caffe

问题 I'm new to caffe. thank you guys! in https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto I saw 1 uncommented enum variable phase. it has 2 option TRAIN and TEST. enum Phase { TRAIN = 0; TEST = 1; } how did they work? I saw a model recently has this 2 phase too. the .prototxt file looks like: name: "CIFAR10_full" layer { name: "cifar" type: "Data" top: "data" top: "label" data_param { source: "CIFAR-10/cifar10_train_lmdb" backend: LMDB batch_size: 200 } transform_param {

问题 I executed make pycaffe in the caffe directory and it worked fine. I also did this: gsamaras@gsamaras-A15:~/caffe/python$ export PYTHONPATH=$PYTHONPATH:/home/gsamaras/caffe/python but when I try to import caffe in another project, I get this: ImportError: No module named caffe How to fix this? Also note that in the Makefile.config of caffe, there is this line: PYTHON_INCLUDE := /usr/include/python2.7 \ <-- correct /usr/lib/python2.7/dist-packages/numpy/core/include <-- doesn't exist My numpy

问题 I'm trying run a simple code with caffe that should open deploy.prototxt but it couldn't open the file and throws this error RuntimeError: Could not open file /home/ebadawy/git/caffemodels/bvlc_reference_caffenet/deploy.prototxt this is my code import numpy as np import matplotlib.pyplot as plt plt.rcParams['figure.figsize'] = (10, 10) # large images plt.rcParams['image.interpolation'] = 'nearest' # don't interpolate: show square pixels plt.rcParams['image.cmap'] = 'gray' # use grayscale

问题 I am working on implementing Hinton's Knowledge distillation paper. The first step is to store the soft targets of a "cumbersome model" with a higher temperature (i.e. I don't need to train the network, just need to do forward pass per image and store the soft targets with a temperature T ). Is there a way I can get the output of Alexnet or googlenet soft targets but with a different temperature? I need to modify the soft-max with pi= exp(zi/T)/sum(exp(zi/T) . Need to divide the outputs of

问题 I am using BatchNorm layer. I know the meaning of setting use_global_stats that often set false for training and true for testing/deploy. This is my setting in the testing phase. layer { name: "bnorm1" type: "BatchNorm" bottom: "conv1" top: "bnorm1" batch_norm_param { use_global_stats: true } } layer { name: "scale1" type: "Scale" bottom: "bnorm1" top: "bnorm1" bias_term: true scale_param { filler { value: 1 } bias_filler { value: 0.0 } } } In solver.prototxt, I used the Adam method. I found

问题 DLDR How do I point the cmake at boost-python3 library? It is not automatically detected by cmake. I'm trying to build caffe for Python 3.6 using the provided cmake. My system specs: Python 3.6.5, Anaconda custom (64-bit) Mac OS 10.13.6 No CUDA I've installing boost with brew, e.g. brew install boost boost-python3 I can see the boost libraries using find / -name libboost* 2>/dev/null . They occur in three directories /usr/local/Cellar/boost/1.67.0_1/lib/ /usr/local/lib/ -> symlink to above

问题 After going through the Caffe tutorial here: http://caffe.berkeleyvision.org/gathered/examples/mnist.html I am really confused about the different (and efficient) model using in this tutorial, which is defined here: https://github.com/BVLC/caffe/blob/master/examples/mnist/lenet_train_test.prototxt As I understand, Convolutional layer in Caffe simply calculate the sum of Wx+b for each input, without applying any activation function. If we would like to add the activation function, we should

问题 I'm using the pretrained imagenet model provided along the caffe (CNN) library ( 'bvlc_reference_caffenet.caffemodel' ). I can output a 1000 dim vector of object scores for any images using this model. However I don't know what the actual object categories are. Did someone find a file, where the corresponding object categories are listed? 回答1: You should look for the file 'synset_words.txt' it has 1000 line each line provides a description of a different class. For more information on how to

问题 In this tutorial, the output volumes are stated in output [25], and the receptive fields are specified in output [26]. Okay, the input volume [3, 227, 227] gets convolved with the region of size [3, 11, 11] . Using this formula (W−F+2P)/S+1 , where: W = the input volume size F = the receptive field size P = padding S = stride ...results with (227 - 11)/4 + 1 = 55 i.e. [55*55*96] . So far so good :) For 'pool1' they used F=3 and S=2 I think? The calculation checks out: 55-3/2+1=27 . From this

问题 I'm building one but, and when I use the custom train function provided on lenet example with a batch size bigger than 110 my accuracy gets bigger than 1 (100%). If I use batch size 32, I get 30 percent of accuracy. Batch size equal 64 my net accuracy is 64. And batch size equal to 128, the accuracy is 1.2. My images are 32x32. Train dataset: 56 images of Neutral faces. 60 images of Surprise faces. Test dataset: 15 images of Neutral faces. 15 images of Surprise faces. This is my code: def