caffe 学习(1) —— Classification: Instant Recognition with Caffe

#!/usr/bin/env sh
set -evx
env | sort

mkdir build || true
mkdir build/$GTEST_TARGET || true
cd build/$GTEST_TARGET
cmake -D gtest_build_samples=ON \
      -D gmock_build_samples=ON \
      -D gtest_build_tests=ON \
      -D gmock_build_tests=ON \
      -D CMAKE_CXX_FLAGS=$CXX_FLAGS \
      ../$GTEST_TARGET
make
make test

sudo sh ./autogen.sh
make
sudo make check
sudo make install

# set up Python envirionment: 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'
plt.rcParams['image.cmap'] = 'gray'	#use grayscale output rather than a (potentiallly misleading) color heatmap

# load caffe
# the caffe module needs to be on the Python path
import sys
caffe_root='../'
sys.path.insert(0, caffe_root + 'python')

import caffe

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

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

# 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 imput 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)
transformer.set_raw_scale('data', 255)
transformer.set_channel_swap('data', (2, 1, 0))	# swap channels from RGB to BGR

net.blobs['data'].reshape(50,	# batch size
	3,	# 3-channel (BGR) images
	227, 227)	# image size is 227*227

image = caffe.io.load_image(caffe_root + 'examples/images/cat.jpg')
transformed_image = transformer.preprocess('data', image)
plt.imshow(image)
plt.show()

# copy the image data into the memory allocated for the net
net.blobs['data'].data[...]=transformed_image

### perform calssification
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
	print 'exetute the bash file above'

labels = np.loadtxt(labels_file, str, delimiter='\t')

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)
caffe.set_mode_gpu()
net.forward()
# %timeit net.forward()

for layer_name, blob in net.blobs.iteritems():
	print layer_name + '\t' + str(blob.data.shape)

for layer_name, param in net.params.iteritems():
	print layer_name + '\t' + 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 visulaize each (height, widht) 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)

	# 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')
	plt.show()

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)
plt.show()