update person_attribute&text_direction configs

ppcls/configs/PULC/person_attribute/MobileNetV3_large_x1_0.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: "./output/"
+  device: "gpu"
+  save_interval: 5
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 20
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 256, 192]
+  save_inference_dir: "./inference"
+  use_multilabel: True
+
+# model architecture
+Arch:
+  name: "MobileNetV3_large_x1_0"
+  pretrained: True
+  class_num: 26
+
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+  Eval:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.01
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.0005
+  #clip_norm: 10
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_train_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - Padv2:
+            size: [212, 276]
+            pad_mode: 1
+            fill_value: 0
+        - RandomCropImage:
+            size: [192, 256]
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: True
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+  Eval:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_val_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+
+Metric:
+  Eval:
+    - ATTRMetric:
+
+

ppcls/configs/PULC/person_attribute/PPLCNet_x1_0.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: "./output/"
+  device: "gpu"
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 256, 192]
+  save_inference_dir: "./inference"
+  use_multilabel: True
+
+# model architecture
+Arch:
+  name: "PPLCNet_x1_0"
+  pretrained: True
+  use_ssld: True
+  class_num: 26
+  
+
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+  Eval:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.01
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.0005
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_train_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - TimmAutoAugment:
+            prob: 0.8
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: [192, 256]
+        - Padv2:
+            size: [212, 276]
+            pad_mode: 1
+            fill_value: 0
+        - RandomCropImage:
+            size: [192, 256]
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.4
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: True
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+  Eval:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_val_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+
+Metric:
+  Eval:
+    - ATTRMetric:
+
+

ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_Distillation.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  start_eval_epoch: 1
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+  use_dali: False
+  use_multilabel: True
+
+# model architecture
+Arch:
+  name: "DistillationModel"
+  class_num: &class_num 26
+  # if not null, its lengths should be same as models
+  pretrained_list:
+  # if not null, its lengths should be same as models
+  freeze_params_list:
+  - True
+  - False
+  use_sync_bn: True
+  models:
+    - Teacher:
+        name: ResNet101_vd
+        class_num: *class_num
+    - Student:
+        name: PPLCNet_x1_0
+        class_num: *class_num
+        pretrained: True
+        use_ssld: True
+
+  infer_model_name: "Student"
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - DistillationDMLLoss:
+        weight: 1.0
+        model_name_pairs:
+        - ["Student", "Teacher"]
+    - DistillationMultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        model_names: ["Student"]
+        size_sum: True
+  Eval:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.01
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.0005
+
+
+# data loader for train and eval
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/train_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - TimmAutoAugment:
+            prob: 0.0
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: [192, 256]
+        - Padv2:
+            size: [212, 276]
+            pad_mode: 1
+            fill_value: 0
+        - RandomCropImage:
+            size: [192, 256]
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.0
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: True
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+  Eval:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_val_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+
+
+Metric:
+  Eval:
+    - ATTRMetric:

ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_search.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: "./output/"
+  device: "gpu"
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 256, 192]
+  save_inference_dir: "./inference"
+  use_multilabel: True
+
+# model architecture
+Arch:
+  name: "PPLCNet_x1_0"
+  pretrained: True
+  use_ssld: True
+  class_num: 26
+  
+
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+  Eval:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.01
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.0005
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_train_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - TimmAutoAugment:
+            prob: 0.0
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: [192, 256]
+        - Padv2:
+            size: [212, 276]
+            pad_mode: 1
+            fill_value: 0
+        - RandomCropImage:
+            size: [192, 256]
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.0
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: True
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+  Eval:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_val_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+
+Metric:
+  Eval:
+    - ATTRMetric:
+
+

ppcls/configs/PULC/person_attribute/Res2Net200_vd_26w_4s.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: "./output/"
+  device: "gpu"
+  save_interval: 5
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 20
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 256, 192]
+  save_inference_dir: "./inference"
+  use_multilabel: True
+
+# model architecture
+Arch:
+  name: "Res2Net200_vd_26w_4s"
+  pretrained: True
+  class_num: 26
+
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+  Eval:
+    - MultiLabelLoss:
+        weight: 1.0
+        weight_ratio: True
+        size_sum: True
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.01
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.0005
+  #clip_norm: 10
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_train_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - Padv2:
+            size: [212, 276]
+            pad_mode: 1
+            fill_value: 0
+        - RandomCropImage:
+            size: [192, 256]
+        - RandFlipImage:
+            flip_code: 1
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: True
+      shuffle: True
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+  Eval:
+    dataset:
+      name: MultiLabelDataset
+      image_root: "dataset/attribute/data/"
+      cls_label_path: "dataset/attribute/pa100k_val_list.txt"
+      label_ratio: True
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 256]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+
+Metric:
+  Eval:
+    - ATTRMetric:
+
+

