caffe-ssd使用预训练模型做目标检测

首先参考https://www.jianshu.com/p/4eaedaeafcb4

这是一个傻瓜似的目标检测样例，目前还不清楚图片怎么转换，怎么验证，后续继续跟进

• 模型测试
  （1）图片数据集上测试

python examples/ssd/score_ssd_pascal.py

输出为

I0505 10:32:27.929069 16272 caffe.cpp:155] Finetuning from models/VGGNet/VOC0712/SSD_300x300/VGG_VOC0712_SSD_300x300_iter_120000.caffemodel
I0505 10:32:28.052016 16272 net.cpp:761] Ignoring source layer mbox_loss
I0505 10:32:28.053956 16272 caffe.cpp:251] Starting Optimization
I0505 10:32:28.053966 16272 solver.cpp:294] Solving VGG_VOC0712_SSD_300x300_train
I0505 10:32:28.053969 16272 solver.cpp:295] Learning Rate Policy: multistep
I0505 10:32:28.197612 16272 solver.cpp:332] Iteration 0, loss = 1.45893
I0505 10:32:28.197657 16272 solver.cpp:433] Iteration 0, Testing net (#0)
I0505 10:32:28.213793 16272 net.cpp:693] Ignoring source layer mbox_loss
I0505 10:42:04.390517 16272 solver.cpp:546]     Test net output #0: detection_eval = 0.570833
I0505 10:42:04.414819 16272 solver.cpp:337] Optimization Done.
I0505 10:42:04.414847 16272 caffe.cpp:254] Optimization Done.

作者：Ericzhang922
链接：https://www.jianshu.com/p/4eaedaeafcb4
來源：简书
简书著作权归作者所有，任何形式的转载都请联系作者获得授权并注明出处。

View Code

可以看到图片数据集上的检测结果为57.0833%。利用caffe/examples/ssd_detect.py文件可以用单张图片测试检测效果(注意文件内加载文件的路径，如果报错修改为绝对路径)：

 

 

可以得到如下结果

然后来看caffe/examples/ssd_detect.py中的代码

#encoding=utf8
'''
Detection with SSD
In this example, we will load a SSD model and use it to detect objects.
'''

import os
import sys
import argparse
import numpy as np
from PIL import Image, ImageDraw
# Make sure that caffe is on the python path:
caffe_root = './'
os.chdir(caffe_root)
sys.path.insert(0, os.path.join(caffe_root, 'python'))
import caffe

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


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

class CaffeDetection:
    def __init__(self, gpu_id, model_def, model_weights, image_resize, labelmap_file):
        caffe.set_device(gpu_id)
        caffe.set_mode_gpu()

        self.image_resize = image_resize
        # Load the net in the test phase for inference, and configure input preprocessing.
        self.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]
        self.transformer = caffe.io.Transformer({'data': self.net.blobs['data'].data.shape})
        self.transformer.set_transpose('data', (2, 0, 1))
        self.transformer.set_mean('data', np.array([104, 117, 123])) # mean pixel
        # the reference model operates on images in [0,255] range instead of [0,1]
        self.transformer.set_raw_scale('data', 255)
        # the reference model has channels in BGR order instead of RGB
        self.transformer.set_channel_swap('data', (2, 1, 0))

        # load PASCAL VOC labels
        file = open(labelmap_file, 'r')
        self.labelmap = caffe_pb2.LabelMap()
        text_format.Merge(str(file.read()), self.labelmap)

    def detect(self, image_file, conf_thresh=0.5, topn=5):
        '''
        SSD detection
        '''
        # set net to batch size of 1
        # image_resize = 300
        self.net.blobs['data'].reshape(1, 3, self.image_resize, self.image_resize)
        image = caffe.io.load_image(image_file)

        #Run the net and examine the top_k results
        transformed_image = self.transformer.preprocess('data', image)
        self.net.blobs['data'].data[...] = transformed_image

        # Forward pass.
        detections = self.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 >= conf_thresh]

        top_conf = det_conf[top_indices]
        top_label_indices = det_label[top_indices].tolist()
        top_labels = get_labelname(self.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]

        result = []
        for i in xrange(min(topn, top_conf.shape[0])):
            xmin = top_xmin[i] # xmin = int(round(top_xmin[i] * image.shape[1]))
            ymin = top_ymin[i] # ymin = int(round(top_ymin[i] * image.shape[0]))
            xmax = top_xmax[i] # xmax = int(round(top_xmax[i] * image.shape[1]))
            ymax = top_ymax[i] # ymax = int(round(top_ymax[i] * image.shape[0]))
            score = top_conf[i]
            label = int(top_label_indices[i])
            label_name = top_labels[i]
            result.append([xmin, ymin, xmax, ymax, label, score, label_name])
        return result

def main(args):
    '''main '''
    detection = CaffeDetection(args.gpu_id,
                               args.model_def, args.model_weights,
                               args.image_resize, args.labelmap_file)
    result = detection.detect(args.image_file)
    print result

    img = Image.open(args.image_file)
    draw = ImageDraw.Draw(img)
    width, height = img.size
    print width, height
    for item in result:
        xmin = int(round(item[0] * width))
        ymin = int(round(item[1] * height))
        xmax = int(round(item[2] * width))
        ymax = int(round(item[3] * height))
        draw.rectangle([xmin, ymin, xmax, ymax], outline=(255, 0, 0))
        draw.text([xmin, ymin], item[-1] + str(item[-2]), (0, 0, 255))
        print item
        print [xmin, ymin, xmax, ymax]
        print [xmin, ymin], item[-1]
    img.save('detect_result.jpg')


def parse_args():
    '''parse args'''
    parser = argparse.ArgumentParser()
    parser.add_argument('--gpu_id', type=int, default=0, help='gpu id')
    parser.add_argument('--labelmap_file',
                        default='data/VOC0712/labelmap_voc.prototxt')
    parser.add_argument('--model_def',
                        default='models/VGGNet/VOC0712/SSD_300x300/deploy.prototxt')
    parser.add_argument('--image_resize', default=300, type=int)
    parser.add_argument('--model_weights',
                        default='models/VGGNet/VOC0712/SSD_300x300/'
                        'VGG_VOC0712_SSD_300x300_iter_120000.caffemodel')
    parser.add_argument('--image_file', default='examples/images/fish-bike.jpg')
    return parser.parse_args()

if __name__ == '__main__':
    main(parse_args())

View Code

首先看传参这部分

def parse_args():
    '''parse args'''
    parser = argparse.ArgumentParser()
    parser.add_argument('--gpu_id', type=int, default=0, help='gpu id')
    parser.add_argument('--labelmap_file',
                        default='data/VOC0712/labelmap_voc.prototxt')
    parser.add_argument('--model_def',
                        default='models/VGGNet/VOC0712/SSD_300x300/deploy.prototxt')
    parser.add_argument('--image_resize', default=300, type=int)
    parser.add_argument('--model_weights',
                        default='models/VGGNet/VOC0712/SSD_300x300/'
                        'VGG_VOC0712_SSD_300x300_iter_120000.caffemodel')
    parser.add_argument('--image_file', default='examples/images/fish-bike.jpg')
    return parser.parse_args()

通过这部分的代码，我们可以看到进行检测时与训练时不一样，不需要对图片格式进行转换，直接输入原始图片就可以