caffe-theano-conversion's People
Forkers
bluemellophone lixiangnlp euwen twistedmove yingmin-li malkocb soroushmehr anenbergb jiangzhw yochju idofr maciejklimek dgq2010 magicalfox fartashf vzhangmeng726 svebk imclab sandy4321 milestonesvn belvo utepdatamining liyong3forever wanjinchang hfxunlp jmliu88 arasharchor cjl2183 hyzcn shizhang124 pencilandbikecaffe-theano-conversion's Issues
Convert theano to caffe model
is there a way to conv from theano's model to caffe?
BaseModel problem
Hello,I run your code as you describe.But when I run tests.py, I find that the terminal print the information 'too many indices for array,====== [ ERROR: Caffe was not found. Continuing... ] ======'.I am sure this is not caused by caffe path.So when I debug the code, I find it is caused by the code 'self.forward = theano.function([symbolic_input], outputs)'. and I wonder that why the nOutputs is set to 1,this cause 'print np.sum((fprop[fprop.keys()[0]][:,:,0,0] - outlist[-1])**2)' in test_similarity function of test.py arise that error. Then I turn the code 'outputs = [lay.get_output() for lay in self.all_layers[:nOutputs]] ' into outputs = layers.get_output(self.all_layers[-1]), but it still has problem,ImportError: ('The following error happened while compiling the node', <pylearn2.sandbox.cuda_convnet.filter_acts.FilterActs object at 0xba168d0>(GpuContiguous.0, GpuContiguous.0), '\n', '/home/scw4150/.theano/compiledir_Linux-3.2--generic-x86_64-with-Ubuntu-12.04-precise-x86_64-2.7.3-64/tmpzKRg5C/7e4013877baee663026e238eedaae7fa.so: undefined symbol: _ZN8NVMatrixC1EPK11CudaNdarrayiiPKc', '[<pylearn2.sandbox.cuda_convnet.filter_acts.FilterActs object at 0xba168d0>(<CudaNdarrayType(float32, 4D)>, <CudaNdarrayType(float32, 4D)>)]')
lasagne conv strides keyword changed to stride
Lasagne's <Conv2DLayer>
etc. use the <stride>
keyword, the use of <strides>
in the implementation should be changed to match this
Lasagne & Theano Updates
base.py:
self.all_layers = layers.get_all_layers(last_layer)
should now be self.all_layers = layers.get_all_layers
_old(last_layer)
parse_from_protobuf_caffe.py:
caffe.TEST
is no longer accessible (from what I can tell)
lasagne version
Dear an-kunar,
I try to convert caffe model to theano but always meet error. I think it's the version problem of lasagne. Would you please tell me which version you used when made this project?
Thanks a lot
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.