Keras VGG提取功能

时间:2016-07-30 12:54:12

标签: python keras deep-learning theano vgg-net

我已经加载了预先训练好的VGG面部CNN并成功运行了它。我想从第3层和第8层中提取超列平均值。我正在关注从here中提取超列的部分。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

主要功能:

#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()

获取功能功能:(我跟着this

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

超柱提取:

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,我收到以下错误:

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

我该如何解决这个问题?

注:

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,它可以正常工作。但我想从第3层到第8层提取平均值。

2 个答案:

答案 0 :(得分:1)

让我很困惑:

  1. layers = [K.function([model.layers[0].input],[model.layers[li].output])([instance])[0] for li in layer_indexes]之后,图层是已提取要素的列表。
  2. 然后您将该列表发送到feature_maps = get_features(model,layers,instance)
  3. def get_features(model, layer, X_batch):中,他们的第二个参数,即layer,用于在model.layers[layer].output中进行索引。
  4. 你想要的是:

    1. feature_maps = get_features(model, layer_indexes ,instance):传递图层索引而不是提取的要素。
    2. get_features = K.function([model.layers[0].input, K.learning_phase()], [ model.layers [l] .out in in layer ]):list不能用于索引列表。
    3. 尽管如此,你的功能抽象功能却写得非常糟糕。我建议你重写所有内容而不是混合代码。

答案 1 :(得分:0)

我为单通道输入图像重写了您的功能(W x H x 1)。也许它会有所帮助。

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)