Caffe on Ubuntu 16.04 with VirtualBox + Windows 10 x64 Dell Precision + Quadro 1000

Note: Detailed installation steps of Nvidia DIGITS on Ubuntu 16.04 (native, not VMWare on Windows10), is at https://github.com/prabindh/deepnotes/tree/master/ubuntu16.04.1

Steps

1. Install the AMD64 ISO on the VM using standard procedure

http://releases.ubuntu.com/16.04/ubuntu-16.04.1-desktop-amd64.iso

VMWare version - 5.1.2 r108956

2. sudo apt-get install build-essential

3. sudo apt-get install linux-headers-`uname -r`

4. (For later use only)

5. sudo apt-get install python-dev python-numpy python-scipy python-magic python-matplotlib libatlas-base-dev libjpeg-dev libopencv-dev git

6. sudo apt-get install -y libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libboost-all-dev libhdf5-serial-dev protobuf-compiler gfortran libjpeg62 libfreeimage-dev libatlas-base-dev git python-dev python-pip libgoogle-glog-dev libbz2-dev libxml2-dev libxslt-dev libffi-dev libssl-dev libgflags-dev liblmdb-dev python-yaml curl

7. sudo easy_install pillow

8. sudo apt-get install linux-headers-`uname -r`

9. Below portions for CUDA enablement - Need CUDA v8.0

-----------------------------

Runtime steps:

- sudo ln -s /usr/local/lib/python2.7/dist-packages/numpy/core/include/numpy/ /usr/local/include/python2.7/numpy

- cp Makefile.config.example Makefile.config

- Apply the changes below:

diff --git a/python/caffe/io.py b/python/caffe/io.py
index e1759be..a0bfdcd 100644
--- a/python/caffe/io.py
+++ b/python/caffe/io.py
@@ -255,9 +255,13 @@ class Transformer:
ms = (1,) + ms
if len(ms) != 3:
raise ValueError('Mean shape invalid')
- if ms != self.inputs[in_][1:]:
- raise ValueError('Mean shape incompatible with input shape.')
- self.mean[in_] = mean
+ if ms != self.inputs[in_][1:]:
+ print(self.inputs[in_])
+ in_shape = self.inputs[in_][1:]
+ m_min, m_max = mean.min(), mean.max()
+ normal_mean = (mean - m_min) / (m_max - m_min)
+ mean = resize_image(normal_mean.transpose((1,2,0)),in_shape[1:]).transpose((2,0,1)) * (m_max - m_min) + m_min
+ self.mean[in_] = mean

def set_input_scale(self, in_, scale):
"""
diff --git a/python/classify.py b/python/classify.py
index 4544c51..eb40828 100755
--- a/python/classify.py
+++ b/python/classify.py
@@ -5,6 +5,7 @@ classify.py is an out-of-the-box image classifer callable from the command line.
By default it configures and runs the Caffe reference ImageNet model.
"""
import numpy as np
+import pandas as pd
import os
import sys
import argparse
@@ -86,6 +87,24 @@ def main(argv):
help="Image file extension to take as input when a directory " +
"is given as the input file."
)
+ parser.add_argument(
+ "--labels_file",
+ default=os.path.join(pycaffe_dir,
+ "../data/ilsvrc12/synset_words.txt"),
+ help="Readable label definition file."
+ )
+ parser.add_argument(
+ "--print_results",
+ action='store_true',
+ help="Write output text to stdout rather than serializing to a file."
+ )
+ parser.add_argument(
+ "--force_grayscale",
+ action='store_true',
+ help="Converts RGB images down to single-channel grayscale versions," +
+ "useful for single-channel networks like MNIST."
+ )
+
args = parser.parse_args()

image_dims = [int(s) for s in args.images_dim.split(',')]
@@ -126,9 +145,29 @@ def main(argv):

