PP-LCNet_x1_0_textline_ori无tensorrt高性能推理加速

[wqw0806]

🔎 Search before asking

• [x] I have searched the PaddleOCR Docs and found no similar bug report.
• [x] I have searched the PaddleOCR Issues and found no similar bug report.
• [x] I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

PP-LCNet_x1_0_textline_ori无tensorrt高性能推理加速 当我指定这个模型时，会输出没有该模型，Creating model: ('PP-LCNet_x1_0_textline_ori', 'models/v5/PP-LCNet_x1_0_textline_ori') 2025-11-03 11:53:00,435 - ocr - process_single_file - line:359 - ERROR - [0feafae4] 处理文件失败: PP-LCNet_x1_0_textline_ori is not registered on BasePredictor. The registied entities: [STFPM, PP-DocBee-2B, PP-DocBee-7B, PP-Chart2Table, PP-DocBee2-3B, PP-ShiTuV2_rec, PP-ShiTuV2_rec_CLIP_vit_base, PP-ShiTuV2_rec_CLIP_vit_large, MobileFaceNet, ResNet50_face, LaTeX_OCR_rec, UniMERNet, PP-FormulaNet-S, PP-FormulaNet-L, PP-FormulaNet_plus-S, PP-FormulaNet_plus-M, PP-FormulaNet_plus-L, CLIP_vit_base_patch16_224, CLIP_vit_large_patch14_224, ConvNeXt_tiny, ConvNeXt_small, ConvNeXt_base_224, ConvNeXt_base_384, ConvNeXt_large_224, ConvNeXt_large_384, MobileNetV1_x0_25, MobileNetV1_x0_5, MobileNetV1_x0_75, MobileNetV1_x1_0, MobileNetV2_x0_25, MobileNetV2_x0_5, MobileNetV2_x1_0, MobileNetV2_x1_5, MobileNetV2_x2_0, MobileNetV3_large_x0_35, MobileNetV3_large_x0_5, MobileNetV3_large_x0_75, MobileNetV3_large_x1_0, MobileNetV3_large_x1_25, MobileNetV3_small_x0_35, MobileNetV3_small_x0_5, MobileNetV3_small_x0_75, MobileNetV3_small_x1_0, MobileNetV3_small_x1_25, MobileNetV4_conv_small, MobileNetV4_conv_medium, MobileNetV4_conv_large, MobileNetV4_hybrid_medium, MobileNetV4_hybrid_large, PP-HGNet_tiny, PP-HGNet_small, PP-HGNet_base, PP-HGNetV2-B0, PP-HGNetV2-B1, PP-HGNetV2-B2, PP-HGNetV2-B3, PP-HGNetV2-B4, PP-HGNetV2-B5, PP-HGNetV2-B6, PP-LCNet_x0_25, PP-LCNet_x0_25_textline_ori, PP-LCNet_x0_35, PP-LCNet_x0_5, PP-LCNet_x0_75, PP-LCNet_x1_0, PP-LCNet_x1_0_doc_ori, PP-LCNet_x1_5, PP-LCNet_x2_0, PP-LCNet_x2_5, PP-LCNetV2_small, PP-LCNetV2_base, PP-LCNetV2_large, ResNet101, ResNet152, ResNet18, ResNet34, ResNet50, ResNet200_vd, ResNet101_vd, ResNet152_vd, ResNet18_vd, ResNet34_vd, ResNet50_vd, SwinTransformer_tiny_patch4_window7_224, SwinTransformer_small_patch4_window7_224, SwinTransformer_base_patch4_window7_224, SwinTransformer_base_patch4_window12_384, SwinTransformer_large_patch4_window7_224, SwinTransformer_large_patch4_window12_384, StarNet-S1, StarNet-S2, StarNet-S3, StarNet-S4, FasterNet-L, FasterNet-M, FasterNet-S, FasterNet-T0, FasterNet-T1, FasterNet-T2, PP-LCNet_x1_0_table_cls, ResNet50_ML, PP-LCNet_x1_0_ML, PP-HGNetV2-B0_ML, PP-HGNetV2-B4_ML, PP-HGNetV2-B6_ML, CLIP_vit_base_patch16_448_ML, PP-LCNet_x1_0_pedestrian_attribute, PP-LCNet_x1_0_vehicle_attribute, UVDoc, PicoDet-L, PicoDet-S, PP-YOLOE_plus-L, PP-YOLOE_plus-M, PP-YOLOE_plus-S, PP-YOLOE_plus-X, RT-DETR-H, RT-DETR-L, RT-DETR-R18, RT-DETR-R50, RT-DETR-X, PicoDet_layout_1x, PicoDet_layout_1x_table, PicoDet-S_layout_3cls, PicoDet-S_layout_17cls, PicoDet-L_layout_3cls, PicoDet-L_layout_17cls, RT-DETR-H_layout_3cls, RT-DETR-H_layout_17cls, YOLOv3-DarkNet53, YOLOv3-MobileNetV3, YOLOv3-ResNet50_vd_DCN, YOLOX-L, YOLOX-M, YOLOX