caffe-SSD 安裝、訓練、SSD測試（ubuntu18.04+cuda9.0+openvc3.4）
阿新 • • 發佈：2018-12-13
安裝及MNIST模型測試、matlab caffe介面測試
https://blog.csdn.net/qq_35608277/article/details/84938244
自己看程式碼提供者的最直接，大家都是根據他的ｃｏｐｙ的：
https://github.com/weiliu89/caffe/tree/ssd
1 資料準備
１.1 voc0712資料集下載
# Download the data. cd $HOME/data wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar # Extract the data. tar -xvf VOCtrainval_11-May-2012.tar tar -xvf VOCtrainval_06-Nov-2007.tar tar -xvf VOCtest_06-Nov-2007.tar
放在/home/data下
然後回到ｃａｆｆｅ-ssd資料夾下生成LMDB 檔案.
cd caffe－ssd
./data/VOC0712/create_list.sh
# It will create lmdb files for trainval and test with encoded original image:
# - $HOME/data/VOCdevkit/VOC0712/lmdb/VOC0712_trainval_lmdb
# - $HOME/data/VOCdevkit/VOC0712/lmdb/VOC0712_test_lmdb
./data/VOC0712/create_data.sh
便於自己訓練
預訓練模型（VGG）：VGG_ILSVRC_16_layers_fc_reduced.caffemodel
（下載地址：密碼: t9ub）
下載完畢後將VGG模型放到caffe主目錄下 models\VGGNet 下面(如果沒有的話，models 下面沒有的話mkdir VGGNet)
1.３ 下載訓練好的權重
ｇｉｔ model
百度雲
連結：http://pan.baidu.com/s/1kVoJ6GR 密碼：leo6
解壓替換掉ｍｏｄｅｌｓ裡的檔案。
VGG_VOC0712_SSD_300x300_iter_240000.caffemodel,
.prototxt files, python scripts.
2 測試模型
在caffe-ssd中新建資料夾ｍｙ_detection.定義detect.py,這裡沒有用ipynb
https://github.com/weiliu89/caffe/blob/ssd/examples/ssd_detect.ipynb
# coding: utf-8
# Note: this file is expected to be in {caffe_root}/examples
# ### 1. Setup
from __future__ import print_function
import numpy as np
import matplotlib.pyplot as plt
import pylab
plt.rcParams['figure.figsize'] = (10, 10)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
caffe_root = '../'
import os
os.chdir(caffe_root)
import sys
#sys.path.insert(0, '/home/lilai/LL/caffe/python')
import caffe
from google.protobuf import text_format
from caffe.proto import caffe_pb2
caffe.set_device(0)
caffe.set_mode_gpu()
labelmap_file = '/home/dong/Downloads/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 xrange(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/dong/Downloads/caffe-ssd/my_detection/deploy.prototxt'
model_weights = '/home/dong/Downloads/caffe-ssd/models/VGGNet/VOC0712/SSD_300x300/VGG_VOC0712_SSD_300x300_iter_240000.caffemodel'
net = caffe.Net(model_def, model_weights, 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.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
# ### 2. SSD detection
# Load an image.
image_resize = 300
net.blobs['data'].reshape(1, 3, image_resize, image_resize)
image = caffe.io.load_image('/home/dong/Downloads/caffe-ssd/examples/images/fish-bike.jpg')
plt.imshow(image)
# Run the net and examine the top_k results
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]
# Plot the boxes
colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()
currentAxis = plt.gca()
for i in xrange(top_conf.shape[0]):
# bbox value
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
score = top_conf[i]
# label
label = int(top_label_indices[i])
label_name = top_labels[i]
# display info: label score xmin ymin xmax ymax
display_txt = '%s: %.2f %d %d %d %d' % (label_name, score,xmin, ymin, xmax, ymax)
# display_bbox_value = '%d %d %d %d' % (xmin, ymin, xmax, ymax)
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})
# currentAxis.text((xmin+xmax)/2, (ymin+ymax)/2, display_bbox_value, bbox={'facecolor': color, 'alpha': 0.5})
plt.imshow(image)
pylab.show()
選擇模型檔案，從ｍｏｄｅｌｓ/VGGNet中複製一份到自己資料夾。並且修改上述路徑
deploy.prototxt
最後幾行，修改ｌａｂｅｌ和ｎａｍｅ_size 的路徑
detection_output_param {
num_classes: 21
share_location: true
background_label_id: 0
nms_param {
nms_threshold: 0.449999988079
top_k: 400
}
save_output_param {
output_directory: "/home/dong/Downloads/caffe-ssd/my_detection/myout"
output_name_prefix: "comp4_det_test_"
output_format: "VOC"
label_map_file: "/home/dong/Downloads/caffe-ssd/my_detection/labelmap_voc.prototxt"
name_size_file: "/home/dong/Downloads/caffe-ssd/my_detection/test_name_size.txt"
num_test_image: 4952
}
code_type: CENTER_SIZE
keep_top_k: 200
confidence_threshold: 0.00999999977648
}
}
test_name_size.txt，labelmap_voc.prototxt複製到自己檔案路徑裡。
命令列執行，
python my_detection/detect.py
ｒｅｆ
https://www.jianshu.com/p/109e30491ec4