# Classify.
start = time.time()
- predictions = classifier.predict(inputs, not args.center_only)
+ scores = classifier.predict(inputs, not args.center_only).flatten()
print("Done in %.2f s." % (time.time() - start))

+ if args.print_results:
+ with open(args.labels_file) as f:
+ labels_df = pd.DataFrame([
+ {
+ 'synset_id': l.strip().split(' ')[0],
+ 'name': ' '.join(l.strip().split(' ')[1:]).split(',')[0]
+ }
+ for l in f.readlines()
+ ])
+ labels = labels_df.sort('synset_id')['name'].values
+
+ indices = (-scores).argsort()[:5]
+ predictions = labels[indices]
+
+ meta = [
+ (p, '%.5f' % scores[i])
+ for i, p in zip(indices, predictions)
+ ]
+
+ print meta
# Save
print("Saving results into %s" % args.output_file)
np.save(args.output_file, predictions)

-----------------------------------------

- make pycaffe

- make all

- make test

- ./scripts/download_model_binary.py models/bvlc_reference_caffenet

- ./data/ilsvrc12/get_ilsvrc_aux.sh

- python python/classify.py --print_results examples/images/cat.jpg foo

Result

CPU mode
[[[ 110.17708588 110.45915222 110.68373108 ..., 110.9342804
110.79355621 110.5134201 ]
[ 110.42878723 110.98564148 111.27901459 ..., 111.55055237
111.30683136 110.6951828 ]
[ 110.525177 111.19493103 111.54753113 ..., 111.81067657
111.47111511 110.76550293]
...,
[ 98.6385498 99.15545654 99.39542389 ..., 99.43512726
99.22799683 98.70215607]
[ 98.55238342 98.93383789 99.12541962 ..., 99.1762619
99.03337097 98.60868835]
[ 98.3693161 98.45822906 98.6139679 ..., 98.66000366
98.58787537 98.44535828]]

[[ 117.64383698 118.0049057 118.22001648 ..., 118.46447754
118.22627258 117.91434479]
[ 117.93730164 118.60555267 118.90380859 ..., 119.14463043
118.81645203 118.16949463]
[ 118.08901978 118.87294006 119.24718475 ..., 119.45949554
119.02463531 118.27294922]
...,
[ 110.36632538 111.02960968 111.31279755 ..., 111.16692352
110.83407593 110.2490921 ]
[ 110.24700928 110.75028992 110.95999908 ..., 110.8342514
110.59172821 110.12150574]
[ 109.99901581 110.19393921 110.3454895 ..., 110.23415375
110.05860138 109.87283325]]

