FCENet 训练无法修改eval间隔

[Enchanted0911]

• 系统环境/System Environment：linux
• 版本号/Version：Paddle：2.3.0 PaddleOCR：2.6.0 问题相关组件/Related components：检测模型FCE 以下是我的配置，不论我如何设置 'eval_batch_step' 训练总是在每次epoch结束就eval。希望得到解答！

  
  Global:
  use_gpu: true
  epoch_num: 500
  log_smooth_window: 20
  print_batch_step: 20
  save_model_dir: ./output/det_r50_dcn_fce/
  save_epoch_step: 25
  # evaluation is run every 835 iterations
  eval_batch_step: [0, 835]
  cal_metric_during_train: False
  pretrained_model: ./pretrain_models/ResNet50_vd_ssld_pretrained 
  checkpoints: 
  save_inference_dir: 
  use_visualdl: False
  infer_img: doc/imgs_en/img_10.jpg
  save_res_path: ./output/det_fce/predicts_fce.txt

Architecture: model_type: det algorithm: FCE Transform: Backbone: name: ResNet_vd layers: 50 dcn_stage: [False, True, True, True] out_indices: [1,2,3] Neck: name: FCEFPN out_channels: 256 has_extra_convs: False extra_stage: 0 Head: name: FCEHead fourier_degree: 5 Loss: name: FCELoss fourier_degree: 5 num_sample: 50

Optimizer: name: Adam beta1: 0.9 beta2: 0.999 lr: learning_rate: 0.0001 regularizer: name: 'L2' factor: 0

PostProcess: name: FCEPostProcess scales: [8, 16, 32] alpha: 1.0 beta: 1.0 fourier_degree: 5 box_type: 'poly'

Metric: name: DetFCEMetric main_indicator: hmean

Train: dataset: name: SimpleDataSet data_dir: ./dataset/ label_file_list:

• ./dataset/Label.txt transforms:
• DecodeImage: # load image img_mode: BGR channel_first: False ignore_orientation: True
• DetLabelEncode: # Class handling label
• ColorJitter: brightness: 0.142 saturation: 0.5 contrast: 0.5
• RandomScaling:
• RandomCropFlip: crop_ratio: 0.5
• RandomCropPolyInstances: crop_ratio: 0.8 min_side_ratio: 0.3
• RandomRotatePolyInstances: rotate_ratio: 0.5 max_angle: 30 pad_with_fixed_color: False
• SquareResizePad: target_size: 800 pad_ratio: 0.6
• IaaAugment: augmenter_args:
  • { 'type': Fliplr, 'args': { 'p': 0.5 } }
• FCENetTargets: fourier_degree: 5
• NormalizeImage: scale: 1./255. mean: [0.485, 0.456, 0.406] std: [0.229, 0.224, 0.225] order: 'hwc'
• ToCHWImage:
• KeepKeys: keep_keys: ['image', 'p3_maps', 'p4_maps', 'p5_maps'] # dataloader will return list in this order loader: shuffle: True drop_last: False batch_size_per_card: 6 num_workers: 8

Eval: dataset: name: SimpleDataSet data_dir: ./dataset/ label_file_list:

• ./dataset/Label_eval.txt transforms:
• DecodeImage: # load image img_mode: BGR channel_first: False ignore_orientation: True
• DetLabelEncode: # Class handling label
• DetResizeForTest: limit_type: 'min' limit_side_len: 736
• NormalizeImage: scale: 1./255. mean: [0.485, 0.456, 0.406] std: [0.229, 0.224, 0.225] order: 'hwc'
• Pad:
• ToCHWImage:
• KeepKeys: keep_keys: ['image', 'shape', 'polys', 'ignore_tags'] loader: shuffle: False drop_last: False batch_size_per_card: 1 # must be 1 num_workers: 2

[WenmuZhou]

方便再eval之前打印一下 global_step ，start_eval_step， eval_batch_step吗，https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.6/tools/program.py#L380

[Enchanted0911]

方便再eval之前打印一下 global_step ，start_eval_step， eval_batch_step吗，https://github.com/PaddlePaddle/PaddleOCR/blob/release%2F2.6/tools/program.py#L380

好的，不过模型每次启动训练打印的日志都是每 835 次eval，这个值固定的。