FCN中单张图片可视化的代码

仅参考

import numpy as npfrom PIL import Imageimport sysimport matplotlib.pyplot as plt#import scipy.io as sioimport caffe#import caffeimport glob#fileList=glob.glob('/home/yangwb/JPEGImages/*.jpg')#f=open("/home/yangwb/MYwork/FCN/fcn.berkeleyvision.org-master/data/VOC2012/ImageSets/Segmentation/seg11valid1.txt")#lines=f.readlines()def vis_square(data):    # 输入的数据为一个ndarray，尺寸可以为(n, height, width)或者是 (n, height, width, 3)    # 前者即为n个灰度图像的数据，后者为n个rgb图像的数据    # 在一个sqrt(n) by sqrt(n)的格子中，显示每一幅图像    # 对输入的图像进行normlization    data = (data - data.min()) / (data.max() - data.min())    # 强制性地使输入的图像个数为平方数，不足平方数时，手动添加几幅    n = int(np.ceil(np.sqrt(data.shape[0])))    # 每幅小图像之间加入小空隙    padding = (((0, n ** 2 - data.shape[0]),               (0, 1), (0, 1))                 # add some space between filters                           + ((0, 0),) * (data.ndim - 3))  # don't pad the last dimension (if there is one)    data = np.pad(data, padding, mode='constant', constant_values=1)  # pad with ones (white)       # 将所有输入的data图像平复在一个ndarray-data中（tile the filters into an image）    data = data.reshape((n, n) + data.shape[1:]).transpose((0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))    # data的一个小例子,e.g., (3,120,120)    # 即，这里的data是一个2d 或者 3d 的ndarray    data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])    #print data    # 显示data所对应的图像    plt.imshow(data); plt.axis('off')    plt.savefig('pool5.png')#for i in range(1):    #line = line.strip('\n')    fileList='/home/yangwb/MYwork/FCN/fcn.berkeleyvision.org-master/myvoc1/2008_003821.jpg'    #print fileList    # load image, switch to BGR, subtract mean, and make dims C x H x W for Caffe    #print filename    im = Image.open(fileList)    in_ = np.array(im, dtype=np.float32)    in_ = in_[:,:,::-1]    in_ -= np.array((104.00698793,116.66876762,122.67891434))    in_ = in_.transpose((2,0,1))    # init    #caffe.set_device(int(sys.argv[1]))    caffe.set_device(5)    caffe.set_mode_gpu()    # load net    net = caffe.Net('/home/yangwb/MYwork/FCN/fcn.berkeleyvision.org-master/myvoc1/deploy.prototxt', '/home/yangwb/MYwork/FCN/fcn.berkeleyvision.org-master/myvoc1/_iter_45000.caffemodel', caffe.TEST)    # shape for input (data blob is N x C x H x W), set data    net.blobs['data'].reshape(1, *in_.shape)    print net.blobs['data'].shape    net.blobs['data'].data[...] = in_    # run net and take argmax for prediction    net.forward()    out = net.blobs['score'].data[0].argmax(axis=0)    #out=net.blobs['score'].data[0].argmax(0).flatten()    #a=net.blobs['score'].data[0, 0].flatten()    print out    #abc='/home/yangwb/test1/'+line+'.jpg'    #np.save(abc[:-4], out)    score= net.blobs['upscore8'].data[0,15:16]    #score= net.blobs['upscore21'].data[0]    #print score[20]    vis_square(score)    #plt.imshow(out,cmap='gray')    #plt.axis('off')    #plt.savefig(fileList[:-4]+'.png')    #plt.show()