[[ 117.37848663 117.69866943 117.95220184 ..., 118.175354 117.97561646
117.66732025]
[ 117.67139435 118.27246094 118.59341431 ..., 118.81798553
118.52674866 117.88608551]
[ 117.82942963 118.5504303 118.93952942 ..., 119.14137268
118.74884033 118.0123291 ]
...,
[ 114.00041199 114.62164307 114.9572525 ..., 114.82345581
114.50564575 113.8839035 ]
[ 113.88108063 114.34970093 114.61184692 ..., 114.49390411
114.26222992 113.76023865]
[ 113.64065552 113.81821442 114.03469849 ..., 113.91330719
113.75688934 113.54673004]]]
WARNING: Logging before InitGoogleLogging() is written to STDERR
W0807 07:56:42.692380 1898 _caffe.cpp:122] DEPRECATION WARNING - deprecated use of Python interface
W0807 07:56:42.692435 1898 _caffe.cpp:123] Use this instead (with the named "weights" parameter):
W0807 07:56:42.692458 1898 _caffe.cpp:125] Net('python/../models/bvlc_reference_caffenet/deploy.prototxt', 1, weights='python/../models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel')
I0807 07:56:42.693848 1898 net.cpp:58] Initializing net from parameters:
name: "CaffeNet"
state {
phase: TEST
level: 0
}
layer {
name: "data"
type: "Input"
top: "data"
input_param {
shape {
dim: 10
dim: 3
dim: 227
dim: 227
}
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm1"
type: "LRN"
bottom: "pool1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "norm1"
top: "conv2"
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm2"
type: "LRN"
bottom: "pool2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
top: "conv3"
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
inner_product_param {
num_output: 4096
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
inner_product_param {
num_output: 1000
}
}
layer {
name: "prob"
type: "Softmax"
bottom: "fc8"
top: "prob"
}
I0807 07:56:42.697901 1898 layer_factory.hpp:77] Creating layer data
I0807 07:56:42.697989 1898 net.cpp:100] Creating Layer data
I0807 07:56:42.698143 1898 net.cpp:408] data -> data
I0807 07:56:42.698195 1898 net.cpp:150] Setting up data
I0807 07:56:42.698225 1898 net.cpp:157] Top shape: 10 3 227 227 (1545870)
I0807 07:56:42.698284 1898 net.cpp:165] Memory required for data: 6183480
I0807 07:56:42.698294 1898 layer_factory.hpp:77] Creating layer conv1
I0807 07:56:42.698321 1898 net.cpp:100] Creating Layer conv1
I0807 07:56:42.698339 1898 net.cpp:434] conv1 <- data
I0807 07:56:42.698360 1898 net.cpp:408] conv1 -> conv1
I0807 07:56:42.698459 1898 net.cpp:150] Setting up conv1
I0807 07:56:42.698490 1898 net.cpp:157] Top shape: 10 96 55 55 (2904000)
I0807 07:56:42.698514 1898 net.cpp:165] Memory required for data: 17799480
I0807 07:56:42.698545 1898 layer_factory.hpp:77] Creating layer relu1
I0807 07:56:42.698575 1898 net.cpp:100] Creating Layer relu1
I0807 07:56:42.698601 1898 net.cpp:434] relu1 <- conv1
I0807 07:56:42.698626 1898 net.cpp:395] relu1 -> conv1 (in-place)
I0807 07:56:42.698654 1898 net.cpp:150] Setting up relu1
I0807 07:56:42.698673 1898 net.cpp:157] Top shape: 10 96 55 55 (2904000)
I0807 07:56:42.698689 1898 net.cpp:165] Memory required for data: 29415480
I0807 07:56:42.698706 1898 layer_factory.hpp:77] Creating layer pool1
I0807 07:56:42.698726 1898 net.cpp:100] Creating Layer pool1
