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
2 answers

Install PyQt4 via conda for caffe model

When I try to run the SEC caffe model on from here: https://github.com/kolesman/SEC I geht the error: ImportError: No module named PyQt4 python demo.py --model SEC.caffemodel --image /data/out/dataset/center/1475186965759787059.jpg --smooth --output…
Orlando
  • 1,576
  • 2
  • 15
  • 20
1
vote
1 answer

How can I solve mismatch input size in caffe visualization?

I have trained my network with AlexNet model and I have the model weights. Now I want to test it on my test data. here is part of my code: import matplotlib.pyplot as plt from PIL import Image import cv2 import numpy as np # - - - - - - - - - - - -…
user6726469
  • 231
  • 1
  • 3
  • 14
1
vote
0 answers

How to get output from hdf5 input in caffe?

I fed the network defined below with a hdf5 files name: "match_layers" layers { name: "data" type: HDF5_DATA top: "feat1" top: "feat2" hdf5_data_param { source: "vgg16_train_test_pair.h5list" …
Fangxin
  • 781
  • 1
  • 7
  • 13
1
vote
1 answer

Implement Bhattacharyya loss function using python layer Caffe

Trying to implement my custom loss layer using python layer,caffe. I've used this example as the guide and have wrote the forward function as follow: def forward(self,bottom,top): score = 0; self.mult[...] =…
Saeed
  • 742
  • 1
  • 7
  • 21
1
vote
1 answer

Using im2col layer, reshape layer and inner product layer to implement locally connected layer?

I am using caffe and it doesn't have a locally connected layer. So any example on how to use im2col layer, reshape layer and inner product layer to implement locally connected layer? Thanks
Mickey Shine
  • 12,187
  • 25
  • 96
  • 148
1
vote
0 answers

how to save feature map to a image for visualization in terminal?

import matplotlib.pyplot as plt 7 def vis_square(data): 8 """Take an array of shape (n, height, width) or (n, height, width, 3) 9 and visualize each (height, width) thing in a grid of size approx. sqrt(n) by sqrt(n)""" 10 …
Dylan
  • 1,315
  • 3
  • 12
  • 19
1
vote
1 answer

`caffe': malloc(): memory corruption when snapshotting to disk

I am training a simple network. Having trouble to get caffe run, I decided to test run on 20 images only. But I can't get past this following error message. I have rebuilt caffe as suggested by other posts but didn't solve the issue. I1008…
user2413711
  • 85
  • 2
  • 12
1
vote
1 answer

caffe batchnorm layer affect base_lr?

I saw the following code under caffe framework. The whole code is trying to write caffe train_val.prototxt and solver.prototxt. # Use different initial learning rate. if use_batchnorm: base_lr = 0.0004 else: base_lr = 0.00004 Why is the…
李德健
  • 51
  • 3
1
vote
1 answer

Regression in Caffe: Prediction is highly erroneous

I've been doing a single label regression problem in Caffe. The input contains 5 hdf5 files which I have generated independently using different images. I first tested my network with a single hdf5 file and ran 10000 iterations with about 800…
magneto
  • 97
  • 6
1
vote
1 answer

Why should I rebuild Caffe each time I want to use a new package?

I am very new to Ubuntu and I just started learning Caffe. The question might come stupid as I have no idea about how 'make' command works. Anyway, I installed Caffe following the instruction in this link: Caffe Installation and everything works…
user3157047
  • 479
  • 5
  • 15
1
vote
1 answer

Creating multilabel HDF5 file for caffe

I created HDF5 data using the following python script and placed HDF5 data layer. However, when I tried to train caffe using this data it keeps complaining Check failed: num_spatial_axes_ == 2 (0 vs. 2) kernel_h & kernel_w can only be used for 2D…
user2413711
  • 85
  • 2
  • 12
1
vote
1 answer

ImportError: No module named caffe while running spark-submit

While running a spark-submit on a spark standalone cluster comprised of one master and 1 worker, the caffe python module does not get imported due to error ImportError: No module named caffe This doesn't seem to be an issue whenever I run a job…
Julian Bici
  • 23
  • 6
1
vote
1 answer

Feeding long 1D vector data, 1D vector label to Caffe

Newbie to caffe here. I am trying to replicate LeNet on my own dataset. My training data is a 1D data which can be represented as 1x3000 vector. For each 1x3000 vector I have a label which is another 1D vector of 1x64 dimension binary vector. I have…
user2413711
  • 85
  • 2
  • 12
1
vote
1 answer

net surgery on a custom caffe model

I'm trying to modify the weights of a caffemodel which is part of a caffe-branch called Deep Lab. Although there is a tutorial on how to do net surgery, when I try to do the same with my custom caffemodel the python kernel dies always on the…
mcExchange
  • 6,154
  • 12
  • 57
  • 103
1
vote
1 answer

Understanding net_surgery in caffe

I'm following the net_surgery.ipynb example of caffe which explains how to modify the weights of a saved .caffemodel. However since I'm quite new to python I can't understand some of the syntax. Can someone explain me what the 7th line starting with…
mcExchange
  • 6,154
  • 12
  • 57
  • 103
1 2 3
…
99
100