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.

Filter by
Sorted by
Tagged with
1
vote
1answer
23 views

How to backup a Caffe (DL framework) project? The Caffe folder (downloaded from GitHub) can't be copied or compressed

I am using Ubuntu18.04 and Caffe deep learning framework to do my project. However, when I tried to backup my project, I found that the Caffe folder (downloaded from GitHub) can't be copied or ...
1
vote
1answer
1k views

Is GEMM used in Tensorflow, Theano, Pytorch

I know that Caffe uses GEneral Matrix to Matrix Multiplication (GEMM) which is part of Basic Linear Algebra Subprograms (BLAS) library for performing convolution operations. Where a convolution is ...
1
vote
0answers
55 views

Replacing VGG by LeNet Caffe model

this code works with a VGG caffe model (VGG_ILSVRC_19_layers.caffemodel). When I tried to change the model to a LeNet caffemodel (below the prototxt file), I got the following error. In 6 module of ...
1
vote
0answers
309 views

How to build a Caffe dataset for object detection with ImageNet data

I am new into Caffe and I have some trouble in understanding how should I create a dataset for object detection. I have downloaded some images and bounding boxes from ImageNet. The bounding boxes are ...
1
vote
1answer
571 views

How to divide MNIST training dataset into subparts? [closed]

Background: I am trying to train different sub-samples of MNIST dataset(1 model for 10,000 , another model for 20,000 samples, and so on until a model for all 60,000 training samples) using Caffe. ...
5
votes
1answer
341 views

What is the fully-convolutional model?

What is the fully-convolutional model? Is fully-convolutional model a model that has only convolutional layers (with Batch-norm and Activation) and has not any: max-pool, fully-connected, and other ...
6
votes
2answers
8k views

What is the different between Fine-tuning and Transfer-learning?

Usually the neural network training has at least 2 steps: first trained on a large set of some standard data (ImageNet, ...) and then the resulting weights are trained on a small set of my data (in ...
2
votes
2answers
2k views

Why do we need for Shortcut Connections to build Residual Networks?

Why do we need for Shortcut Connections to build Residual Networks, and how it help to train neural networks for classification and detection?
1
vote
0answers
184 views

Design strategies for higher resolution images for Convolutional neural network?

By BVLC/Caffe examples cifar10, it has 3 convolution layers with pool/norm and its accuracy increases to around 82 easily. Now I want to increase my resolution by downloading the 10 classes of images ...
1
vote
1answer
503 views

Fine tuning CNN with imbalance data gives good results - not sure why

I'm fine tuning with caffenet for a 3 classes classification problem. I have 100 instances of class A, 90 instances of class B and 30 instances of class C. I thought that my net would be biased toward ...
1
vote
0answers
288 views

Intuition of group parameter in Caffe Layer

I am confused about the group parameter in caffe convolution layer. Image I have an input of 20x3x227x227 and filter size is ...
3
votes
3answers
1k views

Generating Image data sets for training CNNs

I want to build a system that recognises (with a given uncertainty) the make and model of a car from an image. I have decided to use Convolution Neural Networks, specifically the Caffe framework. My ...
1
vote
0answers
350 views

L2 regularization in caffe

I have a lasgane code. I want to create the same network using caffe. I could conver the network.But i need help with the hyperparameters in lasagne. The hyperparameters look like: ...
0
votes
1answer
2k views

Caffe net.predict() , predict same probability

I trained pre-trained ResNet-101 following caffe model(By Kaiming He github) with 800000 data for training and 200000 data for validation. After I train this model, I got 59% accuracy for 1st and ...
2
votes
0answers
545 views

Fisher's Iris data set with Caffe

I am trying to use Caffe on the usual Fisher's Iris data set (150 flowers, each having 4 features, and split into 3 classes): if a flower belong to class 1 (setosa), the network output should be [1, ...