I0807 07:56:42.698789 1898 net.cpp:434] pool1 <- conv1
I0807 07:56:42.698840 1898 net.cpp:408] pool1 -> pool1
I0807 07:56:42.698878 1898 net.cpp:150] Setting up pool1
I0807 07:56:42.698905 1898 net.cpp:157] Top shape: 10 96 27 27 (699840)
I0807 07:56:42.698928 1898 net.cpp:165] Memory required for data: 32214840
I0807 07:56:42.698952 1898 layer_factory.hpp:77] Creating layer norm1
I0807 07:56:42.698974 1898 net.cpp:100] Creating Layer norm1
I0807 07:56:42.698992 1898 net.cpp:434] norm1 <- pool1
I0807 07:56:42.699012 1898 net.cpp:408] norm1 -> norm1
I0807 07:56:42.699033 1898 net.cpp:150] Setting up norm1
I0807 07:56:42.699053 1898 net.cpp:157] Top shape: 10 96 27 27 (699840)
I0807 07:56:42.699069 1898 net.cpp:165] Memory required for data: 35014200
I0807 07:56:42.699085 1898 layer_factory.hpp:77] Creating layer conv2
I0807 07:56:42.699105 1898 net.cpp:100] Creating Layer conv2
I0807 07:56:42.699121 1898 net.cpp:434] conv2 <- norm1
I0807 07:56:42.699142 1898 net.cpp:408] conv2 -> conv2
I0807 07:56:42.699553 1898 net.cpp:150] Setting up conv2
I0807 07:56:42.700721 1898 net.cpp:157] Top shape: 10 256 27 27 (1866240)
I0807 07:56:42.700729 1898 net.cpp:165] Memory required for data: 42479160
I0807 07:56:42.700741 1898 layer_factory.hpp:77] Creating layer relu2
I0807 07:56:42.700816 1898 net.cpp:100] Creating Layer relu2
I0807 07:56:42.700826 1898 net.cpp:434] relu2 <- conv2
I0807 07:56:42.700834 1898 net.cpp:395] relu2 -> conv2 (in-place)
I0807 07:56:42.700842 1898 net.cpp:150] Setting up relu2
I0807 07:56:42.700848 1898 net.cpp:157] Top shape: 10 256 27 27 (1866240)
I0807 07:56:42.700852 1898 net.cpp:165] Memory required for data: 49944120
I0807 07:56:42.700856 1898 layer_factory.hpp:77] Creating layer pool2
I0807 07:56:42.700863 1898 net.cpp:100] Creating Layer pool2
I0807 07:56:42.700868 1898 net.cpp:434] pool2 <- conv2
I0807 07:56:42.700875 1898 net.cpp:408] pool2 -> pool2
I0807 07:56:42.700884 1898 net.cpp:150] Setting up pool2
I0807 07:56:42.700891 1898 net.cpp:157] Top shape: 10 256 13 13 (432640)
I0807 07:56:42.700896 1898 net.cpp:165] Memory required for data: 51674680
I0807 07:56:42.700899 1898 layer_factory.hpp:77] Creating layer norm2
I0807 07:56:42.700906 1898 net.cpp:100] Creating Layer norm2
I0807 07:56:42.700911 1898 net.cpp:434] norm2 <- pool2
I0807 07:56:42.700917 1898 net.cpp:408] norm2 -> norm2
I0807 07:56:42.700925 1898 net.cpp:150] Setting up norm2
I0807 07:56:42.700930 1898 net.cpp:157] Top shape: 10 256 13 13 (432640)
I0807 07:56:42.700934 1898 net.cpp:165] Memory required for data: 53405240
I0807 07:56:42.700939 1898 layer_factory.hpp:77] Creating layer conv3
I0807 07:56:42.700947 1898 net.cpp:100] Creating Layer conv3
I0807 07:56:42.700951 1898 net.cpp:434] conv3 <- norm2
I0807 07:56:42.700958 1898 net.cpp:408] conv3 -> conv3
I0807 07:56:42.701668 1898 net.cpp:150] Setting up conv3
I0807 07:56:42.703191 1898 net.cpp:157] Top shape: 10 384 13 13 (648960)
I0807 07:56:42.703200 1898 net.cpp:165] Memory required for data: 56001080
I0807 07:56:42.703213 1898 layer_factory.hpp:77] Creating layer relu3
I0807 07:56:42.703223 1898 net.cpp:100] Creating Layer relu3
