Questions tagged [caffe]

Caffe is a fast deep learning framework. It supports CPU and GPU processing. Caffe is released under the BSD 2-Clause license. It is based on C++ but provides APIs for Python and Matlab.

Caffe is a fast framework, developed by Berkeley AI Research (BAIR)/ The Berkeley Vision and Learning Center (BVLC). Its architecture is based on pure and and supports and processing without the need to adapt the code for one of the processing units. Caffe provides and interfaces. Caffe is released under the BSD 2-Clause license.

Caffe users share popular models for different tasks with all kinds of architectures and data in the Model Zoo. These models are learned and applied for problems ranging from simple regression, to large-scale visual classification, to Siamese networks for image similarity, to speech and robotics applications.

Useful Links:

2834 questions
15
votes
2 answers

Caffe: What can I do if only a small batch fits into memory?

I am trying to train a very large model. Therefore, I can only fit a very small batch size into GPU memory. Working with small batch sizes results with very noisy gradient estimations. What can I do to avoid this problem?
Shai
  • 111,146
  • 38
  • 238
  • 371
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
15
votes
2 answers

LSTM module for Caffe

Does anyone know if there exists a nice LSTM module for Caffe? I found one from a github account by russel91 but apparantly the webpage containing examples and explanations disappeared (Formerly http://apollo.deepmatter.io/ --> it now redirects only…
mcExchange
  • 6,154
  • 12
  • 57
  • 103
15
votes
5 answers

Import caffe error

i compiled caffe successfully in my ubuntu machine but cannot import in python. Caffe is installed /home/pbu/Desktop/caffe i tried adding the /home/pbu/caffe/python path to sys.path.append, still not working i am trying to import…
pbu
  • 2,982
  • 8
  • 44
  • 68
15
votes
2 answers

Caffe Multiple Input Images

I'm looking at implementing a Caffe CNN which accepts two input images and a label (later perhaps other data) and was wondering if anyone was aware of the correct syntax in the prototxt file for doing this? Is it simply an IMAGE_DATA layer with…
14
votes
1 answer

install caffe on mac " Error: invalid option: --with-python"

when I install the caffe on mac according to : Remaining dependencies, with / without Python # with Python pycaffe needs dependencies built from source brew install --build-from-source --with-python -vd protobuf brew install --build-from-source -vd…
pf wang
  • 141
  • 1
  • 3
14
votes
3 answers

How can I implement a weighted cross entropy loss in tensorflow using sparse_softmax_cross_entropy_with_logits

I am starting to use tensorflow (coming from Caffe), and I am using the loss sparse_softmax_cross_entropy_with_logits. The function accepts labels like 0,1,...C-1 instead of onehot encodings. Now, I want to use a weighting depending on the class…
Roger Trullo
  • 1,436
  • 2
  • 10
  • 19
14
votes
2 answers

A simple Convolutional neural network code

I am interested in convolutional neural networks (CNNs) as a example of computationally extensive application that is suitable for acceleration using reconfigurable hardware (i.e. lets say FPGA) In order to do that I need to examine a simple CNN…
bromanous
  • 337
  • 1
  • 3
  • 10
14
votes
1 answer

Caffe | solver.prototxt values setting strategy

On Caffe, I am trying to implement a Fully Convolution Network for semantic segmentation. I was wondering is there a specific strategy to set up your 'solver.prototxt' values for the following…
13
votes
2 answers

Conda command fails silently

My anaconda is behaving oddly. conda list, conda debug, conda install, all return nothing. I have already reinstalled anaconda2, checked my path on .profile, and it's all there. 1. which -a conda /Users/me/anaconda2/bin/conda 2. echo…
user7830303
13
votes
1 answer

What is imbalance in image segmentation?

I know the imbalance in an image classification problem such as the cat vs dog classification,if there are too many cat images and too few dog images. But I don't know how to adress an imbalance in a segmentation problem. For example,my task is to…
13
votes
1 answer

Auto-encoders with tied weights in Caffe

From my understanding, normally an auto-encoder uses tied weights in the encoding and decoding networks right? I took a look at Caffe's auto-encoder example, but I didn't see how the weights are tied. I noticed that the encoding and decoding…
dontloo
  • 10,067
  • 4
  • 29
  • 50
13
votes
1 answer

How to convolve two blobs in caffe

In caffe, the convolution layer takes one bottom blob, and convolves it with learned filters (which are initialized using the weight type - "Xavier", "MSRA" etc.). However, my question is whether we can simply convolve two bottom blobs and produce a…
Autonomous
  • 8,935
  • 1
  • 38
  • 77
13
votes
3 answers

'utf-8' codec can't decode byte 0x80

I'm trying to download BVLC-trained model and I'm stuck with this error UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 110: invalid start byte I think it's because of the following function (complete code) # Closure-d…
Ehab AlBadawy
  • 3,065
  • 4
  • 19
  • 31
13
votes
3 answers

Is it possible to switch between BLAS libraries without recompiling program?

For example can I have Atlas, OpenBlas, MKL installed on my Ubuntu 14.04 at the same time and switch between them without recompiling Caffe?
mrgloom
  • 20,061
  • 36
  • 171
  • 301