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
1 answer

Accuracy reported by caffe and pycaffe are different

Below is the train.Prototxt file that is used to train a pretrained model. name: "TempWLDNET" layer { name: "data" type: "ImageData" top: "data" top: "label" include { phase: TRAIN } …
Venky
  • 11
  • 2
1
vote
2 answers

Convert Caffe configuration to DeepLearning4J configuration

I need to implement an existing Caffe model with DeepLearning4j. However i am new to DL4J so dont know how to implement. Searching through docs and examples had little help, the terminolgy of those two are very different. How would you write the…
math_law
  • 391
  • 1
  • 4
  • 16
1
vote
1 answer

Caffe - Python quit unexpectedly while using the libglog.0.dylib plug-in

I am trying to run the deep visualization toolbox using Caffe Specs: Mac OS X 10.10 Python2.7 import caffe works fine when I try to run ./run_toolbox.py I get the alert: Python quit unexpectedly while using the libglog.0.dylib plug-in Console…
MoritzB
  • 61
  • 4
1
vote
0 answers

Training error and validation error are the same - zero accuracy during training

I am basically using caffeNet to do some sort of image classification, with 256 classes. I am feeding the network a list of HDF5 files. But my network doesn't seem to learn, I m having accuracy 0 all the time and the training error and validation…
user2413711
  • 85
  • 2
  • 12
1
vote
0 answers

GPU out of memory when neural network is called from python function

I asked a similar question very recently: I want to use a caffe convolutional neural network in python for pixel-wise classification on an image sequence. Previously, I determined the maximum image size that I can process with my gpu (450x450…
warped
  • 8,947
  • 3
  • 22
  • 49
1
vote
1 answer

Why most of the predicted results are 0 when I use a Caffe BP regression model?

I converted my input data into hdf5 format. And each input data has a shape of 309 dims and a label the input data just as follow: part of the input data like this my net structure as follow: name: "RegressionNet" layer { name: "framert" …
JW .A
  • 11
  • 4
1
vote
1 answer

MDB_MAP_FULL error when write operations are performed on database

I'm trying to edit labels in my own lmdb-database for caffe in python: def WriteLMDB(lmdbpath): lmdb_env = lmdb.open(lmdbpath) lmdb_txn = lmdb_env.begin(write=True) lmdb_cursor = lmdb_txn.cursor() datum = caffe_pb2.Datum() …
Jimmy_st
  • 61
  • 1
  • 10
1
vote
1 answer

Cannot use GPU in CPU-only Caffe: check mode

I am using a legacy set up of caffe which is running on CPU. I switched one line of code from: caffe.set_mode_cpu() to: caffe.set_mode_gpu() but I get the error: Cannot use GPU in CPU-only Caffe: check mode. I checked the Makefile.config and the…
Alejandro Simkievich
  • 3,512
  • 4
  • 33
  • 49
1
vote
1 answer

unexpected labal '38' deepLab error

I am trying to finetune deepLab network used for Semantic Segmentation on my own data which has pixel-wise labels for 2 classes: 'hands' and background. My ground truth segmentation maps are binary maps with 1 for hands and 0 for background. I…
AUKhan
  • 53
  • 7
1
vote
0 answers

Caffe output only returns zero values

I am trying to estimate the depth of a single image. To do so I have an image and a ground_truth = depth_image and a really simple fully convolutional network. My images and depth images have both the shape 1x227x227 I have a train_val.prototxt like…
user4911648
1
vote
0 answers

Local convolution in Keras or Matconvnet

I am new to implementing CNNs. I have some experience with Keras and Matconvnet. I am trying to implement region layer of the paper:DRML network for AU detection which as follows :- Here the input to 64 filters in Region layer is a different…
Pranjal Sahu
  • 1,469
  • 3
  • 18
  • 27
1
vote
1 answer

LNK1104 Visual studio 2015

I am trying to build Caffe Deep Learning Network solution using Windows and I have literally tried everything to make it work. I found similar questions, but they were using VS 2010 or 2013 and I don't have any of the options listed in most of the…
Johhny Bravo
  • 199
  • 3
  • 15
1
vote
0 answers

How to increase Caffe nVidia Pascal GPU utilization?

I've got an nVidia Pascal GPU running Caffe on Windows 10. When I run NSight on Visual Studio, forward propagation in testing mode shows only 4.3% utilization of the GPU with less than 1% use of the 16 kernel calls. I'm working on a real time…
empty
  • 5,194
  • 3
  • 32
  • 58
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
1 answer

How do I compute the convolution input shape/size?

If I have the output shape, filter shape, strides and padding, filter shape: [kernel_height, kernel_width, output_depth, input_depth] output shape: [batch, height, width, depth] strides=[1,1,1,1] padding='VALID' Can I get the input shape? For…
DunkOnly
  • 1,682
  • 4
  • 17
  • 39
1 2 3
…
99 100