Questions tagged [caffe2]

Caffe2 is an open-source deep learning framework, which is developed and maintained by Facebook, and is based on the Caffe framework.

Caffe2 is a deep learning framework, which is based on the framework. It is developed and maintained by Facebook, and released under the Apache 2.0 license, on GitHub.

Caffe2 is an improved / redesigned version of Caffe. A presentation by Caffe2's lead developer Yangqing Jia, held at CVPR 2015, shows some of the consideration of the redesign.

Useful links

116 questions
3
votes
1 answer

Adding a custom python layer in caffe2

Adding a python layer in caffe was fairly straightforward (creating a child class that inherits from caffe.layer and adding four basic methods, as described here and here. However, adding a custom python layer in caffe2 is not as straightforward to…
Feynman27
  • 3,049
  • 6
  • 30
  • 39
3
votes
0 answers

Caffe2 installed correct but can't load glog library

I pip installed caffe2 via a "Prebuilt Caffe2 Python Wheel" without an error. But running the first example I get the following error message which seems not be able to find/load "/usr/local/opt/glog/lib/libglog.0.dylib". If I import caffe2.python…
digit
  • 1,513
  • 5
  • 29
  • 49
3
votes
1 answer

how to know if Caffe2 has been successfully installed or not in ubuntu 16.04?

I am trying install caffe2 as instructed, on https://caffe2.ai/docs/getting-started.html?platform=ubuntu&configuration=compile, but when I try to run the command python -c 'from caffe2.python import core' 2>/dev/null && echo "Success" || echo…
Abby Jangir
  • 55
  • 2
  • 12
3
votes
2 answers

How to install Caffe2 on Windows 7?

Facebook has released caffe2 recently - deep learning library. How to install on Windows 7 system?
a3.14_Infinity
  • 5,653
  • 7
  • 42
  • 66
2
votes
1 answer

Enable multi-threading on Caffe2

When compiling my program using Caffe2 I get this warnings: [E init_intrinsics_check.cc:43] CPU feature avx is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. [E…
ClaudiaR
  • 3,108
  • 2
  • 13
  • 27
2
votes
4 answers

PyTorch dll issues for Caffe2

I am using a Windows 10 Machine and after re-installing Anaconda and all of the packages I had previously, including torchvision, torch and necessary dependencies, I am still getting this error: OSError: [WinError 127] The specified procedure could…
mmmmm
  • 21
  • 1
  • 2
2
votes
0 answers

How can we load caffe2 pre-trained model in keras?

I have pre-trained weights for maskrcnn in caffe2 in .pkl extension and it's config file as yaml. If I try to load it directly it throws Improper config format: . Is there a way to use it without installing caffe2. Config.py MODEL: TYPE:…
hR 312
  • 824
  • 1
  • 9
  • 22
2
votes
1 answer

Modifying loss function faster rcnn detectron

For my thesis I am trying to modify the loss function of faster-rcnn with regards to recognizing table structures. Currently I am using Facebooks Detectron. Seems to be working great but I am now actively trying to modify the loss function.…
2
votes
0 answers

How to install Caffe2 with Anaconda Python 3.6

According to the site of Caffe2, Python 3 support for Caffe2 is still experimental. I want to use Caffe2 with Anaconda Python 3.6. How to do install Caffe2 successfully in this scenario? Both pip install caffe2 and conda install caffe2 have failed.…
Preetom Saha Arko
  • 2,588
  • 4
  • 21
  • 37
2
votes
1 answer

how to apply "Gather" operation like numpy in Caffe2?

I am new to Caffe2, and I want to compose an operation like this: Numpy way example code pytoch way example code My question is, how to compose Caffe2 operators to make the same operators like above? I have tried some compositions but still I…
2
votes
0 answers

How can I get the size of a leveldb dataset using Python?

is there a function or an efficient way to get the size of a leveldb dataset using python? I am working with big datasets which contain more than 400,000 elements. I am using Caffe2 for deep learning. Thanks in advance.
CarlosYev
  • 31
  • 1
  • 4
2
votes
1 answer

Why USE_OPENCV is OFF in PyTorch installation?

In CMakeLists.txt in pytorch folder, use Opencv is ON. option(USE_OPENCL "Use OpenCL" OFF) option(USE_OPENCV "Use OpenCV" ON) option(USE_OPENMP "Use OpenMP for parallel code" OFF) In setup.py, variable is set with Opencv as use_env_vars = ['CUDA',…
batuman
  • 7,066
  • 26
  • 107
  • 229
2
votes
1 answer

Application gets stuck while we are Instantiating a Caffe2 predictor

Application gets stuck while we are Instantiating a Caffe2 predictor! Tools I use: Android Studio 3.0.1 Build #AI-171.4443003, built on November 9, 2017 JRE: 1.8.0_152-release-915-b01 amd64 JVM: OpenJDK 64-Bit Server VM by JetBrains s.r.o Linux…
2
votes
2 answers

Is there a way to use fastText's word representation process in parallel?

I am new to fastText, a library for efficient learning of word representations and sentence classification. I am trying to generate word-vector for huge data set. But in single process it's taking significantly long time. So let me put my questions…
Shukla
  • 91
  • 6
2
votes
0 answers

Error with kIndexInFileMessages while compiling Caffe2 on Windows 10 system

I have been trying to compile caffe2 on a windows 10 system with cuda for the past week. The library is clearly not ready for windows release as there were many problem during the installation. After various tweaking on CMake and running in on git…
yapws87
  • 1,809
  • 7
  • 16