Comments (9)
@jaspercloud ,hi
I didn't see the wrong message,
Can you provide specific failure information?
from tensorflowasr.
代码停在self.train_datasets.take(self.train_steps_per_epoch):没有往下执行
def _train_batches(self):
"""Train model one epoch."""
try:
for batch in self.train_datasets.take(self.train_steps_per_epoch):
from tensorflowasr.
前几个step 都会比较慢,涉及资源的申请等操作。
建议可以先设置小一点的batch_size(例如4)进行测试。
from tensorflowasr.
前几个step 都会比较慢,涉及资源的申请等操作。
建议可以先设置小一点的batch_size(例如4)进行测试。
from tensorflowasr.
前几个step 都会比较慢,涉及资源的申请等操作。
建议可以先设置小一点的batch_size(例如4)进行测试。
停了半小时了
from tensorflowasr.
在usage中写了格式如下:
file_path1 \t text1
file_path2 \t text2
…………
其中 ’\t’ 为水平制表符
可以将所有的‘try’去掉,以查明具体错误原因。
from tensorflowasr.
try:
final_outputs, final_state = decoder.finalize(
final_outputs, final_state, final_sequence_lengths
)
except NotImplementedError:
pass
File "/root/anaconda3/envs/tf2/lib/python3.6/site-packages/tensorflow_addons/seq2seq/decoder.py", line 101, in finalize
raise NotImplementedError
去掉NotImplementedError报错,加上代码停在train
from tensorflowasr.
from tensorflowasr.
正确安装所需库后,模型相关的是不会有问题的。 还是需要看看数据读取方面。------------------ 原始邮件 ------------------ 发件人: "jaspercloud"<[email protected]> 发送时间: 2020年11月3日(星期二) 下午4:41 收件人: "Z-yq/TensorflowASR"<[email protected]>; 抄送: "Z-yq"<[email protected]>;"Assign"<[email protected]>; 主题: Re: [Z-yq/TensorflowASR] train failed (#12)
requirments.txt全部安装了,python3.6 tensorflow2.2
from tensorflowasr.
Related Issues (20)
- 关于2020/12/1的更新,自动打标点语言模型
- 训练am模型的时候,内存一直下降。下降到几百兆 HOT 2
- can i use it in a windows system? HOT 1
- 是否能提供StreamingConformer模型 HOT 1
- transducer解码时lstm存在大量重复计算 HOT 4
- tensorflow.python.framework.errors_impl.InternalError: Blas GEMM launch failed HOT 1
- 数字好像无法识别,这个应该如何优化处理? HOT 2
- 一个题外话,交流群的二维码失效了,不知道是否可以再放一次
- 想问一下楼主这个出错是什么问题 HOT 1
- bert_feature_loss in LM HOT 1
- 希望添加命令词模型或例子教程 HOT 3
- dict目录下缺少必要文件 HOT 1
- 关于VAD的训练集
- 关于使用Tester 来大批量测试 HOT 3
- 大佬可以更新下微信群吗,想交流一下 HOT 1
- 标点预测模型转换TFLITE问题
- 训练loss不下降 HOT 1
- 关于train_loss、ctc_loss和translate_loss的关系有些疑问 HOT 2
- 关于标点恢复模型OOV的问问 HOT 3
- 请问一下如何只使用cpu推理的方式
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorflowasr.