登录
注册
开源
企业版
高校版
搜索
帮助中心
使用条款
关于我们
开源
企业版
高校版
私有云
模力方舟
登录
注册
代码拉取完成，页面将自动刷新
开源项目
>
人工智能
>
计算机视觉/人脸识别
&&
捐赠
捐赠前请先登录
取消
前往登录
扫描微信二维码支付
取消
支付完成
支付提示
将跳转至支付宝完成支付
确定
取消
Watch
不关注
关注所有动态
仅关注版本发行动态
关注但不提醒动态
507
Star
4.1K
Fork
1.1K
GVP
PaddlePaddle
/
PaddleOCR
代码
Issues
227
Pull Requests
7
Wiki
统计
流水线
服务
质量分析
Jenkins for Gitee
腾讯云托管
腾讯云 Serverless
悬镜安全
阿里云 SAE
Codeblitz
SBOM
我知道了，不再自动展开
更新失败，请稍后重试！
移除标识
内容风险标识
本任务被
标识为内容中包含有代码安全 Bug 、隐私泄露等敏感信息，仓库外成员不可访问
RE训练 报错
待办的
#I9AZ88
LuckWang2019
创建于
2024-03-23 16:29
Connected to pydev debugger (build 233.14475.56) [2024/03/23 16:28:13] ppocr INFO: Architecture : [2024/03/23 16:28:13] ppocr INFO: Backbone : [2024/03/23 16:28:13] ppocr INFO: checkpoints : None [2024/03/23 16:28:13] ppocr INFO: mode : vi [2024/03/23 16:28:13] ppocr INFO: name : LayoutXLMForRe [2024/03/23 16:28:13] ppocr INFO: pretrained : True [2024/03/23 16:28:13] ppocr INFO: Transform : None [2024/03/23 16:28:13] ppocr INFO: algorithm : LayoutXLM [2024/03/23 16:28:13] ppocr INFO: model_type : kie [2024/03/23 16:28:13] ppocr INFO: Eval : [2024/03/23 16:28:13] ppocr INFO: dataset : [2024/03/23 16:28:13] ppocr INFO: data_dir : train_data/XFUND/zh_val/image [2024/03/23 16:28:13] ppocr INFO: label_file_list : ['train_data/XFUND/zh_val/val.json'] [2024/03/23 16:28:13] ppocr INFO: name : SimpleDataSet [2024/03/23 16:28:13] ppocr INFO: transforms : [2024/03/23 16:28:13] ppocr INFO: DecodeImage : [2024/03/23 16:28:13] ppocr INFO: channel_first : False [2024/03/23 16:28:13] ppocr INFO: img_mode : RGB [2024/03/23 16:28:13] ppocr INFO: VQATokenLabelEncode : [2024/03/23 16:28:13] ppocr INFO: algorithm : LayoutXLM [2024/03/23 16:28:13] ppocr INFO: class_path : train_data/XFUND/class_list_xfun.txt [2024/03/23 16:28:13] ppocr INFO: contains_re : True [2024/03/23 16:28:13] ppocr INFO: order_method : tb-yx [2024/03/23 16:28:13] ppocr INFO: use_textline_bbox_info : True [2024/03/23 16:28:13] ppocr INFO: VQATokenPad : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: return_attention_mask : True [2024/03/23 16:28:13] ppocr INFO: VQAReTokenRelation : None [2024/03/23 16:28:13] ppocr INFO: VQAReTokenChunk : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: TensorizeEntitiesRelations : None [2024/03/23 16:28:13] ppocr INFO: Resize : [2024/03/23 16:28:13] ppocr INFO: size : [224, 224] [2024/03/23 16:28:13] ppocr INFO: NormalizeImage : [2024/03/23 16:28:13] ppocr INFO: mean : [123.675, 116.28, 103.53] [2024/03/23 16:28:13] ppocr INFO: order : hwc [2024/03/23 16:28:13] ppocr INFO: scale : 1 [2024/03/23 16:28:13] ppocr INFO: std : [58.395, 57.12, 57.375] [2024/03/23 16:28:13] ppocr INFO: ToCHWImage : None [2024/03/23 16:28:13] ppocr INFO: KeepKeys : [2024/03/23 16:28:13] ppocr INFO: keep_keys : ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'entities', 'relations'] [2024/03/23 16:28:13] ppocr INFO: loader : [2024/03/23 16:28:13] ppocr INFO: batch_size_per_card : 8 [2024/03/23 16:28:13] ppocr INFO: drop_last : False [2024/03/23 16:28:13] ppocr INFO: num_workers : 1 [2024/03/23 16:28:13] ppocr INFO: shuffle : False [2024/03/23 