7

我已经加载了一个预训练的 VGG 人脸 CNN 并成功运行它。我想从第 3 层和第 8 层中提取超列平均值。我正在关注关于从此处提取超列的部分。但是,由于 get_output 函数不起作用,我不得不进行一些更改:

进口:

import matplotlib.pyplot as plt
import theano
from scipy import misc
import scipy as sp
from PIL import Image
import PIL.ImageOps
from keras.models import Sequential
from keras.layers.core import Flatten, Dense, Dropout
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.optimizers import SGD
import numpy as np
from keras import backend as K

主功能:

#after necessary processing of input to get im
layers_extract = [3, 8]
hc = extract_hypercolumn(model, layers_extract, im)
ave = np.average(hc.transpose(1, 2, 0), axis=2)
print(ave.shape)
plt.imshow(ave)
plt.show()

获取特征函数:(我跟着这个

def get_features(model, layer, X_batch):
    get_features = K.function([model.layers[0].input, K.learning_phase()], [model.layers[layer].output,])
    features = get_features([X_batch,0])
    return features

超列提取:

def extract_hypercolumn(model, layer_indexes, instance):
    layers = [K.function([model.layers[0].input],[model.layers[li].output])([instance])[0] for li in layer_indexes]
    feature_maps = get_features(model,layers,instance)
    hypercolumns = []
    for convmap in feature_maps:
        for fmap in convmap[0]:
            upscaled = sp.misc.imresize(fmap, size=(224, 224),mode="F", interp='bilinear')
            hypercolumns.append(upscaled)
    return np.asarray(hypercolumns)

但是,当我运行代码时,出现以下错误:

get_features = K.function([model.layers[0].input, K.learning_phase()], [model.layers[layer].output,])
TypeError: list indices must be integers, not list

我怎样才能解决这个问题?

笔记:

在超列提取功能中,当我使用feature_maps = get_features(model,1,instance)或任何整数代替 1 时,它工作正常。但我想从第 3 层到第 8 层提取平均值。

4

2 回答 2

1

这让我很困惑:

  1. 之后layers = [K.function([model.layers[0].input],[model.layers[li].output])([instance])[0] for li in layer_indexes],层是提取特征的列表。
  2. 然后你将该列表发送到feature_maps = get_features(model,layers,instance).
  3. def get_features(model, layer, X_batch):中,它们的第二个参数,即layer,用于在 中进行索引model.layers[layer].output

你想要的是:

  1. feature_maps = get_features(model,layer_indexes,instance):传递层索引而不是提取的特征。
  2. get_features = K.function([model.layers[0].input, K.learning_phase()], [model.layers[l].output for l in layer]) : list 不能用于索引列表。

尽管如此,您的特征抽象函数还是写得很糟糕。我建议您重写所有内容,而不是混合代码。

于 2016-08-04T06:54:35.987 回答
0

我为单通道输入图像(W x H x 1)重写了您的函数。也许会有所帮助。

def extract_hypercolumn(model, layer_indexes, instance):
    test_image = instance
    outputs    = [layer.output for layer in model.layers]          # all layer outputs
    comp_graph = [K.function([model.input]+ [K.learning_phase()], [output]) for output in outputs]  # evaluation functions

    feature_maps = []
    for layerIdx in layer_indexes:
        feature_maps.append(layer_outputs_list[layerIdx][0][0])


    hypercolumns = []
    for idx, convmap in enumerate(feature_maps):
        #        vv = np.asarray(convmap)
        #        print(vv.shape)
        vv = np.asarray(convmap)
        print('shape of feature map at layer ', layer_indexes[idx], ' is: ', vv.shape)

        for i in range(vv.shape[-1]):
            fmap = vv[:,:,i]
            upscaled = sp.misc.imresize(fmap, size=(img_width, img_height),
                                    mode="F", interp='bilinear')
            hypercolumns.append(upscaled)  

    # hypc = np.asarray(hypercolumns)
    # print('shape of hypercolumns ', hypc.shape)

    return np.asarray(hypercolumns)
于 2017-07-26T22:47:07.713 回答