caffe

问题 I am working on semantic segmentation using CNNs. I have an imbalance number of pixels for each class. Based on this link, I am trying to create weight matrix H in order to define Infogain loss layer for my imbalance class members. My data has five classes. I wrote the following code in python: Reads a sample image: im=imread(sample_img_path) Counts the number of pixels of each class cl0=np.count_nonzero(im == 0) #0=background class . . cl4=np.count_nonzero(im == 4) #4=class 4 output: 39817

问题 I'm trying to read weight and bias in a caffe network with pycaffe. Here is my code weight = net.params[layer_name][0].data bias = net.params[layer_name][1].data But, some layers in my network has no bias, so that there will be an error which is Index out of range . So my question is can I use if(net.params[layer_name][1] exists): bias = net.params[layer_name][1].data to control the assignments to bias ? And how to write the code? 回答1: You can simply iterate over net.params[layer_name] :

问题 I modify the FCN net and design a new net,in which I use two ImageData Layer as input param and hope the net produces a picture as output. here is the train_val.prototxt and the deploy.prototxt the original picture and the label are both gray scale pics and sizes are 224*224. I've trained a caffemodel and use infer.py to use the caffemodel to do a segmentation,but meet the error: F0505 06:15:08.072602 30713 net.cpp:767] Check failed: target_blobs.size() == source_layer.blobs_size() (2 vs. 1)

问题 I have a data layer with HDF5 type. It contains both Train and Test phase as expected name: "LogisticRegressionNet" layer { name: "data" type: "HDF5Data" top: "data" top: "label" include { phase: TRAIN } hdf5_data_param { source: "examples/hdf5_classification/data/train.txt" batch_size: 10 } } layer { name: "data" type: "HDF5Data" top: "data" top: "label" include { phase: TEST } hdf5_data_param { source: "examples/hdf5_classification/data/test.txt" batch_size: 10 } } I want to use python to

问题 I am creating a network using Caffe, for which I need to define my own layer. I would like to use the Python layer for this. My layer will contain some learned parameters. From this answer, I am told that I will need to create a blob vector for this. Is there any specification that this blob will need to follow, such as constraints in dimensions, etc.? Irrespective of what my layer does, can I create a blob of one dimension, and use any element, one each, of the blob for any computation in

问题 I'm training caffenet with multilabel data. However the lost is not decreasing during training phase. I'm now trying to check if the backward() is not working properly. I have this code to check if there is a gradient. import numpy as np import os.path as osp import matplotlib.pyplot as plt from pprint import pprint from copy import copy % matplotlib inline plt.rcParams['figure.figsize'] = (6, 6) caffe_root = '../' # this file is expected to be in {caffe_root}/examples sys.path.append(caffe

问题 This is a really weird error, partly a follow-up to the previous question(Deconvolution layer FCN initialization - loss drops too fast). However I init Deconv layers (bilinear or gaussian), I get the same situation: 1) Weights are updated, I checked this for multiple iterations . The size of deconvolution/upsample layers is the same: (2,2,8,8) First of all, net_mcn.layers[idx].blobs[0].diff return matrices with floats, the last Deconv layer ( upscore5 ) produces two array with the same

问题 I am using apollocaffe and Reinspect. Apollocaffe is in c++ library and Reinspect is in python that uses apollocaffe library . I build apollocaffe using g++-4.8.5. When I run the command python -m pdb train.py config-- config.json , I have this error, ImportError: '/home/xxx/Softwares/Libraries/apollocaffe_22_3_17/build_debug/lib/libcaffe.so: undefined symbol: _ZdlPvm' What could be wrong? 回答1: Based on this (theano) thread, looks like you're using incompatible gcc versions. Try to move to

问题 I am trying to load data to the network, since I need a custom data input (3 tops: 1 for data image, 2 for different labels) I load the data with HD5F files. It looks similar to this: layer { name: "data" type: "HDF5Data" top: "img" top: "alabels" top: "blabels" include { phase: TRAIN } hdf5_data_param { source: "path_to_caffe/examples/hdf5_classification/data/train.txt" batch_size: 64 } } I want to preprocess the images using Caffe's own Transformer (for standard), how can I do this when I

问题 I want to set up a caffe CNN with python, using caffe.NetSpec() interface. Although I saw we can put test net in solver.prototxt , I would like to write it in model.prototxt with different phase. For example, caffe model prototxt implement two data layer with different phases: layer { name: "data" type: "Data" top: "data" top: "label" include { phase: TRAIN } .... } layer { name: "data" type: "Data" top: "data" top: "label" include { phase: TEST } .... } How should I do in python to get such