-N, YOLOX-S, YOLOX-T, YOLOX-X, FasterRCNN-ResNet34-FPN, FasterRCNN-ResNet50, FasterRCNN-ResNet50-FPN, FasterRCNN-ResNet50-vd-FPN, FasterRCNN-ResNet50-vd-SSLDv2-FPN, FasterRCNN-ResNet101, FasterRCNN-ResNet101-FPN, FasterRCNN-ResNeXt101-vd-FPN, FasterRCNN-Swin-Tiny-FPN, Cascade-FasterRCNN-ResNet50-FPN, Cascade-FasterRCNN-ResNet50-vd-SSLDv2-FPN, PicoDet-M, PicoDet-XS, FCOS-ResNet50, DETR-R50, PP-ShiTuV2_det, PP-YOLOE-L_human, PP-YOLOE-S_human, PP-YOLOE-L_vehicle, PP-YOLOE-S_vehicle, PP-YOLOE_plus_SOD-L, PP-YOLOE_plus_SOD-S, PP-YOLOE_plus_SOD-largesize-L, CenterNet-DLA-34, CenterNet-ResNet50, PicoDet_LCNet_x2_5_face, BlazeFace, BlazeFace-FPN-SSH, PP-YOLOE_plus-S_face, PP-YOLOE-R-L, Co-Deformable-DETR-R50, Co-Deformable-DETR-Swin-T, Co-DINO-R50, Co-DINO-Swin-L, RT-DETR-L_wired_table_cell_det, RT-DETR-L_wireless_table_cell_det, PP-DocLayout-L, PP-DocLayout-M, PP-DocLayout-S, PP-DocLayout_plus-L, PP-DocBlockLayout, Mask-RT-DETR-S, Mask-RT-DETR-M, Mask-RT-DETR-X, Mask-RT-DETR-H, Mask-RT-DETR-L, SOLOv2, MaskRCNN-ResNet50, MaskRCNN-ResNet50-FPN, MaskRCNN-ResNet50-vd-FPN, MaskRCNN-ResNet101-FPN, MaskRCNN-ResNet101-vd-FPN, MaskRCNN-ResNeXt101-vd-FPN, MaskRCNN-ResNet50-vd-SSLDv2-FPN, Cascade-MaskRCNN-ResNet50-FPN, Cascade-MaskRCNN-ResNet50-vd-SSLDv2-FPN, PP-YOLOE_seg-S, PP-TinyPose_128x96, PP-TinyPose_256x192, BEVFusion, whisper_large, whisper_medium, whisper_base, whisper_small, whisper_tiny, GroundingDINO-T, YOLO-Worldv2-L, SAM-H_point, SAM-H_box, Deeplabv3_Plus-R101, Deeplabv3_Plus-R50, Deeplabv3-R101, Deeplabv3-R50, OCRNet_HRNet-W48, OCRNet_HRNet-W18, PP-LiteSeg-T, PP-LiteSeg-B, SegFormer-B0, SegFormer-B1, SegFormer-B2, SegFormer-B3, SegFormer-B4, SegFormer-B5, SeaFormer_base, SeaFormer_tiny, SeaFormer_small, SeaFormer_large, MaskFormer_tiny, MaskFormer_small, SLANet, SLANet_plus, SLANeXt_wired, SLANeXt_wireless, PP-OCRv5_mobile_det, PP-OCRv5_server_det, PP-OCRv4_mobile_det, PP-OCRv4_server_det, PP-OCRv4_mobile_seal_det, PP-OCRv4_server_seal_det, PP-OCRv3_mobile_det, PP-OCRv3_server_det, PP-OCRv3_mobile_rec, en_PP-OCRv3_mobile_rec, korean_PP-OCRv3_mobile_rec, japan_PP-OCRv3_mobile_rec, chinese_cht_PP-OCRv3_mobile_rec, te_PP-OCRv3_mobile_rec, ka_PP-OCRv3_mobile_rec, ta_PP-OCRv3_mobile_rec, latin_PP-OCRv3_mobile_rec, arabic_PP-OCRv3_mobile_rec, cyrillic_PP-OCRv3_mobile_rec, devanagari_PP-OCRv3_mobile_rec, PP-OCRv4_mobile_rec, PP-OCRv4_server_rec, en_PP-OCRv4_mobile_rec, PP-OCRv4_server_rec_doc, ch_SVTRv2_rec, ch_RepSVTR_rec, PP-OCRv5_server_rec, PP-OCRv5_mobile_rec, AutoEncoder_ad, DLinear_ad, Nonstationary_ad, PatchTST_ad, TimesNet_ad, TimesNet_cls, DLinear, NLinear, Nonstationary, PatchTST, RLinear, TiDE, TimesNet, PP-TSM-R50_8frames_uniform, PP-TSMv2-LCNetV2_8frames_uniform, PP-TSMv2-LCNetV2_16frames_uniform, YOWO] 这个报错 我指定的模型为 "text_line_orientation_model_name": "PP-LCNet_x1_0_textline_ori", "text_line_orientation_model_dir": "PP-LCNet_x1_0_textline_ori"

🏃‍♂️ Environment (运行环境)

paddleocr3.0.0

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

"text_line_orientation_model_name": "PP-LCNet_x1_0_textline_ori", "text_line_orientation_model_dir": "PP-LCNet_x1_0_textline_ori" , "enable_hpi": True