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
0
votes
1 answer

What Loss layer can be used for median frequency balancing? How?

I have written a python script which calculates the median frequency balancing weights for each class during the pixel-wise segmentation. Then, I added a Python Layer to the caffe model definition, which sends the weights to the loss function. Based…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

Data augmentation on-the-fly for semantic segmentation, Is my python layer definition correct?

I am not expert in caffe and Python, but I am trying to learn step by step. I am a little bit confused, so I would really appreciate if experts have a look on my questions. I am working on image segmentation. I am trying to do on-the-fly data…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

cannot convert argument 1 from 'char *' to 'const caffe::NetParameter

i have this issue when building opencl caffe with matlab . "D:\Projects\shawkat\caffe-opencl\caffe-opencl\build\ALL_BUILD.vcxproj" (default target) (1) -> "D:\Projects\shawkat\caffe-opencl\caffe-opencl\build\Matlab\matlab.vcxproj" (default…
Hesham Mohamed
  • 11
  • 3
0
votes
1 answer

How can I get a solid segmentation from a probability map?

I trained the network for my data. Once I ran this: To see the probability map plt.imshow(prob[1], cmap='hot', interpolation='nearest') plt.show() And this is the probability map of Object 1: How can I get the solid segmentation from the…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

Testing FCN on large image sizes

I am testing an FCN-VGG16 network in Caffe. Instead of resizing the input images to a fixed size, I reshape the network each time to the image size. I tried this in both matcaffe and pycaffe. In both cases, it seems that it is able to run for small…
user6137678
  • 3
  • 2
0
votes
1 answer

Does scaling the values to [0,1] affect the CNN learning procedure?

I am working on semantic segmentation using CNNs. I have normalized the values of images to range [0,1]. I have trained my network many times, learning curve seems is learning well, however, the output is always black image. My question is does…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
0 answers

Should I scale the ground truth images in semantic segmentation?

I am applying CNNs for semantic segmentation. I am hoping someone here can recommend. What I am doing now is that I scaled ground truth images. I have 5 classes that I scaled them to (0-1) in Data Layer based on this: transform_param { scale:…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

Deploy and use LeNet on Matlab using MatCaffe

I am having issue with MatCaffe. I trained LeNet using my own dataset (2 classification, 0 or 1) in python successfully and trying to deploy it on Matlab now. Net architecture is from caffe/examples/mnist/lenet.prototxt. All the input images I fed…
Paul Ang
  • 65
  • 1
  • 1
  • 11
0
votes
1 answer

I am getting error while finetuning fcn-alexnet for my single-channel dataset

I am running fcn-alexnet for semantic segmentation, I downloaded the pretrained model. Since my data is single channel,it is showing an error: ERROR: Cannot copy param 0 weights from layer 'conv1'; shape mismatch. Source param shape is 96 3 11 11…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

Should we create different images for each class labels in semantic segmentation?

I will be thankful if you answer my question. I am worried I am doing wrong, because my network always gives black image without any segmentation. I am doing semantic segmentation in Caffe. The output of score layer is <1 5 256 256> batch_size…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

Makefile:517: recipe for target 'matlab/+caffe/private/caffe_.mexa64' failed make: ***

I have been facing this issue. I am using ubuntu 16.04, cuda 8, cudnn 5.1, opencv 3.1, matlab 2014a. I installed opencv3.1 with cuda I want to configure matcaffe. Thanks in advance. Here is my error report. MEX…
Mustansar Fiaz
  • 769
  • 1
  • 5
  • 7
0
votes
0 answers

Many challenges to obtain semantic segmentation results for a long time

I did not have any choice except asking here. I have a lot of difficulties for a long time. I have not been to observe any output from FCN32 :( I trained FCN32 on my data from scratch and always getting a black image. I added gaussian with std= 0.01…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

What I am doing wrong with this semantic segmentation?

Now it is quite a long time (almost two months) that I was working on FCN32 for semantic segmentation of single channel images. I played around with different learning rates and even adding BatchNormalization layer. However, I was not successful to…
S.EB
  • 1,966
  • 4
  • 29
  • 54
0
votes
1 answer

Error in matcaffe installation

The above error showed up when I tried to install matcaffe in ubuntu. I switched to caffe root directory, and ran the following commands: $ cd /home/naved/Desktop/caffe-master $ make all matcaffe $ make mattest My matlab version is 2011a. After…
Sonali Dhali
  • 1
0
votes
1 answer

Do I have to transpose my gray scale image while creating LMDB database?

I am converting a set of images and a set of ground truth images to LMDB database. The purpose is pixel-wise prediction. Most of the codes for creating LMDB from RGB images has a line indicating transpose in CxHxW order, as follows: im =…
S.EB
  • 1,966
  • 4
  • 29
  • 54
1 2 3 4
5
6 7