paddleocr预训练模型加载问题

[H-eaven-1]

训练检测模型的过程中，加载MobileNetV3_large_x1_0_pretrained.pdparams模型时出错,显示类似下面的问题 [2023/04/19 14:37:51] ppocr WARNING: The pretrained params conv1.conv.weight not in model [2023/04/19 14:37:51] ppocr WARNING: The pretrained params conv1.bn.weight not in model [2023/04/19 14:37:51] ppocr WARNING: The pretrained params conv1.bn.bias not in model [2023/04/19 14:37:51] ppocr WARNING: The pretrained params conv1.bn._mean not in model [2023/04/19 14:37:51] ppocr WARNING: The pretrained params conv1.bn._variance not in model

配置文件如下： Global: use_gpu: true use_xpu: false use_mlu: false epoch_num: 300 log_smooth_window: 20 print_batch_step: 30 save_model_dir: E:/output/db_mv3 save_epoch_step: 40 eval_batch_step: [0, 500] cal_metric_during_train: False
pretrained_model: E:/pretrain_models/MobileNetV3_large_x1_0_pretrained checkpoints: save_inference_dir: use_visualdl: True infer_img: doc/imgs_en/img_10.jpg save_res_path: ./output/det_db/predicts_db.txt

Architecture: model_type: det algorithm: DB Transform: Backbone: name: MobileNetV3 scale: 1.0 model_name: large Neck: name: DBFPN out_channels: 256 Head: name: DBHead k: 50

Loss: name: DBLoss balance_loss: true main_loss_type: DiceLoss alpha: 5 beta: 10 ohem_ratio: 3

Optimizer: name: Adam beta1: 0.9 beta2: 0.999 lr: learning_rate: 0.001 regularizer: name: 'L2' factor: 0

PostProcess: name: DBPostProcess thresh: 0.3 box_thresh: 0.6 max_candidates: 1000 unclip_ratio: 1.5

Metric: name: DetMetric main_indicator: hmean

Train: dataset: name: SimpleDataSet data_dir: E:/paddleocr_out/train_data/det/ label_file_list:

• E:/paddleocr_out/train_data/det/label.txt ratio_list: [1.0] transforms:
• DecodeImage: # load image img_mode: BGR channel_first: False
• DetLabelEncode: # Class handling label
• IaaAugment: augmenter_args:
  • { 'type': Fliplr, 'args': { 'p': 0.5 } }
  • { 'type': Affine, 'args': { 'rotate': [-10, 10] } }
  • { 'type': Resize, 'args': { 'size': [0.5, 3] } }
• EastRandomCropData: size: [640, 640] max_tries: 50 keep_ratio: true
• MakeBorderMap: shrink_ratio: 0.4 thresh_min: 0.3 thresh_max: 0.7
• MakeShrinkMap: shrink_ratio: 0.4 min_text_size: 8
• 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', 'threshold_map', 'threshold_mask', 'shrink_map', 'shrink_mask'] # the order of the dataloader list loader: shuffle: True drop_last: False batch_size_per_card: 8 num_workers: 1 use_shared_memory: True

Eval: dataset: name: SimpleDataSet data_dir: E:/paddleocr_out/train_data/det/ label_file_list:

• E:/paddleocr_out/train_data/det/label1.txt transforms:
• DecodeImage: # load image img_mode: BGR channel_first: False
• DetLabelEncode: # Class handling label
• DetResizeForTest: image_shape: [736, 1280]
• 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', 'shape', 'polys', 'ignore_tags'] loader: shuffle: False drop_last: False batch_size_per_card: 1 # must be 1 num_workers: 1 use_shared_memory: True

在backbone部分的选择和预训练模型是对应的，但是为什么会有参数匹配不上的问题呢

[raderqi]

我看他们官方出版的教程里也有这个warning，但是他们是能够正常训练下去的

[H-eaven-1]

我看他们官方出版的教程里也有这个warning，但是他们是能够正常训练下去的

能训练，但是预训练模型参数加载不进去，模型训练的时间会长一些，效果也不太好

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.