caffe学习笔记（5）：层的特征可视化

最新推荐文章于 2024-08-07 09:14:37 发布

guyunee

最新推荐文章于 2024-08-07 09:14:37 发布

阅读量1.2w

点赞数 7

分类专栏： deep learning python 文章标签： cnn layer caffe 可视化

本文链接：https://blog.csdn.net/qq_30401249/article/details/51469184

版权

本文详细记录了使用Caffe进行深度学习时，如何加载网络并设置输入预处理，通过CPU和GPU模式进行分类，以及查看中间输出的过程。内容包括CaffeNet模型的加载、输入图像的预处理、分类结果的展示，并探讨了如何观察网络的参数和激活形状，特别是对卷积层和全连接层的可视化分析。

摘要由CSDN通过智能技术生成

1.setup

# set up Python environment: numpy for numerical routines, and matplotlib for plotting
import numpy as np
import matplotlib.pyplot as plt
# display plots in this notebook
%matplotlib inline # put the image in ipython notebook

# set display defaults
plt.rcParams['figure.figsize'] = (10, 10)        # large images
plt.rcParams['image.interpolation'] = 'nearest'  # don't interpolate: show square pixels
plt.rcParams['image.cmap'] = 'gray'  # use grayscale output rather than a (potentially misleading) color heatmap

# load caffe
# The caffe module needs to be on the Python path;
# we'll add it here explicitly.
import sys
caffe_root='./caffe-master/'  # this file should be run from {caffe_root}/examples
sys.path.insert(0, caffe_root + 'python')

import caffe # If you get "No module named _caffe", either you have not built pycaffe or you have the wrong path.

If needed, download the reference model (“CaffeNet”, a variant of AlexNet).

import os
if os.path.isfile(caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'):
    print 'CaffeNet found.'
else:
    print 'Downloading pre-trained CaffeNet model...'
    !../scripts/download_model_binary.py ../models/bvlc_reference_caffenet

CaffeNet found.

2. Load net and set up input preprocessing

Set Caffe to CPU mode and load the net from disk.

caffe.set_mode_cpu()
model_def = caffe_root + 'models/bvlc_reference_caffenet/deploy.prototxt'
model_weights = caffe_root + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'

net = caffe.Net(model_def,      # defines the structure of the model
                model_weights,  # contains the trained weights
                caffe.TEST)     # use test mode

Set up input preprocessing. (We’ll use Caffe’s caffe.io.Transformer to do this, but this step is independent of other parts of Caffe, so any custom preprocessing code may be used).
Our default CaffeNet is configured to take images in BGR format.
Values are expected to start in the range [0, 255] and then have the mean ImageNet pixel value subtracted from them. in addition, the channel dimension is expected as the first (outermost) dimension.
As matplotlib will load images with values in the range [0, 1] in RGB format with the channel as the innermost dimension, we are arranging for the needed transformations here.

# load the mean ImageNet image (as distributed with Caffe) for subtraction
mu = np.load(caffe_root + 'python/caffe/imagenet/ilsvrc_2012_mean.npy')
mu = mu.mean(1).mean(1)  # average over pixels to obtain the mean (BGR) pixel values
print 'mean-subtracted values:', zip('BGR', mu)

# create transformer for the input called 'data'
transformer = caffe.io.Transformer({
   'data': net.blobs['data'].data.shape})

transformer.set_transpose('data', (2,0,1))  # move image channels to outermost dimension