Caffe/visualization.py at master · PaperAnalyticalDeviceND/Caffe · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
import os
import numpy as np
import matplotlib.pyplot as plt

# Make sure that caffe is on the python path:
caffe_root = '/home/jsweet/Documents/Code/caffe/'  # this file is expected to be in {caffe_root}/examples
import sys
sys.path.insert(0, caffe_root + 'python')

import caffe

plt.rcParams['figure.figsize'] = (10, 10)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

caffe.set_mode_cpu()
net = caffe.Net( 'train_val.prototxt', 'caffenet_train_iter_10000.caffemodel', caffe.TEST)

# input preprocessing: 'data' is the name of the input blob == net.inputs[0]
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2,0,1))
transformer.set_mean('data', np.load( 'imagenet_mean.npy').mean(1).mean(1)) # mean pixel
transformer.set_raw_scale('data', 255)  # the reference model operates on images in [0,255] range instead of [0,1]
transformer.set_channel_swap('data', (2,1,0))  # the reference model has channels in BGR order instead of RGB

net.blobs['data'].reshape(1,3,227,227)
net.blobs['data'].data[...] = transformer.preprocess('data', caffe.io.load_image('example.jpg'))
out = net.forward()
print("Predicted class is #{}.".format(out['prob'].argmax()))

[(k, v.data.shape) for k, v in net.blobs.items()]
[(k, v[0].data.shape) for k, v in net.params.items()]

# take an array of shape (n, height, width) or (n, height, width, channels)
# and visualize each (height, width) thing in a grid of size approx. sqrt(n) by sqrt(n)
def vis_square(i, data, padsize=1, padval=0):
    data -= data.min()
    data /= data.max()

    # 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, padsize), (0, padsize)) + ((0, 0),) * (data.ndim - 3)
    data = np.pad(data, padding, mode='constant', constant_values=(padval, padval))

    # 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.imsave(str(i)+'.jpg', data)

plt.imsave('image.jpg', transformer.deprocess('data', net.blobs['data'].data[0]))

# the parameters are a list of [weights, biases]
filters = net.params['conv1'][0].data
vis_square(0, filters.transpose(0, 2, 3, 1))

feat = net.blobs['conv1'].data[0, :36]
vis_square(1, feat, padval=1)

filters = net.params['conv2'][0].data
vis_square(2, filters[:48].reshape(48**2, 5, 5))

feat = net.blobs['conv2'].data[0, :36]
vis_square(3, feat, padval=1)

feat = net.blobs['conv3'].data[0]
vis_square(4, feat, padval=0.5)

feat = net.blobs['conv4'].data[0]
vis_square(5, feat, padval=0.5)

feat = net.blobs['conv5'].data[0]
vis_square(6, feat, padval=0.5)

feat = net.blobs['pool5'].data[0]
vis_square(7, feat, padval=1)

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['fc7'].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.plot(feat.flat)

# load labels
imagenet_labels_filename = 'synset_words.txt'
labels = np.loadtxt(imagenet_labels_filename, str, delimiter='\t')

# sort top k predictions from softmax output
top_k = net.blobs['prob'].data[0].flatten().argsort()[-1:-6:-1]
print labels[top_k]