PaddleOCR: Error [operator < conv2d_fusion > error] while use ppyolov2_r50vd_dcn_365e_publaynet model
Hi, i want to ask when using this model ppyolov2_r50vd_dcn_365e_publaynet i got this error
InvalidArgumentError: The conv2d_fusion Op's Input Variable `Input` contains uninitialized Tensor.
[Hint: Expected t->IsInitialized() == true, but received t->IsInitialized():0 != true:1.] (at /paddle/paddle/fluid/framework/operator.cc:2411)
[operator < conv2d_fusion > error]
here is the code that i use. I’m using paddlepaddle-gpu 2.4.0.post117
import os
import cv2
from paddleocr import PPStructure, save_structure_res
table_engine = PPStructure(
table=False,
ocr=False,
show_log=True,
lang="en",
layout_model_dir="model_zoo/ppyolov2_r50vd_dcn_365e_publaynet/",)
pls help, it’s works normal when i’m use picodet_lcnet_x1_0_fgd_layout model, it use the same dict path.
About this issue
- Original URL
- State: closed
- Created a year ago
- Comments: 16
我也是。使用picodet_lcnet_x1_0_fgd_layout_table_infer模型没问题。但使用ppyolov2_r50vd_dcn_365e_tableBank_word和自己在paddleDetection训练的模型就报这个错