add ppyoloe 36 epoch yaml for xpu. (#5739)

* add ppyoloe 36 epoch yaml for xpu.

* update device and lr.

* fix device.

* fix eval_input_size

configs/ppyoloe/_base_/optimizer_36e_xpu.yml

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

configs/ppyoloe/ppyoloe_crn_l_36e_coco_xpu.yml

+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/optimizer_36e_xpu.yml',
+  './_base_/ppyoloe_reader.yml',
+]
+
+# note: these are default values (use_gpu = true and use_xpu = false) for CI.
+# set use_gpu = false and use_xpu = true for training.
+use_gpu: true
+use_xpu: false
+
+log_iter: 100
+snapshot_epoch: 1
+weights: output/ppyoloe_crn_l_36e_coco/model_final
+find_unused_parameters: True
+
+pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/CSPResNetb_l_pretrained.pdparams
+depth_mult: 1.0
+width_mult: 1.0
+
+TrainReader:
+  batch_size: 8
+
+architecture: YOLOv3
+norm_type: sync_bn
+use_ema: true
+ema_decay: 0.9998
+
+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: 4
+  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: 100
+    score_threshold: 0.01
+    nms_threshold: 0.6