Comments (5)
可以看下
model.py line 37
log_likelihood, self.transition_params = tf_ad.text.crf_log_likelihood(logits, label_sequences, text_lens)
self.transition_params = tf.Variable(self.transition_params, trainable=False)
self.transition_params 可以打印出来,应该会更新的。
from bi-lstm-crf-ner-tf2.0.
可以看下
model.py line 37log_likelihood, self.transition_params = tf_ad.text.crf_log_likelihood(logits, label_sequences, text_lens) self.transition_params = tf.Variable(self.transition_params, trainable=False)
self.transition_params 可以打印出来,应该会更新的。
这样更新得到的transition_params是每次随机生成的,正确的应该是随着训练过程不断调整的吧?
from bi-lstm-crf-ner-tf2.0.
同问,这里的transition_params是怎么更新的
from bi-lstm-crf-ner-tf2.0.
可以看下
model.py line 37log_likelihood, self.transition_params = tf_ad.text.crf_log_likelihood(logits, label_sequences, text_lens) self.transition_params = tf.Variable(self.transition_params, trainable=False)
self.transition_params 可以打印出来,应该会更新的。
这样更新得到的transition_params是每次随机生成的,正确的应该是随着训练过程不断调整的吧?
嗯嗯,发现了,这是一个bug。需要在 crf_log_likelihood 传入 trans 然后进行更新, 已经修改。谢谢提醒
from bi-lstm-crf-ner-tf2.0.
同问,这里的transition_params是怎么更新的
这里代码有一个bug,需要在 crf_log_likelihood 传入 trans 然后进行更新, 已经修改哈。
from bi-lstm-crf-ner-tf2.0.
Related Issues (17)
- 请问为什么accuracy = 0.5? HOT 4
- predict 提示使用tf.function
- why does loss have negative numbers
- error in tf 2.3 and tfa 11.2
- 修改hidden_num为1024或者256都会报错tensor 不匹配
- predict 不能进行预测,求大佬讲解一下 HOT 1
- Why you didn't use model.fit?
- 现在pip无法下载addons0.6.0,使用最新addons+tf2.0.0出现错误
- 为什么修改hidden_num会报维度不匹配的错误?请问如何修改这些超参数
- trainer error HOT 2
- test.txt并未使用
- test.txt在划水啊 HOT 1
- accuracy 1.0
- 报错 ValueError: tf.function-decorated function tried to create variables on non-first call. HOT 2
- 这样应该没有办法训练transition_params吧?最后输出的transition_params是不合理的。 HOT 1
- 感觉只用acc作为指标有点问题 HOT 3
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 bi-lstm-crf-ner-tf2.0.