Comments (4)
Sorry to barge in, I am having trouble with adding this layer in the newer version of caffe. I do as the wiki (s://github.com/BVLC/caffe/wiki/Development) tells me and I end up with this error:
src/caffe/layers/bn_layer.cpp: In instantiation of ‘boost::shared_ptr<caffe::Layer<Dtype> > caffe::Creator_BNLayer(const caffe::LayerParameter&) [with Dtype = float]’:
src/caffe/layers/bn_layer.cpp:276:2: required from here
./include/caffe/layer_factory.hpp:121:67: error: cannot allocate an object of abstract type ‘caffe::BNLayer<float>’
return shared_ptr<Layer<Dtype> >(new type##Layer<Dtype>(param)); \
^
src/caffe/layers/bn_layer.cpp:276:2: note: in expansion of macro ‘REGISTER_LAYER_CLASS’
REGISTER_LAYER_CLASS(BN);
^
In file included from src/caffe/layers/bn_layer.cpp:4:0:
./include/caffe/common_layers.hpp:408:7: note: because the following virtual functions are pure within ‘caffe::BNLayer<float>’:
class BNLayer : public Layer<Dtype> {
^
In file included from ./include/caffe/data_layers.hpp:16:0,
from ./include/caffe/common_layers.hpp:10,
from src/caffe/layers/bn_layer.cpp:4:
./include/caffe/layer.hpp:100:16: note: void caffe::Layer<Dtype>::Reshape(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = float]
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
^
./include/caffe/layer.hpp:304:16: note: void caffe::Layer<Dtype>::Forward_cpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = float]
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
^
./include/caffe/layer.hpp:320:16: note: void caffe::Layer<Dtype>::Backward_cpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<bool>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = float]
virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
^
In file included from ./include/caffe/layer.hpp:10:0,
from ./include/caffe/data_layers.hpp:16,
from ./include/caffe/common_layers.hpp:10,
from src/caffe/layers/bn_layer.cpp:4:
src/caffe/layers/bn_layer.cpp: In instantiation of ‘boost::shared_ptr<caffe::Layer<Dtype> > caffe::Creator_BNLayer(const caffe::LayerParameter&) [with Dtype = double]’:
src/caffe/layers/bn_layer.cpp:276:2: required from here
./include/caffe/layer_factory.hpp:121:67: error: cannot allocate an object of abstract type ‘caffe::BNLayer<double>’
return shared_ptr<Layer<Dtype> >(new type##Layer<Dtype>(param)); \
^
src/caffe/layers/bn_layer.cpp:276:2: note: in expansion of macro ‘REGISTER_LAYER_CLASS’
REGISTER_LAYER_CLASS(BN);
^
In file included from src/caffe/layers/bn_layer.cpp:4:0:
./include/caffe/common_layers.hpp:408:7: note: because the following virtual functions are pure within ‘caffe::BNLayer<double>’:
class BNLayer : public Layer<Dtype> {
^
In file included from ./include/caffe/data_layers.hpp:16:0,
from ./include/caffe/common_layers.hpp:10,
from src/caffe/layers/bn_layer.cpp:4:
./include/caffe/layer.hpp:100:16: note: void caffe::Layer<Dtype>::Reshape(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = double]
virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
^
./include/caffe/layer.hpp:304:16: note: void caffe::Layer<Dtype>::Forward_cpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = double]
virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
^
./include/caffe/layer.hpp:320:16: note: void caffe::Layer<Dtype>::Backward_cpu(const std::vector<caffe::Blob<Dtype>*>&, const std::vector<bool>&, const std::vector<caffe::Blob<Dtype>*>&) [with Dtype = double]
virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
Any ideas as to what's going on ?
from batch_normalization.
Were you able to resolve this? I have the same issue. Thanks in advance.
from batch_normalization.
same here !!!!!!!!!!!!!
Actually I have created a layer "example_layer.cpp" and after doing all the appropriate steps I came up with this error
In instantiation of ‘boost::shared_ptrcaffe::Layer caffe::GetExampleLayer(const caffe::LayerParameter&) [with Dtype = double]’:
src/caffe/layer_factory.cpp:229:1: required from here
src/caffe/layer_factory.cpp:222:74: error: cannot allocate an object of abstract type ‘caffe::ExampleLayer’
return shared_ptr<Layer >(new ExampleLayer(param));
In layer_factory.cpp, I added:
template
shared_ptr<Layer > GetExampleLayer (const LayerParameter& param){
return shared_ptr<Layer >(new ExampleLayer(param));
}
REGISTER_LAYER_CREATOR(Example, GetExampleLayer);
from batch_normalization.
Did any of you guys manage to resolve this? This has been plaguing me all day!
from batch_normalization.
Related Issues (3)
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 batch_normalization.