Comments (7)
Hi. Thanks for the interest. I will check it later. So far please try to temporally change in ~/.keras/keras.json located in your user directory:
"image_dim_ordering": "tf",
to
"image_dim_ordering": "th",
and let me know whether it helps
or more likely something is wrong with embedding_weights you get from your trained word2vec. I've uploaded pretrained word2vec model, try with it.
use default:
embedding_dim = 20
min_word_count = 1 # Minimum word count
context = 10 # Context window size
from cnn-for-sentence-classification-in-keras.
Thank you for your answer.
Same error :
ValueError: Error when checking model input: expected dropout_input_2 to have 3 dimensions, but got array with shape (10662L, 56L).
I'll then try with Tensor Flow backend and tell you my comments.
I also tried withthe updated pretrained word2vec and same error.
I'll continue working on this issue.
from cnn-for-sentence-classification-in-keras.
Hello again, after a lot of problems with TensorFlow, everything is working... although I'd like to know if there's a chance to use Theano instead of TensorFlow.
from cnn-for-sentence-classification-in-keras.
It was originally for Theano. I'll let you know when I have a moment to run it with recent Keras. Version conflict is another possible reason
from cnn-for-sentence-classification-in-keras.
Thank you for your time. Could you please tell me, which version of Theano and Keras are you using?
from cnn-for-sentence-classification-in-keras.
I have verified it, and it works as intended. My versions are Theano v0.8.2, Keras v1.2.0 and it's not too much behind the current 1.2.2. Also, added minor changes, they don't affect overall behavior.
from cnn-for-sentence-classification-in-keras.
After changes on my configuration files and your updates, it is running well on Theano.
Thank you for your time.
from cnn-for-sentence-classification-in-keras.
Related Issues (20)
- error when retraining word vector HOT 3
- Error in w2v.py line 52 HOT 4
- TypeError: __init__() takes at least 3 arguments (2 given) HOT 1
- Running instructions HOT 1
- expected input_4 to have shape (None, 185) but got array with shape (1665, 35) HOT 1
- how to run trained model on sample sentence HOT 1
- Trying to replicate the results obtained with denny brtiz's code HOT 8
- Using local directory dataset does not yield the marked results HOT 1
- Using Glove or GoogleNews? HOT 1
- Wrong model for Y.Kim's TextCNN HOT 1
- Using pre-trained google word embeddings HOT 3
- Negative dimension size caused by subtracting 3 from 1
- Only words, no sentences HOT 1
- 问题咨询 HOT 8
- How to train the model with multi-class dataset HOT 2
- accuracy HOT 3
- The model always predicts the same label HOT 1
- Two fully-connected layers after convolutions HOT 1
- as for the CNN-non-static model initialization issue
- Multiple Dropouts different from Original Paper and Denny Britz
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 cnn-for-sentence-classification-in-keras.