-
yml 配置文件如下:
`# rec_en_number_lite_train.yml #
Global:
use_gpu: True
epoch_num: 3000
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_en_number_lite
save_ep…
-
你好，现在遇到个问题，识别模型是在官方模型基础上加图片样本训练出来的。
Global:
algorithm: CRNN
use_gpu: true
epoch_num: 150
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_CRNN
save_epoch_s…
-
I compiled the backend of paddle using version 21.04 and successfully generated the libtriton_paddle.so required by triton and successfully loaded the model of paddle, but I made an error when I press…
-
If the data length after the CTC converter is larger than the input length of input and set flatten=True in CTCLoss, there will be an error when calculating CTC loss. So is it a bug or a feature for n…
-
Hello!
I try to train model on previously created tfrecords.
Error which I get:
```
I1203 18:27:07.126662 30607 train_shadownet.py:573] Use single gpu to train the model
WARNING:tensorflow:Fr…
-
Em xin phép hỏi a một số vấn đề về mặt lý thuyết ạ.
- Mạng VGG-19 a sử dụng có đầu ra trước khi flatten là 1xCx2x32 tương ứng BxCxHxW1 (với ảnh đầu vào 128x32). Khác với mã code của paper CRNN-CTC …
-
when I run main_crnn.py I court this issue:
#error -- unsupported GNU version! gcc versions later than 6 are not supported!
^~~~~
CMake Error at warpctc_generated_reduce.cu.o.cmake:219 (message…
-
Hi, thanks for the code.
When I try to fine-tuning the recognization model (rec_icdar15_train.yml, only modify label_file_list), I get acc is 1.0 on the log file. But when I use tools/infer_rec.py to…
-
Please make sure that this is a bug. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature requests and…
-
python3 train.py -c configs/rec/rec_icdar15_train.yml 2>&1 | tee train_rec.log
2020-11-25 15:08:02,934-INFO: {'Global': {'debug': False, 'algorithm': 'CRNN', 'use_gpu': False, 'epoch_num': 1000, 'log…