-
There are two issues, using Optuna with optuna.integration.allennlp.AllenNLPExecutor. The first is that everything works fine when number of jobs is set to be greater than one. But when njobs …
-
My compilation fails under:
/usr/bin/ld: cannot find -lcudart
/usr/bin/ld: cannot find -lcublas
/usr/bin/ld: cannot find -lcurand
collect2: error: ld returned 1 exi
I've solved this before bu…
-
使用rec_chinese_lite_train_v2.0.yml训练识别模型，对车牌字符进行识别，标准车牌比例是140*440（宽高比3.14）。
我基于CCPD数据集截取车牌区域后，设置RecResizeImg.image_shape: [3, 32, 320]或[3, 32, 100]时可训练，但这个尺寸和车牌相差比较远，重新设置.yml文件，按车牌比例的大小，设置为 [3, 70, 22…
-
## 개요
* 공식 튜토리얼 중 https://github.com/pytorch/tutorials/commit/bc9cac0a77512136d91d717e3c8f1e83165b196d 를 참고하여 반영하였습니다.
* 1.6 버전이 되면 새롭게 프로토타입(prototypes)이 추가되었습니다.
* 현재 메인 메뉴에서 바로 접근이 불가능한 튜토리얼은 …
-
在用paddleocr 2.0.2 训练车牌识别模型时，利用以下配置文件，一直报错，是我的yml 文件文件吗？？？还是什么问题？
参考：
[【AI创造营】使用 PaddleHub 结合 PaddleOCR 实现车牌识别](https://aistudio.baidu.com/aistudio/projectdetail/1603924?channelType=0&channel=0)
[Pa…
-
I got issue to download Language mode
( http://cloud.dlnel.org/filepub/?uuid=d21861e4-4ed6-45bb-ad8e-ae417a43195e)
as the file show its 2.x G in size, but i always can download file up to 1.x GB o…
-
It might not be a bug, but I have noticed the same reference .wav yields different results during test and inference times. When training and testing the same sentence using the same wav file, the spe…
-
各位大佬好！我使用rec_icdar15_train.yml的配置，使用icdar15数据集训练英文识别模型，参考的官方配置，训练结果的acc很低，rec_icdar15_train.yml按照原本的配置为改动。请问是什么原因？
请问是以下原因吗？
- lr过大
- epoch过小
- 使用lr decay
经过修改，将lr改为0.0001；epoch改为1200，增加了pretra…
-
系统:linux 16.04 gcc 4.8
PaddleOCR:release/2.0 版本
Paddle预测库：从官网下载的2.0rc cpu mkldnn预编译库(manylinux_cpu_avx_mkl_gcc482)
代码可以编译成功，但运行的时候报找不到rnn op
terminate called after throwing an instance of 'paddle:…
-
我用了aishell的模型进行测试，结果报错
CUDA_VISIBLE_DEVICES=0 python3 deploy/demo_server.py --host_ip localhost --host_port 8086
‘----------- Configuration Arguments -----------
alpha: 2.5
beam_size: 500
beta…