ppcls/configs/PULC/person_attribute/search.yaml

+base_config_file: ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_search.yaml
+distill_config_file: ppcls/configs/PULC/person_attribute/PPLCNet_x1_0_Distillation.yaml
+
+gpus: 0,1,2,3
+output_dir: output/search_attr
+search_times: 1
+search_dict:
+  - search_key: lrs
+    replace_config:
+      - Optimizer.lr.learning_rate
+    search_values: [0.0001, 0.005, 0.01, 0.02, 0.05]
+  - search_key: resolutions
+    replace_config:
+      - DataLoader.Train.dataset.transform_ops.1.ResizeImage.size
+      - DataLoader.Train.dataset.transform_ops.4.RandomCropImage.size
+      - DataLoader.Train.dataset.transform_ops.2.TimmAutoAugment.img_size
+    search_values: [[192, 256]]
+  - search_key: ra_probs
+    replace_config:
+      - DataLoader.Train.dataset.transform_ops.2.TimmAutoAugment.prob
+    search_values: [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
+  - search_key: re_probs
+    replace_config:
+      - DataLoader.Train.dataset.transform_ops.7.RandomErasing.EPSILON
+    search_values: [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
+  - search_key: lr_mult_list
+    replace_config:
+      - Arch.lr_mult_list
+    search_values:
+      - [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
+      - [0.0, 0.4, 0.4, 0.8, 0.8, 1.0]
+      - [1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
+teacher:
+  rm_keys:
+    - Arch.lr_mult_list
+  search_values:
+    - ResNet101_vd
+    - ResNet50_vd
+final_replace:
+  Arch.lr_mult_list: Arch.models.1.Student.lr_mult_list
+

ppcls/configs/PULC/text_direction/MobileNetV3_large_x1_0.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  start_eval_epoch: 18
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+  use_dali: False
+
+# model architecture
+Arch:
+  name: MobileNetV3_large_x1_0
+  class_num: 2
+  pretrained: True
+  use_sync_bn: True
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+        epsilon: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.13
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.00002
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 512
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 8
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 4
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 2]
+  Eval:
+    - TopkAcc:
+        topk: [1, 2]

ppcls/configs/PULC/text_direction/PPLCNet_x1_0.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  start_eval_epoch: 18
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 80, 160]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+  use_dali: False
+
+# model architecture
+Arch:
+  name: PPLCNet_x1_0
+  class_num: 2
+  pretrained: True
+  use_ssld: True
+  stride_list: [2, [2, 1], [2, 1], [2, 1], [2, 1]]
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.8
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.00004
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [160, 80]
+        - TimmAutoAugment:
+            prob: 1.0
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: [160, 80]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.0
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 256
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 16
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [160, 80]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 8
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        size: [160, 80]
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 2]
+  Eval:
+    - TopkAcc:
+        topk: [1, 2]

ppcls/configs/PULC/text_direction/PPLCNet_x1_0_distillation.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  start_eval_epoch: 18
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 80, 160]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+  use_dali: False
+
+# model architecture
+Arch:
+  name: "DistillationModel"
+  class_num: &class_num 2
+  # if not null, its lengths should be same as models
+  pretrained_list:
+  # if not null, its lengths should be same as models
+  freeze_params_list:
+  - True
+  - False
+  use_sync_bn: True
+  models:
+    - Teacher:
+        name: ResNet101_vd
+        class_num: *class_num
+        stride_list: [2, [2, 1], [2, 1], [2, 1], [2, 1]]
+    - Student:
+        name: PPLCNet_x1_0
+        class_num: *class_num
+        stride_list: [2, [2, 1], [2, 1], [2, 1], [2, 1]]
+        pretrained: True
+        use_ssld: True
+
+  infer_model_name: "Student"
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - DistillationDMLLoss:
+        weight: 1.0
+        model_name_pairs:
+        - ["Student", "Teacher"]
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.8
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.00004
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [160, 80]
+        - TimmAutoAugment:
+            prob: 1.0
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: [160, 80]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.0
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 256
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 16
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [160, 80]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 8
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        size: [160, 80]
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+    Train:
+    - DistillationTopkAcc:
+        model_key: "Student"
+        topk: [1, 2]
+    Eval:
+    - TopkAcc:
+        topk: [1, 2]

ppcls/configs/PULC/text_direction/PPLCNet_x1_0_search.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  start_eval_epoch: 18
+  eval_interval: 1
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 48, 192]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+  use_dali: False
+
+# model architecture
+Arch:
+  name: PPLCNet_x1_0
+  class_num: 2
+  pretrained: True
+  use_ssld: True
+  stride_list: [2, [2, 1], [2, 1], [2, 1], [2, 1]]
+  
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Cosine
+    learning_rate: 0.5
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    coeff: 0.00004
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 48]
+        - TimmAutoAugment:
+            prob: 0.0
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: [192, 48]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.0
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 256
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 16
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            size: [192, 48]
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 8
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        size: [192, 48]
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 2]
+  Eval:
+    - TopkAcc:
+        topk: [1, 2]

