Comments (7)
The size of your dictionary / The input dimension of the embedding
from keras-bert.
I am getting memory errors (used several GPUs with at least 12 gb ram) even for a small size (7k) of dictionary. Considering the real dictionary must consist 100k tokens, there is something wrong. I opened an issue at Keras repo, I will be really happy if you can take a look since it is based on your code.
link: keras-team/keras#12755
from keras-bert.
I think you misunderstood steps_per_epoch
. If you are using a generator, then the batch size is controlled only by the generator itself. Setting steps_per_epoch
means there are batch_size
x steps_per_epoch
samples in one epoch.
from keras-bert.
But don't we set number of sequences/samples? Doesn't this allow us control batch size by changing steps_per_epoch
?
from keras-bert.
There is no way to modify your generator "intelligently" since you may need operators like padding.
from keras-bert.
Okay. What do you suggest about deciding the value of steps_per_epoch
?
from keras-bert.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
from keras-bert.
Related Issues (20)
- keras-bert load pre model failed in keras 2.2.4, maybe it is a bug
- could you provide an albert loader ? HOT 1
- 如何实现在自己的数据上很少的预训练? HOT 1
- 如何提取长度一致的bert词向量? HOT 1
- Input sentence for extract_embeddings HOT 1
- List index out of range for example code HOT 2
- 在哪里可以找到之前的版本呢? HOT 2
- Keras Bert with character embeddings HOT 1
- The method get_model to get the bert model is right? HOT 4
- API reference list
- which version of keras-bert is compatible for tensorflow 1.13? HOT 2
- 关于显存巨量占用的疑惑 HOT 1
- Improve Tokenizer for uppercase text HOT 1
- Error in getting attention map HOT 3
- Masked LM pre-training HOT 1
- AttributeError: module 'keras' has no attribute 'applications' HOT 5
- module 'tensorflow.compat.v2' has no attribute '__internal__' HOT 1
- load_trained_model_from_checkpoint(config_path,checkpoint_file=checkpoint_path) AttributeError: 'tuple' object has no attribute 'layer'
- load_trained_model_from_checkpoint(config_path,checkpoint_file=checkpoint_path)
- 'adamwarmup' object has no attribute '_set_hyper'
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 keras-bert.