I0807 07:56:42.703228 1898 net.cpp:434] relu3 <- conv3
I0807 07:56:42.703235 1898 net.cpp:395] relu3 -> conv3 (in-place)
I0807 07:56:42.703244 1898 net.cpp:150] Setting up relu3
I0807 07:56:42.703250 1898 net.cpp:157] Top shape: 10 384 13 13 (648960)
I0807 07:56:42.703301 1898 net.cpp:165] Memory required for data: 58596920
I0807 07:56:42.703310 1898 layer_factory.hpp:77] Creating layer conv4
I0807 07:56:42.703320 1898 net.cpp:100] Creating Layer conv4
I0807 07:56:42.703326 1898 net.cpp:434] conv4 <- conv3
I0807 07:56:42.703333 1898 net.cpp:408] conv4 -> conv4
I0807 07:56:42.704098 1898 net.cpp:150] Setting up conv4
I0807 07:56:42.704110 1898 net.cpp:157] Top shape: 10 384 13 13 (648960)
I0807 07:56:42.704115 1898 net.cpp:165] Memory required for data: 61192760
I0807 07:56:42.704123 1898 layer_factory.hpp:77] Creating layer relu4
I0807 07:56:42.704130 1898 net.cpp:100] Creating Layer relu4
I0807 07:56:42.704135 1898 net.cpp:434] relu4 <- conv4
I0807 07:56:42.704141 1898 net.cpp:395] relu4 -> conv4 (in-place)
I0807 07:56:42.704147 1898 net.cpp:150] Setting up relu4
I0807 07:56:42.704154 1898 net.cpp:157] Top shape: 10 384 13 13 (648960)
I0807 07:56:42.704157 1898 net.cpp:165] Memory required for data: 63788600
I0807 07:56:42.704162 1898 layer_factory.hpp:77] Creating layer conv5
I0807 07:56:42.704170 1898 net.cpp:100] Creating Layer conv5
I0807 07:56:42.704175 1898 net.cpp:434] conv5 <- conv4
I0807 07:56:42.704181 1898 net.cpp:408] conv5 -> conv5
I0807 07:56:42.704694 1898 net.cpp:150] Setting up conv5
I0807 07:56:42.704969 1898 net.cpp:157] Top shape: 10 256 13 13 (432640)
I0807 07:56:42.704998 1898 net.cpp:165] Memory required for data: 65519160
I0807 07:56:42.705027 1898 layer_factory.hpp:77] Creating layer relu5
I0807 07:56:42.705057 1898 net.cpp:100] Creating Layer relu5
I0807 07:56:42.705083 1898 net.cpp:434] relu5 <- conv5
I0807 07:56:42.705111 1898 net.cpp:395] relu5 -> conv5 (in-place)
I0807 07:56:42.705139 1898 net.cpp:150] Setting up relu5
I0807 07:56:42.705166 1898 net.cpp:157] Top shape: 10 256 13 13 (432640)
I0807 07:56:42.705189 1898 net.cpp:165] Memory required for data: 67249720
I0807 07:56:42.705214 1898 layer_factory.hpp:77] Creating layer pool5
I0807 07:56:42.705240 1898 net.cpp:100] Creating Layer pool5
I0807 07:56:42.705281 1898 net.cpp:434] pool5 <- conv5
I0807 07:56:42.705310 1898 net.cpp:408] pool5 -> pool5
I0807 07:56:42.705343 1898 net.cpp:150] Setting up pool5
I0807 07:56:42.705370 1898 net.cpp:157] Top shape: 10 256 6 6 (92160)
I0807 07:56:42.705394 1898 net.cpp:165] Memory required for data: 67618360
I0807 07:56:42.705417 1898 layer_factory.hpp:77] Creating layer fc6
I0807 07:56:42.705446 1898 net.cpp:100] Creating Layer fc6
I0807 07:56:42.705471 1898 net.cpp:434] fc6 <- pool5
I0807 07:56:42.705498 1898 net.cpp:408] fc6 -> fc6
I0807 07:56:42.742313 1898 net.cpp:150] Setting up fc6
I0807 07:56:42.746018 1898 net.cpp:157] Top shape: 10 4096 (40960)
I0807 07:56:42.746031 1898 net.cpp:165] Memory required for data: 67782200
I0807 07:56:42.746065 1898 layer_factory.hpp:77] Creating layer relu6
I0807 07:56:42.746078 1898 net.cpp:100] Creating Layer relu6
I0807 07:56:42.746100 1898 net.cpp:434] relu6 <- fc6
