Caffe net.predict() 输出随机结果 (GoogleNet)

我使用了预训练的 GoogleNethttps://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet https://github.com/BVLC/caffe/tree/master/models/bvlc_googlenet并用我自己的数据（~ 100k 图像，101 个类）对其进行微调。 经过一天的训练后，我在 top-1 分类中达到了 62%，在 top-5 分类中达到了 85%，并尝试使用该网络来预测多个图像。

我只是按照以下示例https://github.com/BVLC/caffe/blob/master/examples/classification.ipynb https://github.com/BVLC/caffe/blob/master/examples/classification.ipynb,

这是我的Python代码：

import caffe
import numpy as np


caffe_root = './caffe'


MODEL_FILE = 'caffe/models/bvlc_googlenet/deploy.prototxt'
PRETRAINED = 'caffe/models/bvlc_googlenet/bvlc_googlenet_iter_200000.caffemodel'

caffe.set_mode_gpu()

net = caffe.Classifier(MODEL_FILE, PRETRAINED,
               mean=np.load('ilsvrc_2012_mean.npy').mean(1).mean(1),
               channel_swap=(2,1,0),
               raw_scale=255,
               image_dims=(224, 224))

def caffe_predict(path):
        input_image = caffe.io.load_image(path)
        print path
        print input_image
        prediction = net.predict([input_image])


        print prediction
        print "----------"

        print 'prediction shape:', prediction[0].shape
        print 'predicted class:', prediction[0].argmax()


        proba = prediction[0][prediction[0].argmax()]
        ind = prediction[0].argsort()[-5:][::-1] # top-5 predictions


        return prediction[0].argmax(), proba, ind

在我的deploy.prototxt中，我更改了最后一层只是为了预测我的101个类。

layer {
  name: "loss3/classifier"
  type: "InnerProduct"
  bottom: "pool5/7x7_s1"
  top: "loss3/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }
  param {
    lr_mult: 2
    decay_mult: 0
  }
  inner_product_param {
    num_output: 101
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "loss3/classifier"
  top: "prob"
}

这是softmax输出的分布：

[[ 0.01106235  0.00343131  0.00807581  0.01530041  0.01077161  0.0081002
   0.00989228  0.00972753  0.00429183  0.01377776  0.02028225  0.01209726
   0.01318955  0.00669979  0.00720005  0.00838189  0.00335461  0.01461464
   0.01485041  0.00543212  0.00400191  0.0084842   0.02134697  0.02500303
   0.00561895  0.00776423  0.02176422  0.00752334  0.0116104   0.01328687
   0.00517187  0.02234021  0.00727272  0.02380056  0.01210031  0.00582192
   0.00729601  0.00832637  0.00819836  0.00520551  0.00625274  0.00426603
   0.01210176  0.00571806  0.00646495  0.01589645  0.00642173  0.00805364
   0.00364388  0.01553882  0.01549598  0.01824486  0.00483241  0.01231962
   0.00545738  0.0101487   0.0040346   0.01066607  0.01328133  0.01027429
   0.01581303  0.01199994  0.00371804  0.01241552  0.00831448  0.00789811
   0.00456275  0.00504562  0.00424598  0.01309276  0.0079432   0.0140427
   0.00487625  0.02614347  0.00603372  0.00892296  0.00924052  0.00712763
   0.01101298  0.00716757  0.01019373  0.01234141  0.00905332  0.0040798
   0.00846442  0.00924353  0.00709366  0.01535406  0.00653238  0.01083806
   0.01168014  0.02076091  0.00542234  0.01246306  0.00704035  0.00529556
   0.00751443  0.00797437  0.00408798  0.00891858  0.00444583]]

看起来就像是随机分布，没有任何意义。

感谢您的任何帮助或提示以及最诚挚的问候， 亚历克斯

解决方案非常简单：我只是忘记重命名部署文件中的最后一层：

layer {
  name: "loss3/classifier"
  type: "InnerProduct"
  bottom: "pool5/7x7_s1"
  top: "loss3/classifier"
  param {
    lr_mult: 1
    decay_mult: 1
  }