16:28:13] ppocr INFO: Global : [2024/03/23 16:28:13] ppocr INFO: cal_metric_during_train : False [2024/03/23 16:28:13] ppocr INFO: distributed : False [2024/03/23 16:28:13] ppocr INFO: epoch_num : 130 [2024/03/23 16:28:13] ppocr INFO: eval_batch_step : [0, 19] [2024/03/23 16:28:13] ppocr INFO: infer_img : ppstructure/docs/kie/input/zh_val_21.jpg [2024/03/23 16:28:13] ppocr INFO: kie_det_model_dir : None [2024/03/23 16:28:13] ppocr INFO: kie_rec_model_dir : None [2024/03/23 16:28:13] ppocr INFO: log_smooth_window : 10 [2024/03/23 16:28:13] ppocr INFO: print_batch_step : 10 [2024/03/23 16:28:13] ppocr INFO: save_epoch_step : 20 [2024/03/23 16:28:13] ppocr INFO: save_inference_dir : None [2024/03/23 16:28:13] ppocr INFO: save_model_dir : D:/demo/PaddleOCR/output/re_vi_layoutxlm_xfund_zh [2024/03/23 16:28:13] ppocr INFO: save_res_path : ./output/re/xfund_zh/with_gt [2024/03/23 16:28:13] ppocr INFO: seed : 2022 [2024/03/23 16:28:13] ppocr INFO: use_gpu : True [2024/03/23 16:28:13] ppocr INFO: use_visualdl : True [2024/03/23 16:28:13] ppocr INFO: Loss : [2024/03/23 16:28:13] ppocr INFO: key : loss [2024/03/23 16:28:13] ppocr INFO: name : LossFromOutput [2024/03/23 16:28:13] ppocr INFO: reduction : mean [2024/03/23 16:28:13] ppocr INFO: Metric : [2024/03/23 16:28:13] ppocr INFO: main_indicator : hmean [2024/03/23 16:28:13] ppocr INFO: name : VQAReTokenMetric [2024/03/23 16:28:13] ppocr INFO: Optimizer : [2024/03/23 16:28:13] ppocr INFO: beta1 : 0.9 [2024/03/23 16:28:13] ppocr INFO: beta2 : 0.999 [2024/03/23 16:28:13] ppocr INFO: clip_norm : 10 [2024/03/23 16:28:13] ppocr INFO: lr : [2024/03/23 16:28:13] ppocr INFO: learning_rate : 5e-05 [2024/03/23 16:28:13] ppocr INFO: warmup_epoch : 10 [2024/03/23 16:28:13] ppocr INFO: name : AdamW [2024/03/23 16:28:13] ppocr INFO: regularizer : [2024/03/23 16:28:13] ppocr INFO: factor : 0.0 [2024/03/23 16:28:13] ppocr INFO: name : L2 [2024/03/23 16:28:13] ppocr INFO: PostProcess : [2024/03/23 16:28:13] ppocr INFO: name : VQAReTokenLayoutLMPostProcess [2024/03/23 16:28:13] ppocr INFO: Train : [2024/03/23 16:28:13] ppocr INFO: dataset : [2024/03/23 16:28:13] ppocr INFO: data_dir : train_data/XFUND/zh_train/image [2024/03/23 16:28:13] ppocr INFO: label_file_list : ['train_data/XFUND/zh_train/train.json'] [2024/03/23 16:28:13] ppocr INFO: name : SimpleDataSet [2024/03/23 16:28:13] ppocr INFO: ratio_list : [1.0] [2024/03/23 16:28:13] ppocr INFO: transforms : [2024/03/23 16:28:13] ppocr INFO: DecodeImage : [2024/03/23 16:28:13] ppocr INFO: channel_first : False [2024/03/23 16:28:13] ppocr INFO: img_mode : RGB [2024/03/23 16:28:13] ppocr INFO: VQATokenLabelEncode : [2024/03/23 16:28:13] ppocr INFO: algorithm : LayoutXLM [2024/03/23 16:28:13] ppocr INFO: class_path : train_data/XFUND/class_list_xfun.txt [2024/03/23 16:28:13] ppocr INFO: contains_re : True [2024/03/23 16:28:13] ppocr INFO: order_method : tb-yx [2024/03/23 16:28:13] ppocr INFO: use_textline_bbox_info : True [2024/03/23 16:28:13] ppocr INFO: VQATokenPad : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: return_attention_mask : True [2024/03/23 16:28:13] ppocr INFO: VQAReTokenRelation : None [2024/03/23 16:28:13] ppocr INFO: VQAReTokenChunk : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: TensorizeEntitiesRelations : None [2024/03/23 16:28:13] ppocr INFO: Resize : [2024/03/23 16:28:13] ppocr INFO: size : [224, 224] [2024/03/23 16:28:13] ppocr INFO: NormalizeImage : [2024/03/23 16:28:13] ppocr INFO: mean : [123.675, 116.28, 103.53] [2024/03/23 16:28:13] ppocr INFO: order : hwc [2024/03/23 16:28:13] ppocr INFO: scale : 1 [2024/03/23 16:28:13] ppocr INFO: std : [58.395, 57.12, 57.375] [2024/03/23 16:28:13] ppocr INFO: ToCHWImage : None [2024/03/23 16:28:13] ppocr INFO: KeepKeys : [2024/03/23 16:28:13] ppocr INFO: keep_keys : ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'entities', 'relations'] [2024/03/23 16:28:13] ppocr INFO: loader : [2024/03/23 16:28:13] ppocr INFO: batch_size_per_card : 2 [2024/03/23 16:28:13] ppocr INFO: drop_last : False [2024/03/23 16:28:13] ppocr INFO: num_workers : 1 [2024/03/23 16:28:13] ppocr INFO: shuffle : True [2024/03/23 16:28:13] ppocr INFO: profiler_options : None [2024/03/23 16:28:13] ppocr INFO: train with paddle 2.6.0 and device Place(gpu:0) [2024/03/23 16:28:22] ppocr INFO: Initialize indexs of datasets:['D:/demo/PaddleOCR/train_data/XFUND/zh_train/train.json'] list index out of range [2024-03-23 16:28:22,741] [ INFO] - Already cached D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\sentencepiece.bpe.model [2024-03-23 16:28:23,121] [ INFO] - tokenizer config file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\tokenizer_config.json [2024-03-23 16:28:23,121] [ INFO] - Special tokens file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\special_tokens_map.json [2024-03-23 16:28:23,124] [ INFO] - Already cached D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\sentencepiece.bpe.model [2024/03/23 16:28:23] ppocr INFO: Initialize indexs of datasets:['D:/demo/PaddleOCR/train_data/XFUND/zh_val/val.json'] [2024-03-23 16:28:23,429] [ INFO] - tokenizer config file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\tokenizer_config.json [2024-03-23 16:28:23,429] [ INFO] - Special tokens file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\special_tokens_map.json [2024-03-23 16:28:23,441] [ INFO] - Loading configuration file D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy\config.json [2024-03-23 16:28:23,442] [ INFO] - Loading weights file D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy\model_state.pdparams [2024-03-23 16:28:24,118] [ INFO] - Loaded weights file from disk, setting weights to model. W0323 16:28:24.221403 20396 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.9, Driver API Version: 12.3, Runtime API Version: 12.0 W0323 16:28:24.234532 20396 gpu_resources.cc:164] device: 0, cuDNN Version: 8.9. [2024-03-23 16:28:25,251] [ INFO] - All model checkpoint weights were used when initializing LayoutXLMForRelationExtraction. [2024-03-23 16:28:25,251] [ INFO] - All the weights of LayoutXLMForRelationExtraction were initialized from the model checkpoint at