我想在
python中实现
VGG Face Descriptor.但我一直收到一个错误：
TypeError: can only concatenate list (not “numpy.ndarray”) to list
我的代码：
import numpy as np
import cv2
import caffe
img = cv2.imread("ak.png")
img = cv2.cvtColor(img,cv2.COLOR_RGB2BGR)
net = caffe.Net("VGG_FACE_deploy.prototxt","VGG_FACE.caffemodel",caffe.TEST)
print net.forward(img)
你能帮助我吗 ？
更新1
这个工作代码是matlab中的示例
% Copyright (c) 2015,Omkar M. Parkhi
% All rights reserved.
img = imread('ak.png');
img = single(img);
Img = [129.1863,104.7624,93.5940] ;
img = cat(3,img(:,:,1)-averageImage(1),...
img(:,2)-averageImage(2),3)-averageImage(3));
img = img(:,[3,2,1]); % convert from RGB to BGR
img = permute(img,[2,1,3]); % permute width and height
model = 'VGG_FACE_16_deploy.prototxt';
weights = 'VGG_FACE.caffemodel';
caffe.set_mode_cpu();
net = caffe.Net(model,weights,'test'); % create net and load weights
res = net.forward({img});
prob = res{1};
caffe_ft = net.blobs('fc7').get_data();
解决方法
要使用python接口,您需要先将输入图像转换为网络
img = caffe.io.load_image( "ak.png" ) img = img[:,::-1]*255.0 # convert RGB->BGR avg = np.array([93.5940,129.1863]) # BGR mean values img = img - avg # subtract mean (numpy takes care of dimensions :)
现在img是H-by-W-by-3 numpy数组.
Caffe期望其输入为4D：batch_index x channel x width x height.
因此,您需要转置输入并添加单个维度以表示“batch_index”前导维度
img = img.transpose((2,1)) img = img[None,:] # add singleton dimension
现在你可以运行前进传球了
out = net.forward_all( data = img )