-
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…
-
Traceback (most recent call last):
File "app.py", line 12, in
from model import text_predict,crnn_handle
File "/home/wangdawei/github/ocr/chineseocr_lite/model.py", line 1, in
from …
-
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…
-
你好，后续有增加其他特种车牌的打算吗？
-
https://github.com/Mingtzge/2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement/blob/6f11d683ab7bc044c0223fedfb15f8af74af1ae3/recognize_process/crnn_model/crnn_model.py#L136
看到您的tf版本是1.1.12，该版本ctcloss…
-
ocr_recognition，CRNN模型保存为fluid.io.save_inference_model(dirname=args.freeze_model_path,
feeded_var_names=['pixel'],
target_…
-
I got a similar task recently, but there are 20838 characters in my dic. I have trained recognition model for almost 2 weeks,and it will last for another 2 weeks at least i guess. It's my first time …
-
在训练的时候这几个参数['reduce_sum_0.tmp_0', 'reduce_sum_2.tmp_0', 'elementwise_sub_0']对应的值为 [nan, 4.791813, 5]，其中第一个参数reduce_sum_0.tmp_0的值为nan这是为什么？之前的训练都是正常的，在executor执行run后输出的结果中出现Nan，求解答
-
你好，识别模型是怎么训练的，会开源代码吗
-
请问下360万的数据集是自己制作生成的还是网上的开源数据集，另外如果要用自己的数据集(一万左右)是用您的数据集先跑，之后迁移过去呢，还是两种数据集混在一起直接训练呢？