I0807 07:56:42.746111 1898 net.cpp:395] relu6 -> fc6 (in-place)
I0807 07:56:42.746124 1898 net.cpp:150] Setting up relu6
I0807 07:56:42.746129 1898 net.cpp:157] Top shape: 10 4096 (40960)
I0807 07:56:42.746134 1898 net.cpp:165] Memory required for data: 67946040
I0807 07:56:42.746139 1898 layer_factory.hpp:77] Creating layer drop6
I0807 07:56:42.746146 1898 net.cpp:100] Creating Layer drop6
I0807 07:56:42.746150 1898 net.cpp:434] drop6 <- fc6
I0807 07:56:42.746156 1898 net.cpp:395] drop6 -> fc6 (in-place)
I0807 07:56:42.746165 1898 net.cpp:150] Setting up drop6
I0807 07:56:42.746170 1898 net.cpp:157] Top shape: 10 4096 (40960)
I0807 07:56:42.746175 1898 net.cpp:165] Memory required for data: 68109880
I0807 07:56:42.746178 1898 layer_factory.hpp:77] Creating layer fc7
I0807 07:56:42.746186 1898 net.cpp:100] Creating Layer fc7
I0807 07:56:42.746191 1898 net.cpp:434] fc7 <- fc6
I0807 07:56:42.746197 1898 net.cpp:408] fc7 -> fc7
I0807 07:56:42.766569 1898 net.cpp:150] Setting up fc7
I0807 07:56:42.774121 1898 net.cpp:157] Top shape: 10 4096 (40960)
I0807 07:56:42.774138 1898 net.cpp:165] Memory required for data: 68273720
I0807 07:56:42.774152 1898 layer_factory.hpp:77] Creating layer relu7
I0807 07:56:42.774169 1898 net.cpp:100] Creating Layer relu7
I0807 07:56:42.774175 1898 net.cpp:434] relu7 <- fc7
I0807 07:56:42.774183 1898 net.cpp:395] relu7 -> fc7 (in-place)
I0807 07:56:42.774194 1898 net.cpp:150] Setting up relu7
I0807 07:56:42.774199 1898 net.cpp:157] Top shape: 10 4096 (40960)
I0807 07:56:42.774204 1898 net.cpp:165] Memory required for data: 68437560
I0807 07:56:42.774207 1898 layer_factory.hpp:77] Creating layer drop7
I0807 07:56:42.774215 1898 net.cpp:100] Creating Layer drop7
I0807 07:56:42.774219 1898 net.cpp:434] drop7 <- fc7
I0807 07:56:42.774225 1898 net.cpp:395] drop7 -> fc7 (in-place)
I0807 07:56:42.774233 1898 net.cpp:150] Setting up drop7
I0807 07:56:42.774238 1898 net.cpp:157] Top shape: 10 4096 (40960)
I0807 07:56:42.774242 1898 net.cpp:165] Memory required for data: 68601400
I0807 07:56:42.774246 1898 layer_factory.hpp:77] Creating layer fc8
I0807 07:56:42.774253 1898 net.cpp:100] Creating Layer fc8
I0807 07:56:42.774258 1898 net.cpp:434] fc8 <- fc7
I0807 07:56:42.774266 1898 net.cpp:408] fc8 -> fc8
I0807 07:56:42.777400 1898 net.cpp:150] Setting up fc8
I0807 07:56:42.780128 1898 net.cpp:157] Top shape: 10 1000 (10000)
I0807 07:56:42.780143 1898 net.cpp:165] Memory required for data: 68641400
I0807 07:56:42.780158 1898 layer_factory.hpp:77] Creating layer prob
I0807 07:56:42.780175 1898 net.cpp:100] Creating Layer prob
I0807 07:56:42.780182 1898 net.cpp:434] prob <- fc8
I0807 07:56:42.780191 1898 net.cpp:408] prob -> prob
I0807 07:56:42.780208 1898 net.cpp:150] Setting up prob
I0807 07:56:42.780215 1898 net.cpp:157] Top shape: 10 1000 (10000)
I0807 07:56:42.780220 1898 net.cpp:165] Memory required for data: 68681400
I0807 07:56:42.780223 1898 net.cpp:228] prob does not need backward computation.
I0807 07:56:42.780228 1898 net.cpp:228] fc8 does not need backward computation.
I0807 07:56:42.780233 1898 net.cpp:228] drop7 does not need backward computation.