D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy. If your task is similar to the task the model of the checkpoint was trained on, you can already use LayoutXLMForRelationExtraction for predictions without further training. [2024/03/23 16:28:25] ppocr INFO: train dataloader has 75 iters [2024/03/23 16:28:25] ppocr INFO: valid dataloader has 7 iters [2024/03/23 16:28:25] ppocr INFO: resume from D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy [2024/03/23 16:28:25] ppocr WARNING: D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy.pdopt is not exists, params of optimizer is not loaded [2024/03/23 16:28:25] ppocr INFO: During the training process, after the 0th iteration, an evaluation is run every 19 iterations Traceback (most recent call last): File "C:\PyCharm Community Edition 2023.3.4\plugins\python-ce\helpers\pydev\pydevd.py", line 1534, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "C:\PyCharm Community Edition 2023.3.4\plugins\python-ce\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "D:\demo\PaddleOCR\tools\train.py", line 451, in <module> re_main_train() File "D:\demo\PaddleOCR\tools\train.py", line 435, in re_main_train main(config, device, logger, vdl_writer) File "D:\demo\PaddleOCR\tools\train.py", line 199, in main program.train(config, train_dataloader, valid_dataloader, device, model, File "D:\demo\PaddleOCR\tools\program.py", line 304, in train preds = model(batch) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\ppocr\modeling\architectures\base_model.py", line 86, in forward x = self.backbone(x) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\ppocr\modeling\backbones\vqa_layoutlm.py", line 227, in forward x = self.model( File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\paddlenlp\transformers\layoutxlm\modeling.py", line 1331, in forward loss, pred_relations = self.extractor(sequence_output, entities, relations) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\paddlenlp\transformers\layoutxlm\modeling.py", line 1225, in forward relations, entities = self.build_relation(relations, entities) File "D:\demo\PaddleOCR\paddlenlp\transformers\layoutxlm\modeling.py", line 1198, in build_relation relation_per_doc = paddle.concat([reordered_relations, relation_per_doc_label], axis=1) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\tensor\manipulation.py", line 1263, in concat return _C_ops.concat(input, axis) ValueError: (InvalidArgument) concat(): argument 'x' (position 0) must be list of Tensors, but got empty list (at ..\paddle\fluid\pybind\eager_utils.cc:1383) 好像更新之后就报错了，不知道如何解决？
Connected to pydev debugger (build 233.14475.56) [2024/03/23 16:28:13] ppocr INFO: Architecture : [2024/03/23 16:28:13] ppocr INFO: Backbone : [2024/03/23 16:28:13] ppocr INFO: checkpoints : None [2024/03/23 16:28:13] ppocr INFO: mode : vi [2024/03/23 16:28:13] ppocr INFO: name : LayoutXLMForRe [2024/03/23 16:28:13] ppocr INFO: pretrained : True [2024/03/23 16:28:13] ppocr INFO: Transform : None [2024/03/23 16:28:13] ppocr INFO: algorithm : LayoutXLM [2024/03/23 16:28:13] ppocr