Replies: 2 comments
-
遇到了同样的问题,预训练模型训练后无法opt。推理模型下载下来可以直接opt。请问有解决吗 @balcklive |
Beta Was this translation helpful? Give feedback.
0 replies
-
没有,只能使用Paddlelite 2.12才行 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
./opt_linux --model_file=inference.pdmodel --param_file=inference.pdiparams --optimize_out_type=naive_buffer --optimize_out=quant_opt --valid_targets=arm
-Loading topology data from inference.pdmodel
Loading params data from inference.pdiparams
[F 8/27 2:35:29.277 ...-Lite/lite/core/model/general/op_desc.cc:63 Output] Check failed: it != outputs_.end():
已放弃 (核心已转储)
备注:尝试了使用paddlelite2.12版本执行上述命令是可以正常运行的
在https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/models_list.md上分别下载了推理模型和训练模型,使用推理模型直接运行上述代码是可以转换的,但是使用训练模型先执行
python tools/export_model.py -c configs/rec/PP-OCRv4/en_PP-OCRv4_rec.yml -o Global.pretrained_model=E:\02-ocr\03-infer_models\trained_own\best_accuracy Global.save_inference_dir=E:\02-ocr\03-infer_models\trained_own
然后再执行上述命令时,则出现上述报错
我们提供了AceIssueSolver来帮助你解答问题,你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no): yes
请尽量不要包含图片在问题中/Please try to not include the image in the issue.
Beta Was this translation helpful? Give feedback.
All reactions