-
I have trained TPS-ResNet-BiLSTM-CTC model on my dataset and have tried to run demo.py. But I had an error in convert.decode():
```
Traceback (most recent call last):
File "demo.py", line 133…
-
These would be separate from the mixing weights (the three scalars) used for the input to the BiLSTM. They would impact only the skip connection, and they would be separate for each pretraining or tar…
-
Sorry to bother you, I used command you provided in github (metaQA hop1 full-KG), I just get 0.93, while your paper is 0.97, there is a large gap, on the other hand, I found your paper uses ROBERT to …
-
Hi , I was trying to compress a normal text file , the model runs on all epochs and shows the loss improving significantly , the compressor file also executes with no error.However , the result gives …
kv304 updated
4 years ago
-
paddlepaddle-gpu 1.7.2.post107
PaddleOCR [3b40c32](https://github.com/PaddlePaddle/PaddleOCR/commit/3b40c32a2f73fac958ad3476ca8af5ab5116c169)
`python tools/expo…
-
`aistudio@jupyter-363593-683413:~/work/PaddleOCR-develop$ python tools/train.py -c configs/rec/rec_chinese_common_train.yml
2020-08-27 22:01:04,734-INFO: {'Global': {'debug': False, 'algorithm': 'CR…
-
Hi, I have met the same problem as issue # 40.
I use a Bilstm+CRF to do NER tasks, the loss decreases and the f1 remains 0.12.
I find the outputs of the CRF layer are almost all O( a label of ner).…
-
Hi,
Currently I'm checking again the German-English pre-trained model in https://opennmt.net/Models-py/, and feel confused about the tokenization method. Before preprocessing the tokenized data, ht…
-
g2des updated
4 years ago
-
when i use ST_spe and validation from https://drive.google.com/drive/folders/192UfE9agQUMNq6AgU3_E05_FcPZK4hyt
```
CUDA_VISIBLE_DEVICES=2 python3 train.py --train_data data/ST_spe --valid_data data/…