Stack Overflow
Stack Overflow

Questions tagged [matcaffe]

MatCaffe is a MATLAB interface for the deep-learning framework Caffe.

Caffe is a framework by the Berkeley Vision and Learning Center (BVLC). It is based on and and supports both CPU and GPU processing. Caffe is released under the BSD 2-Clause license.

MatCaffe is a MATLAB interface for the Caffe framework. Use the tag in addition to the tag for problems related to the MATLAB interface.

Useful links:

96 questions
15
votes
2 answers

Multiple category classification in Caffe

I thought we might be able to compile a Caffeinated description of some methods of performing multiple category classification. By multi category classification I mean: The input data containing representations of multiple model output categories…
Aidan Gomez
  • 8,167
  • 5
  • 28
  • 51
10
votes
2 answers

number of parameters in Caffe LENET or Imagenet models

How to calculate number of parameters in a model e.g. LENET for mnist, or ConvNet for imagent model etc. Is there any specific function in caffe that returns or saves number of parameters in a model. regards
khan
  • 531
  • 6
  • 29
7
votes
1 answer

Convert data to leveldb for caffe

I have a bunch of 2D data matrices in Matlab (no image data, but some single precision data). Does anyone know how to convert 2D matlab matrices to the leveldb format which is required by caffe to train a custom neural network? I already did the…
mcExchange
  • 6,154
  • 12
  • 57
  • 103
5
votes
1 answer

Object categories of pretrained imagenet model in caffe

I'm using the pretrained imagenet model provided along the caffe (CNN) library ('bvlc_reference_caffenet.caffemodel'). I can output a 1000 dim vector of object scores for any images using this model. However I don't know what the actual object…
mcExchange
  • 6,154
  • 12
  • 57
  • 103
4
votes
1 answer

caffe fully convolutional cnn - how to use the crop parameters

I am trying to train a fully convolutional network for my problem. I am using the implementation https://github.com/shelhamer/fcn.berkeleyvision.org . I have different image sizes. I am not sure how to set the 'Offset' param in the 'Crop' layer.…
user570593
  • 3,420
  • 12
  • 56
  • 91
4
votes
1 answer

Caffe pretrained models with larger input image sizes

Could you suggest me a trained CNN model which is trained on a larger dataset which supports input image size >400x400 pixels? In my case I have very thin structures, if I rescale the images to the standard size e.g. 224x224 I will loose those…
user570593
  • 3,420
  • 12
  • 56
  • 91
3
votes
1 answer

What parts an parameters of train_val.prototxt, solver.prototxt, and deploy.prototxt should be changed based on our own data?

I am confused about changing the parameters for training a net in caffe based on our own data. Which layers of net we should pay attention more to train the net on our own data? For example, the number of outputs based on the number of classes. I…
S.EB
  • 1,966
  • 4
  • 29
  • 54
3
votes
1 answer

Results for python and MATLAB caffe are different for the same network

I am trying to port MATLAB implementation of MTCNN_face_detection_alignment to python. I use the same version of caffe bindings for MATLAB and for python. Minimal runnable code to reproduce the issue: MATLAB: addpath('f:/Documents/Visual Studio…
Andrey Smorodov
  • 10,649
  • 2
  • 35
  • 42
3
votes
0 answers

How to generate the predicted label in caffe from the output of the last layer?

I have trained my own dataset of images (traffic light images 11x27) with LeNet, using caffe and DIGITS interface. I get 99% accuracy and when I give new images via DIGITS, it predicts the good label, so the network seems to work very well. However,…
Arthur Pesah
  • 235
  • 2
  • 9
3
votes
1 answer

Calculating ROC and AUC in Caffe?

I have trained imagenet in Caffe. Now i am trying to calculate ROC/AUC for my model and the trained model provided by caffe. I have two questions: 1) ROC/AUC is mainly used for binary classes, but i also found that in some cases people used it for…
khan
  • 531
  • 6
  • 29
3
votes
5 answers

Cannot find -lpython2 : MatCaffe installation error

During the build of MatCaffe (Matlab wrapper of Caffe), I face the following error : [ 96%] Built target convert_mnist_data [ 96%] Built target convert_mnist_siamese_data [ 98%] Built target pycaffe [100%] Building Matlab interface:…
Ujjwal Aryan
  • 3,827
  • 3
  • 20
  • 31
2
votes
0 answers

generalized Dice loss for segmentation for Caffe

I am struggling to implement the generalized Dice loss for Caffe as Python Layer, which calculates loss for sub-volumes. I am hoping to get some help here. Or at least, if there is any code, please share the link. I have 5 labels (0: background and…
S.EB
  • 1,966
  • 4
  • 29
  • 54
2
votes
1 answer

Check failed: top_shape[j] == bottom[i]->shape(j): for Concat layer in 3D data

I am trying to train 3D-Unet in caffe. The width, height and depth of different volumes is different. The input shape of the first volume in HDF5 dataset is 1 1 104 281 389 (NxCxDxHxW), when it reaches to the Concat layer (concat_d2c_u2a-b), it is…
sc241
  • 189
  • 17
2
votes
1 answer

How can I start writing the code for my layer?

I have seen that researchers are adding some functionalities to the original version of Caffe and use those layers and functionalities according to what they need and then these versions are shared through Github. If I am not mistaken, there are two…
S.EB
  • 1,966
  • 4
  • 29
  • 54
2
votes
0 answers

Error with Caffe installation (cmake command): LINK_INTERFACE_LIBRARIES

Hi when I want to run cmake for caffe installation it is showing me this: Target "caffe" has an INTERFACE_LINK_LIBRARIES property which differs from its LINK_INTERFACE_LIBRARIES properties. INTERFACE_LINK_LIBRARIES: …
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
2 3 4 5 6 7