caffe特徵層可視化

#參考1:https://blog.csdn.net/sushiqian/article/details/78614133
#參考2:https://blog.csdn.net/thy_2014/article/details/51659300
# coding=utf-8

import numpy as np
import matplotlib.pyplot as plt
import os
import sys
sys.path.append("/home/wit/caffe/python")
sys.path.append("/home/wit/caffe/python/caffe")
import caffe

deploy_file_name = '/home/wit/wjx/MobileNetSSD_deploy.prototxt'
model_file_name  = '/home/wit/wjx/mobilenet_iter_25000.caffemodel'
test_img   = "/home/wit/wjx/src.jpg"
#編寫一個函數，用於顯示各層的參數,padsize用於設置圖片間隔空隙,padval用於調整亮度 
def show_data(data, padsize=1, padval=0, name = 'conv0'):
    #歸一化
    data -= data.min()
    data /= data.max()
 
    #根據data中圖片數量data.shape[0]，計算最後輸出時每行每列圖片數n
    n = int(np.ceil(np.sqrt(data.shape[0])))
    # padding = ((圖片個數維度的padding),(圖片高的padding), (圖片寬的padding), ....)
    padding = ((0, n ** 2 - data.shape[0]), (0, padsize), (0, padsize)) + ((0, 0),) * (data.ndim - 3)
    data = np.pad(data, padding, mode='constant', constant_values=(padval, padval))
 
    # 先將padding後的data分紅n*n張圖像
    data = data.reshape((n, n) + data.shape[1:]).transpose((0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))
    # 再將（n, W, n, H）變換成(n*w, n*H)
    data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])
    plt.set_cmap('gray')
    plt.imshow(data)
    plt.imsave(name+'.jpg',data)
    
 
if __name__ == '__main__':
 
    deploy_file = deploy_file_name
    model_file  = model_file_name
    #若是是用了GPU
    #caffe.set_mode_gpu()
 
    #初始化caffe 
    net = caffe.Net(deploy_file, model_file, caffe.TEST)
 
    #數據輸入預處理
    # 'data'對應於deploy文件：
    # input: "data"
    transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
 
    # python讀取的圖片文件格式爲H×W×K，需轉化爲K×H×W
    transformer.set_transpose('data', (2, 0, 1))
 
    # python中將圖片存儲爲[0, 1]
    # 若是模型輸入用的是0~255的原始格式，則須要作如下轉換
    transformer.set_raw_scale('data', 255)
 
    # caffe中圖片是BGR格式，而原始格式是RGB，因此要轉化
    transformer.set_channel_swap('data', (2, 1, 0))
 
    # 將輸入圖片格式轉化爲合適格式（與deploy文件相同）
    net.blobs['data'].reshape(1, 3, 300, 300)
 
    #讀取圖片
    #參數color: True(default)是彩色圖，False是灰度圖
    img = caffe.io.load_image(test_img,color=True)
 
    # 數據輸入、預處理
    net.blobs['data'].data[...] = transformer.preprocess('data', img)
 
    # 前向迭代，即分類
    out = net.forward()
 
    # 輸出結果爲各個可能分類的機率分佈(deploy中最後一層)
    predicts = out['detection_out']
    print "Prob:"
    print predicts

    #最可能分類
    predict = predicts.argmax()
    print "Result:"
    print predict
 
    for layer_name, blob in net.blobs.iteritems():
        print layer_name + '\t' + str(blob.data.shape)

    #---------------------------- 顯示特徵圖 -------------------------------
    feature = net.blobs['conv1'].data
    print(feature.shape)
    feature = feature.reshape(64,150,150)   
    show_data(feature, padsize=2, padval=0, name='conv1')