Ubuntu16.04 + Opencv3.4.2 + python3.5 + caffe-ssd

這一篇的前提是已經按照 Ubuntu 16.04 裝機指南（分區 + 顯卡驅動 + Cuda9.0 + CUDNN7.0）安裝好驅動， Cuda9.0 和 CUDNN7.0 。

1. opencv3.4.2

編譯 opencv 是一個比較麻煩的過程，一步不對就可能會編譯不成功。這部分主要參考

這裏進行一點補充：

根據參考1, 把依賴項單獨下載下來再進行編譯
可以選擇用 cmake-gui，其實用命令也是不錯的選擇,下面是我用的命令，用的是 ubuntu16.04 自帶的 python3.5，你需要檢查你的 python3 的相關路徑，以及 EXTRA_MODULES 放的位置。

cmake -D CMAKE_BUILD_TYPE=RELEASE  \
    -D INSTALL_C_EXAMPLES=OFF \
    -D INSTALL_PYTHON_EXAMPLES=ON \
    -D BUILD_EXAMPLES=OFF \
    -DENABLE_CXX11=ON \
    -D BUILD_opencv_python3=ON  \
    -D BUILD_opencv_python2=ON  \
    -D BUILD_opencv_java=OFF  \
    -D OPENCV_EXTRA_MODULES_PATH=~/opencv/opencv_contrib-3.4.2/modules \
    -D PYTHON3_EXECUTABLE=$(which python3)\
    -D PYTHON3_INCLUDE_DIR=/usr/include/python3.5m \
    -D PYTHON3_LIBRARY=/usr/lib/x86_64-linux-gnu/libpython3.5m.so.1 \
    -D PYTHON3_NUMPY_PATH=/usr/local/lib/python3.5/dist-packages \
    -D PYTHON2_EXECUTABLE=$(which python2)\
    -D PYTHON2_INCLUDE_DIR=/usr/include/python2.7 \
    -D PYTHON2_LIBRARY=/usr/lib/x86_64-linux-gnu/libpython2.7.so.1 \
    -D PYTHON2_NUMPY_PATH=/usr/local/lib/python2.7/dist-packages ..

這一步很關鍵，你需要檢查輸出的結果，如下必須要有 python3 相關的路徑信息，否則後面即使編譯成功了，其 python3 接口也無法調用。

編譯成功後可以看到 python2 和 python3 接口都編譯成功了。

2. caffe-ssd

主要參考

第一篇博客已經寫的比較全了，不過文中沒有將 opencv3 放出來。另外在執行

for req in $(cat requirements.txt); do sudo pip3 install --no-cache-dir $req; done

需要看是不是每項都符合要求，如果有哪一項不滿足，會下載安裝，但是比較慢，如果下載不成功，可以自己手動單獨安裝對應的項，然後在運行上面的命令，看是否都已經滿足，在把所有的要求項都滿足之後，後面 build 起來其實是非常順利的。

3. 測試 caffe

這部分主要參考 SSD: Single Shot MultiBox Detector 檢測單張圖片.
但是在實際操作中，上面參考的代碼並不能跑起來，部分是因爲上面測試的是 python2，而我需要測試的是 python3，這一部分改動比較容易。還有一個原因就是環境還是有差別，比如在用到 python 的路徑時直接指定。下面是我測試成功的代碼。

################################################
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

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

# Make sure that caffe is on the python path:
caffe_root = '/home/alvin/caffe/caffe-ssd/examples'  # this file is expected to be in {caffe_root}/examples
import os
os.chdir(caffe_root)
import sys
sys.path.insert(0, '/home/alvin/caffe/caffe-ssd/python')

import caffe
caffe.set_device(0)
caffe.set_mode_gpu()

##################################################
from google.protobuf import text_format
from caffe.proto import caffe_pb2

# load PASCAL VOC labels
labelmap_file = '/home/alvin/caffe/caffe-ssd/data/VOC0712/labelmap_voc.prototxt'
file = open(labelmap_file, 'r')
labelmap = caffe_pb2.LabelMap()
text_format.Merge(str(file.read()), labelmap)

def get_labelname(labelmap, labels):
    num_labels = len(labelmap.item)
    labelnames = []
    if type(labels) is not list:
        labels = [labels]
    for label in labels:
        found = False
        for i in range(0, num_labels):
            if label == labelmap.item[i].label:
                found = True
                labelnames.append(labelmap.item[i].display_name)
                break
        assert found == True
    return labelnames
    ###################################################
    model_def = '/home/alvin/caffe/caffe-ssd/models/VGGNet/VOC0712/SSD_300x300/deploy.prototxt'
model_weights = '/home/alvin/caffe/caffe-ssd/models/VGGNet/VOC0712/SSD_300x300/VGG_VOC0712_SSD_300x300_iter_120000.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)

# 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.array([104,117,123])) # 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
######################################################
# set net to batch size of 1
image_resize = 300
net.blobs['data'].reshape(1,3,image_resize,image_resize)
######################################################
image = caffe.io.load_image('/home/alvin/caffe/caffe-ssd/examples/images/fish-bike.jpg')
plt.imshow(image)
transformed_image = transformer.preprocess('data', image)
net.blobs['data'].data[...] = transformed_image

# Forward pass.
detections = net.forward()['detection_out']

# Parse the outputs.
det_label = detections[0,0,:,1]
det_conf = detections[0,0,:,2]
det_xmin = detections[0,0,:,3]
det_ymin = detections[0,0,:,4]
det_xmax = detections[0,0,:,5]
det_ymax = detections[0,0,:,6]

# Get detections with confidence higher than 0.6.
top_indices = [i for i, conf in enumerate(det_conf) if conf >= 0.6]

top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_labels = get_labelname(labelmap, top_label_indices)
top_xmin = det_xmin[top_indices]
top_ymin = det_ymin[top_indices]
top_xmax = det_xmax[top_indices]
top_ymax = det_ymax[top_indices]
############################################################
colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()

plt.imshow(image)
currentAxis = plt.gca()

for i in range(top_conf.shape[0]):
    xmin = int(round(top_xmin[i] * image.shape[1]))
    ymin = int(round(top_ymin[i] * image.shape[0]))
    xmax = int(round(top_xmax[i] * image.shape[1]))
    ymax = int(round(top_ymax[i] * image.shape[0]))
    score = top_conf[i]
    label = int(top_label_indices[i])
    label_name = top_labels[i]
    display_txt = '%s: %.2f'%(label_name, score)
    coords = (xmin, ymin), xmax-xmin+1, ymax-ymin+1
    color = colors[label]
    currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor=color, linewidth=2))
    currentAxis.text(xmin, ymin, display_txt, bbox={'facecolor':color, 'alpha':0.5})

發表評論

所有評論

還沒有人評論，想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.

Ubuntu16.04 + Opencv3.4.2 + python3.5 + caffe

Ubuntu16.04 + Opencv3.4.2 + python3.5 + caffe-ssd

1. opencv3.4.2

2. caffe-ssd

3. 測試 caffe

交叉熵損失函數總結: 定義、應用及求導

深度神經網絡中常用的激活函數的優缺點分析

ubuntu自帶的merge工具 Meld Diff Tool 無法啓動

pytorch 中的 transforms.TenCrop 和 transforms.FiveCrop 講解

Ubuntu 16.04 裝機指南（分區 + 顯卡驅動 + Cuda9.0 + CUDNN7.0）

https://yachay.unat.edu.pe/blog/index.php?comment_area=format_blog&comment_component=blog&comment_co

linux以太網驅動總結