Stack Overflow
Stack Overflow

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
1
vote
0 answers

Different between Caffe and Keras

I have trained LeNet for MNIST using Caffe and now I would like to export this model to be used within Keras. To this end I tried to extract weights from caffe.Net and use them to initialize Keras's network. However, I received different…
Sanparith Marukatat
  • 171
  • 1
  • 1
  • 9
1
vote
1 answer

Float Multi-label Regression in Caffe - loss results

I have trained NN for Regression problem. my data type is HDF5_DATA that made of .jpg images (3X256X256) and float-label array (3 labels). Data-Set create script: import h5py, os import caffe import numpy as np SIZE = 256 # images size with open(…
Z.Kal
  • 426
  • 4
  • 18
1
vote
1 answer

What is the difference of SGDSolver and get_solver method in pycaffe?

I'm trying to implement DNN (mnist) on pycaffe. pretrained_solver = caffe.SGDSolver('mnist/lenet_solver.prototxt') pretrained_solver = caffe.get_solver('mnist/lenet_solver.prototxt') What is the difference between the two lines above? It seems that…
sandman
  • 13
  • 4
1
vote
1 answer

Error in compiling Caffe: ld: can't map file, errno=22

I am trying to compile Caffe and am receiving the following error that I cannot debug: ld: can't map file, errno=22 file '/usr/local/opt/openblas/lib' for architecture x86_64 clang: error: linker command failed with exit code 1 (use -v to see…
Melanie
  • 1,787
  • 3
  • 12
  • 15
1
vote
1 answer

Creating a Training/Validation LMDB for NVIDIA Digits in Python

I'm trying to make a Training/Validation LMDB set for use with NVIDIA Digits, but I can't find any good examples/tutorials. I understand how to create an LMDB database, but I'm uncertain on how to correctly format the data. I get how to create an…
AdmiralJonB
  • 2,038
  • 3
  • 23
  • 27
1
vote
1 answer

Caffe two class multi label classification with hdf5

I have the following structure in a .txt file: /path/to/image x y /path/to/image x y where x and y are integers. What I want to do now is: Create a hdf5 file to use in Caffe ('train.prototxt') My Python code looks like this: import h5py,…
user4911648
1
vote
2 answers

How to use video for traning deep learning (caffe & digits)?

Based on a, b, c, d, Action Recognition with Deep Learning, Long-term Recurrent Convolutional Networks, e, Generic Features for Video Analysis,... there are several methods for analyses video by caffe but what is exactly the input for caffe. Can we…
Video Analysis Deep Learning
  • 338
  • 2
  • 12
1
vote
0 answers

Numpy installation issues with Miniconda2

I'm on a windows 10 machine and trying to install caffe for deep learning. The installation steps asked me to install Miniconda, so I did. I already had Anaconda2 installed on my system. Now when I try to build the solution (using Visual Studio…
Patthebug
  • 4,647
  • 11
  • 50
  • 91
1
vote
1 answer

import caffe, error _message.so

I installed caffe from source code on my Mac os x, but when I type this command: python -c "import caffe" I got this error: Traceback (most recent call last): File "", line 1, in File…
Junhao Wen
  • 31
  • 2
  • 6
1
vote
1 answer

How to create HDF5 file (mutli label classification) out of txt file to use in Caffe

I have the following structure in a .txt file: /path/to/image x y /path/to/image x y where x and y are integers. What I want to do now is: Create a hdf5 file to use in Caffe ('train.prototxt') My Python code looks like this: import h5py import…
user4911648
1
vote
1 answer

logging weights and biases in caffe

I am working on project that requires identifying facial features given a person's face. I formulated this as a regression problem and want to start with a simple conv network and defined the network below. I noticed the output predicted was always…
r3t2
  • 85
  • 6
1
vote
1 answer

Forward from the first of lmdb when using net.forward in pycaffe

I am using pycaffe and my train and test data is in LMDB format. I have created my net like this: net = caffe.Net('train.prototxt', 'c.caffemodel', caffe.TEST) when you call net.forward, implicitly you walk through the LMDB test database one by…
ali khodadadi
  • 65
  • 1
  • 6
1
vote
0 answers

When using pycaffe to run solver.solve(), only one iteration is executed, then the current process is killed

I am using pycaffe to do a multilabel classification task. When I run solver.slove() or solver.step(2), only one iteration is executed, then the current process is killed somehow. ipython console says the kernel died unexpectedly. No other error…
Robinson David
  • 21
  • 1
  • 4
1
vote
0 answers

Error converting prototxt and caffe model from caffe to tensorflow

I am trying to convert caffe prototxt and caffemodel file to a tensorflow and I get the following error : google.protobuf.text_format.ParseError: 33:3 : Expected identifier or number. I did these steps: LAYERS : layers , WINDOW_DATA : "INPUT" etc I…
yaffaity
  • 61
  • 5
1
vote
1 answer

Centos 6.5 make caffe error

all. when I make caffe on centos 6.5, I faced error like this: $ make all PROTOC src/caffe/proto/caffe.proto CXX .build_release/src/caffe/proto/caffe.pb.cc ........ CXX src/caffe/common.cpp AR -o .build_release/lib/libcaffe.a LD -o…
aaronshan
  • 382
  • 3
  • 9
1 2 3
…
99 100