Comments (7)
@dnnguifever You need prepare the data before running the code. E.g., you can prepare STL dataset by using the following commands:
cd data/stl
bash get_data.sh
cd ../..
Other datasets can be prepared according to README
from dec-keras.
Thank you for your response. I have re-performed that step, just to make sure I have done it, and still, I get the same " IOError: [Errno 2] No such file or directory: './data/stl/train_y.bin' " error.
Any other ideas? I appreciate your help.
Thanks.
from dec-keras.
Whoops, did not unpack the data enough before. I've unpacked it, will try it again now. Thanks.
from dec-keras.
"No data! Use %s/get_data.sh to get data ready, then come back" % data_path
AssertionError: No data! Use ./data/stl/get_data.sh to get data ready, then come back
I have run:
cd data/stl
bash get_data.sh
cd ../..
And unpacked the data, revealing train_y.bin and other files. Now, instead of getting the train_y.bin error, I am getting the error above.
Am I doing something wrong?
Thanks!
from dec-keras.
@dnnguifever After unpacking, there should be at least four files existing in 'data/stl': train_X.bin, test_X.bin, train_y.bin, test_y.bin. Please make sure that satisfied. See details on http://ai.stanford.edu/~acoates/stl10/
from dec-keras.
-rw-r--r-- 1 221184000 Sep 21 10:43 test_X.bin
-rw-r--r-- 1 8000 Sep 21 10:43 test_y.bin
-rw-r--r-- 1 138240000 Sep 21 10:43 train_X.bin
-rw-r--r-- 1 5000 Sep 21 10:42 train_y.bin
Those are four files in my data/stl folder. I am still getting that error.
Thank you for your help!
from dec-keras.
@dnnguifever Maybe you can implement load_stl()
by yourself according to http://ai.stanford.edu/~acoates/stl10/. It is very easy.
from dec-keras.
Related Issues (20)
- Question about epoch HOT 2
- Why does it get the higher Acc than that of the paper? HOT 2
- about acc HOT 1
- TypeError: add_weight() got multiple values for argument 'name' HOT 9
- loss 先升后下降 HOT 1
- Can using different autoencoder architectures help improve results? HOT 1
- What does it mean if clustering accuracy metric fluctuates a lot? HOT 1
- Conflicts to the Network Structure HOT 2
- Licence
- Difference between your reuters dataset and keras's reuters dataset HOT 1
- SAE part may be wrong. HOT 2
- cifar-10 数据集acc很低的疑问
- Suggested fix for deprecated 'from sklearn.utils.linear_assignment_ import linear_assignment' HOT 1
- How to feed TFRecord data (over 60GB) to the DEC-keras model?
- How to calculate the clusterig (KLD) loss for every instance
- ValueError: too many values to unpack (expected 2) HOT 1
- n_samples=23205 should be >= n_clusters=85617.
- Why is evaluation done on the training set
- Encoder weights are not updated during the clustering phase HOT 1
- ValueError: No such layer: clustering. HOT 2
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 dec-keras.