Comments (6)
- tril = tf.contrib.linalg.LinearOperatorTriL(diag_vals).to_dense() # (T_q, T_k)
+ tril = tf.linalg.LinearOperatorLowerTriangular(diag_vals).to_dense() # (T_q, T_k)
from transformer.
function has been changed to LinearOperatorLowerTriangular
from transformer.
Thank you! I have the same problem and it works for me!
from transformer.
function has been changed to LinearOperatorLowerTriangular
Hi, bro, how do you deal with such VERSION problems? I think google should add some instructions in the history versions.
from transformer.
Hello I am getting a similar error.
File "/Users/aishwarya/Desktop/transformers/modules.py", line 227, in multihead_attention
tril = tf.contrib.linalg.LinearOperatorLowerTriangular(diag_vals).to_dense() # (T_q, T_k)
AttributeError: module 'tensorflow.contrib' has no attribute 'linalg'
My tf version is - 1.13.0-dev20181108
Any guidance will be really helpful.
from transformer.
Hello I am getting a similar error.
File "/Users/aishwarya/Desktop/transformers/modules.py", line 227, in multihead_attention
tril = tf.contrib.linalg.LinearOperatorLowerTriangular(diag_vals).to_dense() # (T_q, T_k)
AttributeError: module 'tensorflow.contrib' has no attribute 'linalg'My tf version is - 1.13.0-dev20181108
Any guidance will be really helpful.
I think you should exclude 'contrib' when you use this function.
In my case, it works well (tf version 1.12.0)
from transformer.
Related Issues (20)
- how to understand decoder_inputs have ["<s>"] while y_hat, y or x don't have ["<s>"] HOT 1
- How do you connect Convolutional layers to Transformers?
- Can anyone improve the code to reproduce WMT2014 results?
- Why to remove query masking?
- something about Model.py , in which something wrong between encoder and decoder HOT 2
- 自己学习率没有调节好 HOT 4
- 无 HOT 1
- Error! excuting the train.py
- Question:multihead_attention()’s output and ff()‘s output need dropout?
- Is value must be linear transformed at multi-head attention?
- request for dataset HOT 1
- 请问下,有TF2.X有实现的代码吗 HOT 2
- There is a problem when I execute the command bash download.sh HOT 2
- train error
- 多头问题的实现推导不太理解
- 您好,我想请问论文里bleu和meteor的数据是怎么得到的?我运行test.py文件,出现的是很多句子。
- 数据集链接失效了 HOT 3
- tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[27,100] = 100 is not in [0, 100) HOT 2
- About the query_mask
- about spm.SentencePieceTrainer.Train(train) HOT 1
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 transformer.