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
1
vote
1 answer

Is it possible to use pretrained model after adding elementwise layers?

I am using a pre-trained model which I want to add Elementwise layer that products the output of two layers: one layer is output of convolution layer 1x1x256x256 and the other is also the output of convolution layer 1x32x256x256. My question is: If…
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
0 answers

What kind of on-the-fly artificial data augmentation can be applied for semantic segmentation?

I have almost 5223 and 577 images for training and validation sets, respectively. I am applying CNNs for image segmentation and would like to do artificial on-the-fly data augmentation. I have installed Caffe latest version. I am wondering whether…
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
0 answers

Caffe with matlab support build issues

I am having issues building caffe with matlab wrapper. Using the following build commands cmake -DCUDA_HOST_COMPILER:STRING=gcc-5 -DBUILD_matlab=ON .. make I get [...]/caffe/matlab/+caffe/private/caffe_.cpp:18:27: fatal error: caffe/caffe.hpp: No…
MagoNick
  • 331
  • 1
  • 4
  • 17
1
vote
0 answers

Linking libraries error while installing Caffe:

I had already installed Caffe many times. This time I tried to download the newest version of that, however, I am facing a lot of issues while installation. I do not know how to solve it. I tried two ways: building by make and make all. By cmake, I…
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
1 answer

What is the concept of mini-batch for FCN (semantic segmentation)?

What is the concept of mini-batch when we are sending one image to FCN for semantic segmentation? The default value in data layers is batch_size: 1. That means every forward and backward pass, one image is sent to the network. So what will be the…
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
2 answers

I am getting a black image in FCN32

I trained FCN32 from the scratch on my data, unfortunately I am getting a black image as output. Here is the loss curve. I am not sure whether this training loss curve is normal or not, or whether I have done something wrong or not. I really…
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
1 answer

After adding Xavier and bias_filler, the loss values starts becoming negative. Why?

After I added xavier initialization to every convolution layer, the loss starts becoming negative. Could someone give any suggestion/reason? I added the following lines to all convolutional layers: weight_filler { type: "xavier" } …
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
0 answers

Getting error for adding InfogainLoss layer?

I followed the instructions here to create weight matrix for classes and add the Infogainloss function, which is able to tackle my imbalance data. The few last layers .... layer { name: "score_fr" type: "Convolution" bottom:…
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
1 answer

Getting error on [base_conv_layer.cpp:122] Check failed: channels_ % group_ == 0 (1 vs. 0) , how to solve it?

When I am trying to train FCN32 for semantic segmentation on my own data, I am getting this error: I0106 12:57:53.273977 19825 net.cpp:100] Creating Layer upscore_sign I0106 12:57:53.273982 19825 net.cpp:434] upscore_sign <- score_fr_sign …
S.EB
  • 1,966
  • 4
  • 29
  • 54
1
vote
1 answer

Matcaffe on Ubuntu 16.04

I have been trying to compile Matcaffe in Ubuntu 16.04. I could successfully compile caffe and pycaffe (using gcc 5). However since Ubuntu 16.04 comes with gcc 5, and MATLAB R2016b is compatible with gcc 4.9, I got following warning during…
user1586259
  • 11
  • 1
  • 3
1
vote
2 answers

Image Channel Mismatch in Caffe

I know this may be better asked in caffe user group but I cannot access the user group and don't know where to pose the question as I'm not sure whether this needs to be raised as an issue in git. In any case, what I'm doing is this: I have a set of…
words_of_wisdom
  • 163
  • 3
  • 16
1
vote
2 answers

Read LevelDB format from Matlab

I am working on Caffe. I already extract features using extract_features.bin, it will create a result as this figure below. It said that the feature will stored in LevelDB format. But, since I almost work in MATLAB, so I want to read this output on…
nafilatur2724
  • 35
  • 2
1
vote
0 answers

matcaffe - different image sizes in testing and training

My training prototxt file uses images of size 400x400. I dont use any cropping, image resizing in the training. I am finetuning the Alexnet for my problem. In my deploy.protxt file I define image size as 350x350. I am using matcaffe for training as…
user570593
  • 3,420
  • 12
  • 56
  • 91
1
vote
1 answer

Reading dangerously large protocol message Caffe warning

I am trying to fine tune the fully convolutional nets for my problem. I am getting the following warning. Why I am getting this warning? [libprotobuf WARNING google/protobuf/io/coded_stream.cc:505] Reading dangerously large protocol…
user570593
  • 3,420
  • 12
  • 56
  • 91
1
vote
1 answer

Is it possible to add new layers to Caffe?

Is it possible for me to add a new layer (for a different loss) with Caffe? How can I do it using Matlab or Python?
user570593
  • 3,420
  • 12
  • 56
  • 91
1 2
3
4 5 6 7