INFO: model_type : kie [2024/03/23 16:28:13] ppocr INFO: Eval : [2024/03/23 16:28:13] ppocr INFO: dataset : [2024/03/23 16:28:13] ppocr INFO: data_dir : train_data/XFUND/zh_val/image [2024/03/23 16:28:13] ppocr INFO: label_file_list : ['train_data/XFUND/zh_val/val.json'] [2024/03/23 16:28:13] ppocr INFO: name : SimpleDataSet [2024/03/23 16:28:13] ppocr INFO: transforms : [2024/03/23 16:28:13] ppocr INFO: DecodeImage : [2024/03/23 16:28:13] ppocr INFO: channel_first : False [2024/03/23 16:28:13] ppocr INFO: img_mode : RGB [2024/03/23 16:28:13] ppocr INFO: VQATokenLabelEncode : [2024/03/23 16:28:13] ppocr INFO: algorithm : LayoutXLM [2024/03/23 16:28:13] ppocr INFO: class_path : train_data/XFUND/class_list_xfun.txt [2024/03/23 16:28:13] ppocr INFO: contains_re : True [2024/03/23 16:28:13] ppocr INFO: order_method : tb-yx [2024/03/23 16:28:13] ppocr INFO: use_textline_bbox_info : True [2024/03/23 16:28:13] ppocr INFO: VQATokenPad : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: return_attention_mask : True [2024/03/23 16:28:13] ppocr INFO: VQAReTokenRelation : None [2024/03/23 16:28:13] ppocr INFO: VQAReTokenChunk : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: TensorizeEntitiesRelations : None [2024/03/23 16:28:13] ppocr INFO: Resize : [2024/03/23 16:28:13] ppocr INFO: size : [224, 224] [2024/03/23 16:28:13] ppocr INFO: NormalizeImage : [2024/03/23 16:28:13] ppocr INFO: mean : [123.675, 116.28, 103.53] [2024/03/23 16:28:13] ppocr INFO: order : hwc [2024/03/23 16:28:13] ppocr INFO: scale : 1 [2024/03/23 16:28:13] ppocr INFO: std : [58.395, 57.12, 57.375] [2024/03/23 16:28:13] ppocr INFO: ToCHWImage : None [2024/03/23 16:28:13] ppocr INFO: KeepKeys : [2024/03/23 16:28:13] ppocr INFO: keep_keys : ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'entities', 'relations'] [2024/03/23 16:28:13] ppocr INFO: loader : [2024/03/23 16:28:13] ppocr INFO: batch_size_per_card : 8 [2024/03/23 16:28:13] ppocr INFO: drop_last : False [2024/03/23 16:28:13] ppocr INFO: num_workers : 1 [2024/03/23 16:28:13] ppocr INFO: shuffle : False [2024/03/23 16:28:13] ppocr INFO: Global : [2024/03/23 16:28:13] ppocr INFO: cal_metric_during_train : False [2024/03/23 16:28:13] ppocr INFO: distributed : False [2024/03/23 16:28:13] ppocr INFO: epoch_num : 130 [2024/03/23 16:28:13] ppocr INFO: eval_batch_step : [0, 19] [2024/03/23 16:28:13] ppocr INFO: infer_img : ppstructure/docs/kie/input/zh_val_21.jpg [2024/03/23 16:28:13] ppocr INFO: kie_det_model_dir : None [2024/03/23 16:28:13] ppocr INFO: kie_rec_model_dir : None [2024/03/23 16:28:13] ppocr INFO: log_smooth_window : 10 [2024/03/23 16:28:13] ppocr INFO: print_batch_step : 10 [2024/03/23 16:28:13] ppocr INFO: save_epoch_step : 20 [2024/03/23 16:28:13] ppocr INFO: save_inference_dir : None [2024/03/23 16:28:13] ppocr INFO: save_model_dir : D:/demo/PaddleOCR/output/re_vi_layoutxlm_xfund_zh [2024/03/23 16:28:13] ppocr INFO: save_res_path : ./output/re/xfund_zh/with_gt [2024/03/23 16:28:13] ppocr INFO: seed : 2022 [2024/03/23 16:28:13] ppocr INFO: use_gpu : True [2024/03/23 16:28:13] ppocr