |        49.1         |   23.43   |  49.91   |   123.4   |  208.3   | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](./ppyoloe_crn_m_300e_coco.yml)                   |
+| PP-YOLOE-l                  | 300 |     8      |    20    | cspresnet-l |     640     |       51.4        |        51.6         |   52.20   |  110.07  |   78.1    |  149.2   | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](./ppyoloe_crn_l_300e_coco.yml)                   |
+| PP-YOLOE-x                  | 300 |     8      |    16    | cspresnet-x |     640     |       52.3        |        52.4         |   98.42   |  206.59  |   45.0    |   95.2   | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](./ppyoloe_crn_x_300e_coco.yml)                   |
+
+### Comprehensive Metrics
+|          Model           | Epoch | AP<sup>0.5:0.95 | AP<sup>0.5 |  AP<sup>0.75  | AP<sup>small  | AP<sup>medium | AP<sup>large | AR<sup>small | AR<sup>medium | AR<sup>large | download | config  |
+|:----------------------:|:-----:|:---------------:|:----------:|:-------------:| :------------:| :-----------: | :----------: |:------------:|:-------------:|:------------:| :-----: | :-----: |
+| PP-YOLOE-s             | 400 |      43.4      |     60.0    |     47.5      |     25.7      |      47.8     |     59.2     |     43.9     |      70.8     |   81.9         | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_400e_coco.pdparams) | [config](./ppyoloe_crn_s_400e_coco.yml)|
+| PP-YOLOE-s             | 300 |      43.0      |     59.6    |     47.2      |     26.0      |      47.4     |     58.7     |     45.1     |      70.6     |   81.4         | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_s_300e_coco.pdparams) | [config](./ppyoloe_crn_s_300e_coco.yml)|
+| PP-YOLOE-m             | 300 |      49.0      |     65.9    |     53.8      |     30.9      |      53.5     |     65.3     |     50.9     |      74.4     |   84.7         | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_m_300e_coco.pdparams) | [config](./ppyoloe_crn_m_300e_coco.yml)|
+| PP-YOLOE-l             | 300 |      51.4      |     68.6    |     56.2      |     34.8      |      56.1     |     68.0     |     53.1     |      76.8     |   85.6         | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams) | [config](./ppyoloe_crn_l_300e_coco.yml)|
+| PP-YOLOE-x             | 300 |      52.3      |     69.5    |     56.8      |     35.1      |      57.0     |     68.6     |     55.5     |      76.9     |   85.7         | [model](https://paddledet.bj.bcebos.com/models/ppyoloe_crn_x_300e_coco.pdparams) | [config](./ppyoloe_crn_x_300e_coco.yml)|
+
+
+**Notes:**
+
+- PP-YOLOE is trained on COCO train2017 dataset and evaluated on val2017 & test-dev2017 dataset.
+- The model weights in the table of Comprehensive Metrics are **the same as** that in the original Model Zoo, and evaluated on **val2017**.
+- PP-YOLOE used 8 GPUs for training, if **GPU number** or **mini-batch size** is changed, **learning rate** should be adjusted according to the formula **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>)**.
+- PP-YOLOE inference speed is tesed on single Tesla V100 with batch size as 1, **CUDA 10.2**, **CUDNN 7.6.5**, **TensorRT 6.0.1.8** in TensorRT mode.
+
+## Appendix
+
+Ablation experiments of PP-YOLOE.
+
+| NO.  |        Model                 | Box AP<sup>val</sup> | Params(M) | FLOPs(G) | V100 FP32 FPS |
+| :--: | :---------------------------: | :------------------: | :-------: | :------: | :-----------: |
+|  A   | PP-YOLOv2          |         49.1         |   54.58   |  115.77   |     68.9     |
+|  B   | A + Anchor-free    |         48.8         |   54.27   |  114.78   |     69.8     |
+|  C   | B + CSPRepResNet   |         49.5         |   47.42   |  101.87   |     85.5     |
+|  D   | C + TAL            |         50.4         |   48.32   |  104.75   |     84.0     |
+|  E   | D + ET-Head        |         50.9         |   52.20   |  110.07   |     78.1     |

configs/ppyoloe/_base_/optimizer_300e.yml

+epoch: 300
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+    - name: CosineDecay
+      max_epochs: 360
+    - name: LinearWarmup
+      start_factor: 0.
+      epochs: 5
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/_base_/optimizer_36e_xpu.yml

+epoch: 36
+
+LearningRate:
+  base_lr: 0.00125
+  schedulers:
+    - name: CosineDecay
+      max_epochs: 43
+    - name: LinearWarmup
+      start_factor: 0.001
+      steps: 2000
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/_base_/optimizer_400e.yml

+epoch: 400
+
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+    - name: CosineDecay
+      max_epochs: 480
+    - name: LinearWarmup
+      start_factor: 0.
+      epochs: 5
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/_base_/optimizer_60e.yml

+epoch: 60
+
+LearningRate:
+  base_lr: 0.001
+  schedulers:
+    - name: CosineDecay
+      max_epochs: 72
+    - name: LinearWarmup
+      start_factor: 0.
+      epochs: 1
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/_base_/optimizer_80e.yml

+epoch: 80
+
+LearningRate:
+  base_lr: 0.001
+  schedulers:
+    - name: CosineDecay
+      max_epochs: 96
+    - name: LinearWarmup
+      start_factor: 0.
+      epochs: 5
+
+OptimizerBuilder:
+  optimizer:
+    momentum: 0.9
+    type: Momentum
+  regularizer:
+    factor: 0.0005
+    type: L2

configs/ppyoloe/_base_/ppyoloe_crn.yml

+architecture: YOLOv3
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+ema_black_list: ['proj_conv.weight']
+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
+
+CustomCSPPAN:
+  out_channels: [768, 384, 192]
+  stage_num: 1
+  block_num: 3
+  act: 'swish'
+  spp: true
+
+PPYOLOEHead:
+  fpn_strides: [32, 16, 8]
+  grid_cell_scale: 5.0
+  grid_cell_offset: 0.5
+  static_assigner_epoch: 100
+  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: 1000
+    keep_top_k: 300
+    score_threshold: 0.01
+    nms_threshold: 0.7