首先，数据文件和模型文件都已经下载并处理好，不提。
cd "caffe-root-dir "
----------------------------------分割线-------------------------------
# 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
--------------------------------------------------------------------------------------
# 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
--------------------------------------------------------------------------------------
# The caffe module needs to be on the Python path;
# we'll add it here explicitly.
import sys
caffe_root = './' # this file should be run from {caffe_root}/examples (otherwise change this line)
sys.path.insert(0, caffe_root + 'build/install/python')
--------------------------------------------------------------------------------------
import caffe
# If you get "No module named _caffe", either you have not built pycaffe or you have the wrong path.
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 (e.g., don't perform dropout)
--------------------------------------------------------------------------------------
# load the mean ImageNet image (as distributed with Caffe) for subtraction
mu = np.load(caffe_root + 'build/install/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
transformer.set_mean('data', mu) # subtract the dataset-mean value in each channel
transformer.set_raw_scale('data', 255) # rescale from [0, 1] to [0, 255]
transformer.set_channel_swap('data', (2,1,0)) # swap channels from RGB to BGR
--------------------------------------------------------------------------------------
# set the size of the input (we can skip this if we're happy
# with the default; we can also change it later, e.g., for different batch sizes)
net.blobs['data'].reshape(50, # batch size
3, # 3-channel (BGR) images
227, 227) # image size is 227x227
image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg')
transformed_image = transformer.preprocess('data', image)
plt.imshow(image)
--------------------------------------------------------------------------------------
# copy the image data into the memory allocated for the net
net.blobs['data'].data[...] = transformed_image
### perform classification
output = net.forward()
output_prob = output['prob'][0] # the output probability vector for the first image in the batch
print 'predicted class is:', output_prob.argmax()
-----------------------------------------
# load ImageNet labels
labels_file = caffe_root + 'data/ilsvrc12/synset_words.txt'
if not os.path.exists(labels_file):
!../data/ilsvrc12/get_ilsvrc_aux.sh
labels = np.loadtxt(labels_file, str, delimiter=' ')
print 'output label:', labels[output_prob.argmax()]
----------------------------------------------------------------
# sort top five predictions from softmax output
top_inds = output_prob.argsort()[::-1][:5] # reverse sort and take five largest items
print 'probabilities and labels:'
zip(output_prob[top_inds], labels[top_inds])
----------------------------------------------------------------
%timeit net.forward()
----------------------------------------------------------------
caffe.set_device(0) # if we have multiple GPUs, pick the first one
caffe.set_mode_gpu()
net.forward() # run once before timing to set up memory
%timeit net.forward()
----------------------------------------------------------------
# for each layer, show the output shape
for layer_name, blob in net.blobs.iteritems():
print layer_name + ' ' + str(blob.data.shape)
----------------------------------------------------------------
for layer_name, param in net.params.iteritems():
print layer_name + ' ' + str(param[0].data.shape), str(param[1].data.shape)
----------------------------------------------------------------
def vis_square(data):
"""Take an array of shape (n, height, width) or (n, height, width, 3)
and visualize each (height, width) thing in a grid of size approx. sqrt(n) by sqrt(n)"""
# normalize data for display
data = (data - data.min()) / (data.max() - data.min())
# force the number of filters to be square
n = int(np.ceil(np.sqrt(data.shape[0])))
padding = (((0, n ** 2 - data.shape[0]),
(0, 1), (0, 1)) # add some space between filters
+ ((0, 0),) * (data.ndim - 3)) # don't pad the last dimension (if there is one)
data = np.pad(data, padding, mode='constant', constant_values=1) # pad with ones (white)
# tile the filters into an image
data = data.reshape((n, n) + data.shape[1:]).transpose((0, 2, 1, 3) + tuple(range(4, data.ndim + 1)))
data = data.reshape((n * data.shape[1], n * data.shape[3]) + data.shape[4:])
plt.imshow(data); plt.axis('off')
----------------------------------------------------------------
# the parameters are a list of [weights, biases]
filters = net.params['conv1'][0].data
vis_square(filters.transpose(0, 2, 3, 1))
----------------------------------------------------------------
feat = net.blobs['conv1'].data[0, :36]
vis_square(feat)
----------------------------------------------------------------
feat = net.blobs['pool5'].data[0]
vis_square(feat)
----------------------------------------------------------------
feat = net.blobs['fc6'].data[0]
plt.subplot(2, 1, 1)
plt.plot(feat.flat)
plt.subplot(2, 1, 2)
_ = plt.hist(feat.flat[feat.flat > 0], bins=100)
----------------------------------------------------------------
feat = net.blobs['prob'].data[0]
plt.figure(figsize=(15, 3))
plt.plot(feat.flat)
----------------------------------------------------------------
# download an image
my_image_url = "..." # paste your URL here
# for example:
# my_image_url = "https://upload.wikimedia.org/wikipedia/commons/b/be/Orang_Utan%2C_Semenggok_Forest_Reserve%2C_Sarawak%2C_Borneo%2C_Malaysia.JPG"
!wget -O image.jpg $my_image_url
# transform it and copy it into the net
image = caffe.io.load_image('image.jpg')
net.blobs['data'].data[...] = transformer.preprocess('data', image)
# perform classification
net.forward()
# obtain the output probabilities
output_prob = net.blobs['prob'].data[0]
# sort top five predictions from softmax output
top_inds = output_prob.argsort()[::-1][:5]
plt.imshow(image)
print 'probabilities and labels:'
zip(output_prob[top_inds], labels[top_inds])
----------------------------------------------------------------
----------------------------------------------------------------
----------------------------------------------------------------
----------------------------------------------------------------
----------------------------------------------------------------