-
错误:`PaddleCheckError: out of memory at [/paddle/paddle/fluid/platform/device_context.cc:219]`
- 版本、环境信息:
1)PaddlePaddle版本:1.6 release版
2)GPU:P4、CUDA10和CUDNN7.6
4)系统环境:centos7,Python版本:…
-
问题描述:使用models\PaddleCV\ocr_recognition训练attention模型(crnn_ctc模型使用正常),并在infer.py中重新保存为固化模型,使用paddle predictor预测报错,错误信息为:
File "D:\pythonAPI\Python37\call_paddle_OCR.py", line 108, in test_image
…
-
开发环境:
win10,conda安装paddlepaddle=1.8。
已经成功生成model和params文件,只是部署预测的时候出了错。
---------------------------------------------------------------------------------------------------
运行predict_system的时候报错如下:…
-
请教:通用中文OCR与轻量级的区别在哪?
-
Thanks to your work and I have already got a good crnn model. In my test the accuracy is satisfying.
But the inference time is a pity: almost 140ms per image with size = 32 x 150. I noticed that some…
-
您好,作者!我想请教下你对于多gpu训练,训练的每个epoch过后,测试准确率,代码在那个地方修改比较合适?谢谢!
-
hello I'm trying to use MDLSTM with the ctc+crnn function but without success it causes an error by the loss ctc.
```
def ctc_func(args):
y_pred, labels, input_length, label_length = args
…
Zrufy updated
4 years ago
-
您好!我想问一下您,你的训练代码,多gpu训练train_shadownet.py 中 每个gpu上放的训练数据是同一批,我感觉这个是不是有点问题,多gpu训练应该每个gpu上放不同的数据吧?
期待您的回复,谢谢!
-
开启内存优化后,OCR报如下错误
File "/work/weike/svn/baidu/paddle/test/cts_test/test_ocr_recognition.py", line 180, in test_train_ocr_recognition_crnn_ctc_multi_gpu
train_info = executor_network(memory_opti…
-
Date: 19/03
Task:
- [x] Prepare data: Crop image into batches of text-lines given ground truth coordinates @patrickphatnguyen
- [x] Train CRNN baseline model: Train a CRNN model with prepared data…