INFO: use_visualdl : True [2024/03/23 16:28:13] ppocr INFO: Loss : [2024/03/23 16:28:13] ppocr INFO: key : loss [2024/03/23 16:28:13] ppocr INFO: name : LossFromOutput [2024/03/23 16:28:13] ppocr INFO: reduction : mean [2024/03/23 16:28:13] ppocr INFO: Metric : [2024/03/23 16:28:13] ppocr INFO: main_indicator : hmean [2024/03/23 16:28:13] ppocr INFO: name : VQAReTokenMetric [2024/03/23 16:28:13] ppocr INFO: Optimizer : [2024/03/23 16:28:13] ppocr INFO: beta1 : 0.9 [2024/03/23 16:28:13] ppocr INFO: beta2 : 0.999 [2024/03/23 16:28:13] ppocr INFO: clip_norm : 10 [2024/03/23 16:28:13] ppocr INFO: lr : [2024/03/23 16:28:13] ppocr INFO: learning_rate : 5e-05 [2024/03/23 16:28:13] ppocr INFO: warmup_epoch : 10 [2024/03/23 16:28:13] ppocr INFO: name : AdamW [2024/03/23 16:28:13] ppocr INFO: regularizer : [2024/03/23 16:28:13] ppocr INFO: factor : 0.0 [2024/03/23 16:28:13] ppocr INFO: name : L2 [2024/03/23 16:28:13] ppocr INFO: PostProcess : [2024/03/23 16:28:13] ppocr INFO: name : VQAReTokenLayoutLMPostProcess [2024/03/23 16:28:13] ppocr INFO: Train : [2024/03/23 16:28:13] ppocr INFO: dataset : [2024/03/23 16:28:13] ppocr INFO: data_dir : train_data/XFUND/zh_train/image [2024/03/23 16:28:13] ppocr INFO: label_file_list : ['train_data/XFUND/zh_train/train.json'] [2024/03/23 16:28:13] ppocr INFO: name : SimpleDataSet [2024/03/23 16:28:13] ppocr INFO: ratio_list : [1.0] [2024/03/23 16:28:13] ppocr INFO: transforms : [2024/03/23 16:28:13] ppocr INFO: DecodeImage : [2024/03/23 16:28:13] ppocr INFO: channel_first : False [2024/03/23 16:28:13] ppocr INFO: img_mode : RGB [2024/03/23 16:28:13] ppocr INFO: VQATokenLabelEncode : [2024/03/23 16:28:13] ppocr INFO: algorithm : LayoutXLM [2024/03/23 16:28:13] ppocr INFO: class_path : train_data/XFUND/class_list_xfun.txt [2024/03/23 16:28:13] ppocr INFO: contains_re : True [2024/03/23 16:28:13] ppocr INFO: order_method : tb-yx [2024/03/23 16:28:13] ppocr INFO: use_textline_bbox_info : True [2024/03/23 16:28:13] ppocr INFO: VQATokenPad : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: return_attention_mask : True [2024/03/23 16:28:13] ppocr INFO: VQAReTokenRelation : None [2024/03/23 16:28:13] ppocr INFO: VQAReTokenChunk : [2024/03/23 16:28:13] ppocr INFO: max_seq_len : 512 [2024/03/23 16:28:13] ppocr INFO: TensorizeEntitiesRelations : None [2024/03/23 16:28:13] ppocr INFO: Resize : [2024/03/23 16:28:13] ppocr INFO: size : [224, 224] [2024/03/23 16:28:13] ppocr INFO: NormalizeImage : [2024/03/23 16:28:13] ppocr INFO: mean : [123.675, 116.28, 103.53] [2024/03/23 16:28:13] ppocr INFO: order : hwc [2024/03/23 16:28:13] ppocr INFO: scale : 1 [2024/03/23 16:28:13] ppocr INFO: std : [58.395, 57.12, 57.375] [2024/03/23 16:28:13] ppocr INFO: ToCHWImage : None [2024/03/23 16:28:13] ppocr INFO: KeepKeys : [2024/03/23 16:28:13] ppocr INFO: keep_keys : ['input_ids', 'bbox', 'attention_mask', 'token_type_ids', 'entities', 'relations'] [2024/03/23 16:28:13] ppocr INFO: loader : [2024/03/23 16:28:13] ppocr INFO: batch_size_per_card : 2 [2024/03/23 16:28:13] ppocr INFO: drop_last : False [2024/03/23 