Comments (10)
Is this a classification problem? How does the network definition look like?
from nolearn.
Yes it is a classification problem, my input is 100x100 gray-scale images which has to be classified in to 5 classes. I have shared my code.
Here is a architecture of network.
net = NeuralNet(
layers=[
('input', layers.InputLayer),
('conv1', Conv2DLayer),
('pool1', MaxPool2DLayer),
('conv2', Conv2DLayer),
('pool2', MaxPool2DLayer),
('hidden4', layers.DenseLayer),
('output', layers.DenseLayer),
],
input_shape=(None, 1, 100, 100),
conv1_num_filters=1, conv1_filter_size=(3, 3), pool1_ds=(2, 2),
conv2_num_filters=1, conv2_filter_size=(2, 2), pool2_ds=(2, 2),
hidden4_num_units=50,
output_num_units=5, output_nonlinearity=None,
update_learning_rate=0.01,
update_momentum=0.9,
regression=False,
max_epochs=5,
verbose=1)
The dimensions and dtypes of X and Y which I pass to fit method are
net.fit(X, Y)
shape of X (35126L, 1L, 100L, 100L)
shape of Y (35126L,)
dtype of X = float32
dtype of Y = int32
and
theano.config.floatX = float32
from nolearn.
@jayendra13 You just mentioned that this is a classification problem, right ? Then,
output_nonlinearity=None
should be replaced by output_nonlinearity=lasagne.nonlinearities.softmax
from nolearn.
@paipai880429 Thanks for your comment I changed output_nonlinearity to softmax from the None, still
I am getting the same results, I think still there is something where I am making silly mistake.
One thing I forgot to mention that whenever I use predict method, it returns all zeros
from nolearn.
@jayendra13 It seems that the learning process has never been started. Then, did you try to decrease your initial learning rate?
from nolearn.
That might not be issue because initial random weights should give me some non-nan values for train and validation losses
from nolearn.
Hello I have the same problem. How did you fix it? Thank you
from nolearn.
I solved my problem, there were a set of value equal to inf ( it was an error) in my dataset.
from nolearn.
Had the same issue and "softmax" fixed it for me !
Thks 👍
from nolearn.
@paipai880429 In my case I had a learning rate of 0.01, changing it to 0.001 solved the problem, thanks for the tip. Why would the learning rate lead to this numerical instability?! Is it related to dataset size? Mine is big. Thanks
from nolearn.
Related Issues (20)
- RememberBestWeights does not honor the verbose parameter HOT 2
- A replayable fit() method - diff/patch attached HOT 1
- remove('trainable') Lasagne's command doesn't work in nolearn HOT 6
- flip_filters and pad parameter not used by NeuralNet's class HOT 5
- OSError: could not read bytes when trying to fetch mldata HOT 2
- CUDA error, possibly related to network size? HOT 2
- Trained on GPU, inference on CPU doesn't make sense
- Install nolearn with Lasagne dependance not working HOT 2
- Bug in calculating average scores
- nolearn is not installing
- Bug when using Lasagne `mask_input` parameter
- 'NeuralNet' object has no attribute 'layers_' HOT 1
- Weights sum up to zero
- Future issue with sklearn.cross_validation
- Dependency on both backends in requirements.txt switches off GPU support HOT 3
- Enable to reproduce the last value of trainning when predicting CNN
- enable to reproduce loss value of training when predicting CNN HOT 1
- python 3 support not working with Lasagne? HOT 12
- TypeError: Failed to instantiate <class 'lasagne.layers.pool.MaxPool2DLayer'> with args {'name': 'pool1', 'ds': (2, 2), 'incoming': <lasagne.layers.conv.Conv2DLayer object at 0x7ff765fa29e8>}. Maybe parameter names have changed?
- nolearn now on conda-forge 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 nolearn.