I0807 07:56:42.780238 1898 net.cpp:228] relu7 does not need backward computation.
I0807 07:56:42.780243 1898 net.cpp:228] fc7 does not need backward computation.
I0807 07:56:42.780247 1898 net.cpp:228] drop6 does not need backward computation.
I0807 07:56:42.780252 1898 net.cpp:228] relu6 does not need backward computation.
I0807 07:56:42.780257 1898 net.cpp:228] fc6 does not need backward computation.
I0807 07:56:42.780261 1898 net.cpp:228] pool5 does not need backward computation.
I0807 07:56:42.780267 1898 net.cpp:228] relu5 does not need backward computation.
I0807 07:56:42.780272 1898 net.cpp:228] conv5 does not need backward computation.
I0807 07:56:42.780277 1898 net.cpp:228] relu4 does not need backward computation.
I0807 07:56:42.780282 1898 net.cpp:228] conv4 does not need backward computation.
I0807 07:56:42.780287 1898 net.cpp:228] relu3 does not need backward computation.
I0807 07:56:42.780292 1898 net.cpp:228] conv3 does not need backward computation.
I0807 07:56:42.780297 1898 net.cpp:228] norm2 does not need backward computation.
I0807 07:56:42.780303 1898 net.cpp:228] pool2 does not need backward computation.
I0807 07:56:42.780308 1898 net.cpp:228] relu2 does not need backward computation.
I0807 07:56:42.780313 1898 net.cpp:228] conv2 does not need backward computation.
I0807 07:56:42.780318 1898 net.cpp:228] norm1 does not need backward computation.
I0807 07:56:42.780323 1898 net.cpp:228] pool1 does not need backward computation.
I0807 07:56:42.780328 1898 net.cpp:228] relu1 does not need backward computation.
I0807 07:56:42.780331 1898 net.cpp:228] conv1 does not need backward computation.
I0807 07:56:42.780336 1898 net.cpp:228] data does not need backward computation.
I0807 07:56:42.780341 1898 net.cpp:270] This network produces output prob
I0807 07:56:42.780354 1898 net.cpp:283] Network initialization done.
I0807 07:56:42.911769 1898 upgrade_proto.cpp:43] Attempting to upgrade input file specified using deprecated transformation parameters: python/../models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel
I0807 07:56:42.911901 1898 upgrade_proto.cpp:46] Successfully upgraded file specified using deprecated data transformation parameters.
W0807 07:56:42.911941 1898 upgrade_proto.cpp:48] Note that future Caffe releases will only support transform_param messages for transformation fields.
I0807 07:56:42.911973 1898 upgrade_proto.cpp:52] Attempting to upgrade input file specified using deprecated V1LayerParameter: python/../models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel
I0807 07:56:43.070518 1898 upgrade_proto.cpp:60] Successfully upgraded file specified using deprecated V1LayerParameter
I0807 07:56:43.136179 1898 net.cpp:761] Ignoring source layer loss
(10, 3, 227, 227)
Loading file: examples/images/cat.jpg
Classifying 1 inputs.
Done in 3.53 s.
python/classify.py:162: FutureWarning: sort(columns=....) is deprecated, use sort_values(by=.....)
labels = labels_df.sort('synset_id')['name'].values
[('tabby', '0.27933'), ('tiger cat', '0.21915'), ('Egyptian cat', '0.16064'), ('lynx', '0.12844'), ('kit fox', '0.05155')]
Saving results into foo

caffemlpythonubuntu 16.04vmwarewindows10quadrocuda