16:28:13] ppocr INFO: num_workers : 1 [2024/03/23 16:28:13] ppocr INFO: shuffle : True [2024/03/23 16:28:13] ppocr INFO: profiler_options : None [2024/03/23 16:28:13] ppocr INFO: train with paddle 2.6.0 and device Place(gpu:0) [2024/03/23 16:28:22] ppocr INFO: Initialize indexs of datasets:['D:/demo/PaddleOCR/train_data/XFUND/zh_train/train.json'] list index out of range [2024-03-23 16:28:22,741] [ INFO] - Already cached D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\sentencepiece.bpe.model [2024-03-23 16:28:23,121] [ INFO] - tokenizer config file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\tokenizer_config.json [2024-03-23 16:28:23,121] [ INFO] - Special tokens file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\special_tokens_map.json [2024-03-23 16:28:23,124] [ INFO] - Already cached D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\sentencepiece.bpe.model [2024/03/23 16:28:23] ppocr INFO: Initialize indexs of datasets:['D:/demo/PaddleOCR/train_data/XFUND/zh_val/val.json'] [2024-03-23 16:28:23,429] [ INFO] - tokenizer config file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\tokenizer_config.json [2024-03-23 16:28:23,429] [ INFO] - Special tokens file saved in D:/demo/PaddleOCR/pnlMode\models\layoutxlm-base-uncased\special_tokens_map.json [2024-03-23 16:28:23,441] [ INFO] - Loading configuration file D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy\config.json [2024-03-23 16:28:23,442] [ INFO] - Loading weights file D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy\model_state.pdparams [2024-03-23 16:28:24,118] [ INFO] - Loaded weights file from disk, setting weights to model. W0323 16:28:24.221403 20396 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.9, Driver API Version: 12.3, Runtime API Version: 12.0 W0323 16:28:24.234532 20396 gpu_resources.cc:164] device: 0, cuDNN Version: 8.9. [2024-03-23 16:28:25,251] [ INFO] - All model checkpoint weights were used when initializing LayoutXLMForRelationExtraction. [2024-03-23 16:28:25,251] [ INFO] - All the weights of LayoutXLMForRelationExtraction were initialized from the model checkpoint at D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy. If your task is similar to the task the model of the checkpoint was trained on, you can already use LayoutXLMForRelationExtraction for predictions without further training. [2024/03/23 16:28:25] ppocr INFO: train dataloader has 75 iters [2024/03/23 16:28:25] ppocr INFO: valid dataloader has 7 iters [2024/03/23 16:28:25] ppocr INFO: resume from D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy [2024/03/23 16:28:25] ppocr WARNING: D:/demo/PaddleOCR/pretrained_model/re_vi_layoutxlm_xfund_pretrained/best_accuracy.pdopt is not exists, params of optimizer is not loaded [2024/03/23 16:28:25] ppocr INFO: During the training process, after the 0th iteration, an evaluation is run every 19 iterations Traceback (most recent call last): File "C:\PyCharm Community Edition 2023.3.4\plugins\python-ce\helpers\pydev\pydevd.py", line 1534, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "C:\PyCharm