ppcls/configs/PULC/text_direction/SwinTransformer_tiny_patch4_window7_224.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: ./output/
+  device: gpu
+  save_interval: 1
+  eval_during_train: True
+  eval_interval: 1
+  start_eval_epoch: 10
+  epochs: 20
+  print_batch_step: 10
+  use_visualdl: False
+  # used for static mode and model export
+  image_shape: [3, 224, 224]
+  save_inference_dir: ./inference
+  # training model under @to_static
+  to_static: False
+  use_dali: False
+
+# mixed precision training
+AMP:
+  scale_loss: 128.0
+  use_dynamic_loss_scaling: True
+  # O1: mixed fp16
+  level: O1
+
+# model architecture
+Arch:
+  name: SwinTransformer_tiny_patch4_window7_224
+  class_num: 2
+  pretrained: True
+ 
+# loss function config for traing/eval process
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+        epsilon: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  epsilon: 1e-8
+  weight_decay: 0.05
+  no_weight_decay_name: absolute_pos_embed relative_position_bias_table .bias norm
+  one_dim_param_no_weight_decay: True
+  lr:
+    name: Cosine
+    learning_rate: 1e-4
+    eta_min: 2e-6
+    warmup_epoch: 5
+    warmup_start_lr: 2e-7
+
+
+# data loader for train and eval
+DataLoader:
+  Train:
+    dataset:
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/train_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - RandCropImage:
+            size: 224
+            interpolation: bicubic
+            backend: pil
+        - TimmAutoAugment:
+            config_str: rand-m9-mstd0.5-inc1
+            interpolation: bicubic
+            img_size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+        - RandomErasing:
+            EPSILON: 0.25
+            sl: 0.02
+            sh: 1.0/3.0
+            r1: 0.3
+            attempt: 10
+            use_log_aspect: True
+            mode: pixel
+      batch_transform_ops:
+        - OpSampler:
+            MixupOperator:
+              alpha: 0.8
+              prob: 0.5
+            CutmixOperator:
+              alpha: 1.0
+              prob: 0.5
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 128
+      drop_last: False
+      shuffle: True
+    loader:
+      num_workers: 8
+      use_shared_memory: True
+
+  Eval:
+    dataset: 
+      name: ImageNetDataset
+      image_root: ./dataset/text_direction/
+      cls_label_path: ./dataset/text_direction/val_list.txt
+      transform_ops:
+        - DecodeImage:
+            to_rgb: True
+            channel_first: False
+        - ResizeImage:
+            resize_short: 256
+        - CropImage:
+            size: 224
+        - NormalizeImage:
+            scale: 1.0/255.0
+            mean: [0.485, 0.456, 0.406]
+            std: [0.229, 0.224, 0.225]
+            order: ''
+    sampler:
+      name: DistributedBatchSampler
+      batch_size: 64
+      drop_last: False
+      shuffle: False
+    loader:
+      num_workers: 8
+      use_shared_memory: True
+
+Infer:
+  infer_imgs: docs/images/inference_deployment/whl_demo.jpg
+  batch_size: 10
+  transforms:
+    - DecodeImage:
+        to_rgb: True
+        channel_first: False
+    - ResizeImage:
+        resize_short: 256
+    - CropImage:
+        size: 224
+    - NormalizeImage:
+        scale: 1.0/255.0
+        mean: [0.485, 0.456, 0.406]
+        std: [0.229, 0.224, 0.225]
+        order: ''
+    - ToCHWImage:
+  PostProcess:
+    name: Topk
+    topk: 5
+    class_id_map_file: ppcls/utils/imagenet1k_label_list.txt
+
+Metric:
+  Train:
+    - TopkAcc:
+        topk: [1, 2]
+  Eval:
+    - TopkAcc:
+        topk: [1, 2]

ppcls/configs/PULC/text_direction/search.yaml

+base_config_file: ppcls/configs/PULC/text_direction/PPLCNet_x1_0.yaml
+distill_config_file: ppcls/configs/PULC/text_direction/PPLCNet_x1_0_distillation.yaml
+
+gpus: 0,1,2,3
+output_dir: output/search_text
+search_times: 1
+search_dict:
+  - search_key: lrs
+    replace_config:
+      - Optimizer.lr.learning_rate
+    search_values: [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]
+  - search_key: resolutions
+    replace_config:
+      - DataLoader.Train.dataset.transform_ops.1.ResizeImage.size
+      - DataLoader.Train.dataset.transform_ops.2.TimmAutoAugment.img_size
+      - DataLoader.Eval.dataset.transform_ops.1.ResizeImage.size
+    search_values: [[192, 48], [180, 60], [160, 80]]
+  - search_key: ra_probs
+    replace_config:
+      - DataLoader.Train.dataset.transform_ops.2.TimmAutoAugment.prob
+    search_values: [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
+  - search_key: re_probs
+    replace_config:
+      - DataLoader.Train.dataset.transform_ops.4.RandomErasing.EPSILON
+    search_values: [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
+  - search_key: lr_mult_list
+    replace_config:
+      - Arch.lr_mult_list
+    search_values:
+      - [0.0, 0.2, 0.4, 0.6, 0.8, 1.0]
+      - [0.0, 0.4, 0.4, 0.8, 0.8, 1.0]
+      - [1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
+teacher:
+  rm_keys:
+    - Arch.lr_mult_list
+  search_values:
+    - ResNet101_vd
+    - ResNet50_vd
+final_replace:
+  Arch.lr_mult_list: Arch.models.1.Student.lr_mult_list
+