-
paddle 版本 2.0.2 paddleOCR 是2.1
想训练一个手写体识别模型 利用的是hwdb 单字合成图片来训练的 长度已经控制 1-25 目前合成第一批 24万多一点 想试一下效果 字典 7300多字符 原始文件改动了 字典和数据集路劲 和 batch_size_per_card 没有加载预训练模型
name: Cosine 这个属性群里有人说去…
-
Hi~ I used a multi-speaker dataset training a base model then fine tuned on a target speaker dataset, I set n_speakers value to 107. The base model training was ok but got this error when fine tuned o…
-
Hi, Thanks for the nice framework.
Do you plan to include the document context as the BERT paper did?
-
Hi, I notice that in the experiments/centralized/bilstm_exps/main_text_classification.py it imports different dataloaders for different tasks. For example:
```
import data_preprocessing.AGNews.data_…
-
I'm building a CNN-LSTM network in Keras (v2.02) + Tensorflow (v1.0.1) using video frames as input. I'm setting up the network as shown below:
import tensorflow as tf
import keras
imp…
-
Chinese TTS now available, thank @azraelkuan for his support :D. The model used Baker dataset here (https://www.data-baker.com/open_source.htmlt). The pretrained model licensed under CC BY-NC-SA 4.0 (…
-
## Description
Support for BiLSTM layer in DJL.
### Will this change the current api? How?
This will add a new API for layers similar to LSTM, CNN, etc. It should not effect any other APIs.
…
-
-
### I followed the commands as per README, but still, I'm facing some issues. maybe (i don't have any graphics card in my systems, and I have installed all dependencies as per documents.) Please find …
3rang updated
3 years ago
-
文字识别文档当中 给出的预训练模型是这个
https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_none_bilstm_ctc_v2.0_train.tar
我看这个模型不在模型列表当中
https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.0/doc/doc_ch/mo…