Community Edition 2023.3.4\plugins\python-ce\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "D:\demo\PaddleOCR\tools\train.py", line 451, in <module> re_main_train() File "D:\demo\PaddleOCR\tools\train.py", line 435, in re_main_train main(config, device, logger, vdl_writer) File "D:\demo\PaddleOCR\tools\train.py", line 199, in main program.train(config, train_dataloader, valid_dataloader, device, model, File "D:\demo\PaddleOCR\tools\program.py", line 304, in train preds = model(batch) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\ppocr\modeling\architectures\base_model.py", line 86, in forward x = self.backbone(x) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\ppocr\modeling\backbones\vqa_layoutlm.py", line 227, in forward x = self.model( File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\paddlenlp\transformers\layoutxlm\modeling.py", line 1331, in forward loss, pred_relations = self.extractor(sequence_output, entities, relations) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\nn\layer\layers.py", line 1429, in __call__ return self.forward(*inputs, **kwargs) File "D:\demo\PaddleOCR\paddlenlp\transformers\layoutxlm\modeling.py", line 1225, in forward relations, entities = self.build_relation(relations, entities) File "D:\demo\PaddleOCR\paddlenlp\transformers\layoutxlm\modeling.py", line 1198, in build_relation relation_per_doc = paddle.concat([reordered_relations, relation_per_doc_label], axis=1) File "D:\AnacondaMain\envs\ppocr\lib\site-packages\paddle\tensor\manipulation.py", line 1263, in concat return _C_ops.concat(input, axis) ValueError: (InvalidArgument) concat(): argument 'x' (position 0) must be list of Tensors, but got empty list (at ..\paddle\fluid\pybind\eager_utils.cc:1383) 好像更新之后就报错了，不知道如何解决？
评论 (
0
)
登录
后才可以发表评论
状态
待办的
待办的
进行中
已完成
已关闭
负责人
未设置
标签
未设置
标签管理
里程碑
未关联里程碑
未关联里程碑
Pull Requests
未关联
未关联
关联的 Pull Requests 被合并后可能会关闭此 issue
分支
未关联
分支 (35)
标签 (24)
main
gh-pages
dependabot/github_actions/github-actions-a331d3ec2d
release/3.2
release/3.1
MelroseData-patch-1
release/3.0
chatocr_doc
release/2.10
dy2st_config
release/2.9
GreatV-patch-2
GreatV-patch-1
release/2.6.1
dyning-patch-1
release/2.8
release/2.7
dygraph
release/2.6
release/2.7.1
shiyutang-patch-1
docs_update
release/2.5
revert-7381-dygraph
revert-8552-dygraph
release/2.6rc
release/2.0-rc1-0
release/1.1
release/2.0
release/2.1
release/2.2
release/2.3
release/2.4
static
revert-7437-dygraph
v3.2.0
v3.1.1
v3.1.0
v3.0.3
v3.0.2
v3.0.1
v3.0.0
v2.10.0
v2.9.1
v2.9.0
v2.8.1
v2.8.0
v2.7.5
v2.7.4
v2.7.3
v2.7.2
v2.7.1
v2.7.0
v2.6.0
v2.5.0
v2.1.1
v2.1.0
v2.0.0
v1.1.0
开始日期 - 截止日期
-
置顶选项
不置顶
置顶等级：高
置顶等级：中
置顶等级：低
优先级
不指定
严重
主要
次要
不重要
参与者（1）
Python
1
https://gitee.com/paddlepaddle/PaddleOCR.git
git@gitee.com:paddlepaddle/PaddleOCR.git
paddlepaddle
PaddleOCR
PaddleOCR
点此查找更多帮助
搜索帮助
Git 命令在线学习
如何在 Gitee 导入 GitHub 仓库
Git 仓库基础操作
企业版和社区版功能对比
SSH 公钥设置
如何处理代码冲突
仓库体积过大，如何减小？
如何找回被删除的仓库数据
Gitee 产品配额说明
GitHub仓库快速导入Gitee及同步更新
什么是 Release（发行版）
将 PHP 项目自动发布到 packagist.org
评论
仓库举报
回到顶部
登录提示
该操作需登录 Gitee 帐号，请先登录后再操作。
立即登录
没有帐号，去注册
