5 | 
6 | 
7 |
8 | Image object detection demo(YOLO,SSD, Faster rcnn, etc.) running as a Flask web server.
9 |
10 | > ***Notice***
11 | This repo is not a turnkey project for object detection web system but an easy template for those who are not familiar with Web development just like me. You need to understand and modify the code little or much to use.
12 |
13 | ## Requirements
14 |
15 | The demo server requires Python with some dependencies.
16 | To make sure you have the dependencies, please run `pip install -r examples/web_demo/requirements.txt`.
17 |
18 | ## Run
19 |
20 | Running `python app.py` will bring up the demo server, accessible at `http://0.0.0.0:5000`.
21 | You can enable debug mode of the web server, or switch to a different port:
22 |
23 | % python app.py -h
24 | Usage: app.py [options]
25 |
26 | Options:
27 | -h, --help show this help message and exit
28 | -d, --debug enable debug mode
29 | -p PORT, --port=PORT which port to serve content on
30 |
31 | ## More
32 |
33 | The Javascript code `static/js/template.js` includes several part:
34 |
35 | - use of `Dropzone.js`(Drag and drop file plugin) to upload image and get result with AJAX.
36 | - parse JSON result and draw rectangles on image in browser canvas.
37 |
--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | werkzeug
2 | flask
3 | tornado
4 | numpy
5 | pandas
6 | pillow
7 | pyyaml
8 |
--------------------------------------------------------------------------------
/ssd_detect.py:
--------------------------------------------------------------------------------
1 | #encoding=utf8
2 | '''
3 | Detection with SSD
4 | In this example, we will load a SSD model and use it to detect objects.
5 | '''
6 |
7 | import os
8 | import sys
9 | import argparse
10 | import numpy as np
11 | from PIL import Image, ImageDraw
12 | # Make sure that caffe is on the python path:
13 | caffe_root = '/home/s05/caffe_ssd/caffe/'
14 | os.chdir(caffe_root)
15 | sys.path.insert(0, os.path.join(caffe_root, 'python'))
16 | import caffe
17 |
18 | from google.protobuf import text_format
19 | from caffe.proto import caffe_pb2
20 |
21 |
22 | def get_labelname(labelmap, labels):
23 | num_labels = len(labelmap.item)
24 | labelnames = []
25 | if type(labels) is not list:
26 | labels = [labels]
27 | for label in labels:
28 | found = False
29 | for i in xrange(0, num_labels):
30 | if label == labelmap.item[i].label:
31 | found = True
32 | labelnames.append(labelmap.item[i].display_name)
33 | break
34 | assert found == True
35 | return labelnames
36 |
37 | class CaffeDetection:
38 | def __init__(self, gpu_id, model_def, model_weights, image_resize, labelmap_file):
39 | if gpu_id == -1:
40 | caffe.set_mode_cpu()
41 | else:
42 | caffe.set_device(gpu_id)
43 | caffe.set_mode_gpu()
44 |
45 | self.image_resize = image_resize
46 | # Load the net in the test phase for inference, and configure input preprocessing.
47 | self.net = caffe.Net(model_def, # defines the structure of the model
48 | model_weights, # contains the trained weights
49 | caffe.TEST) # use test mode (e.g., don't perform dropout)
50 | # input preprocessing: 'data' is the name of the input blob == net.inputs[0]
51 | self.transformer = caffe.io.Transformer({'data': self.net.blobs['data'].data.shape})
52 | self.transformer.set_transpose('data', (2, 0, 1))
53 | self.transformer.set_mean('data', np.array([104, 117, 123])) # mean pixel
54 | # the reference model operates on images in [0,255] range instead of [0,1]
55 | self.transformer.set_raw_scale('data', 255)
56 | # the reference model has channels in BGR order instead of RGB
57 | self.transformer.set_channel_swap('data', (2, 1, 0))
58 |
59 | # load PASCAL VOC labels
60 | file = open(labelmap_file, 'r')
61 | self.labelmap = caffe_pb2.LabelMap()
62 | text_format.Merge(str(file.read()), self.labelmap)
63 |
64 | def detect(self, image_file, conf_thresh=0.5, topn=5):
65 | '''
66 | SSD detection
67 | '''
68 | # set net to batch size of 1
69 | # image_resize = 300
70 | self.net.blobs['data'].reshape(1, 3, self.image_resize, self.image_resize)
71 | image = caffe.io.load_image(image_file)
72 |
73 | #Run the net and examine the top_k results
74 | transformed_image = self.transformer.preprocess('data', image)
75 | self.net.blobs['data'].data[...] = transformed_image
76 |
77 | # Forward pass.
78 | detections = self.net.forward()['detection_out']
79 |
80 | # Parse the outputs.
81 | det_label = detections[0,0,:,1]
82 | det_conf = detections[0,0,:,2]
83 | det_xmin = detections[0,0,:,3]
84 | det_ymin = detections[0,0,:,4]
85 | det_xmax = detections[0,0,:,5]
86 | det_ymax = detections[0,0,:,6]
87 | #conf_thresh=0.8
88 | # Get detections with confidence higher than 0.6.
89 | top_indices = [i for i, conf in enumerate(det_conf) if conf >= conf_thresh]
90 |
91 | top_conf = det_conf[top_indices]
92 | top_label_indices = det_label[top_indices].tolist()
93 | top_labels = get_labelname(self.labelmap, top_label_indices)
94 | top_xmin = det_xmin[top_indices]
95 | top_ymin = det_ymin[top_indices]
96 | top_xmax = det_xmax[top_indices]
97 | top_ymax = det_ymax[top_indices]
98 |
99 | result = []
100 | for i in xrange(min(topn, top_conf.shape[0])):
101 | xmin = top_xmin[i] # xmin = int(round(top_xmin[i] * image.shape[1]))
102 | ymin = top_ymin[i] # ymin = int(round(top_ymin[i] * image.shape[0]))
103 | xmax = top_xmax[i] # xmax = int(round(top_xmax[i] * image.shape[1]))
104 | ymax = top_ymax[i] # ymax = int(round(top_ymax[i] * image.shape[0]))
105 | score = top_conf[i]
106 | label = int(top_label_indices[i])
107 | label_name = top_labels[i]
108 | result.append([xmin, ymin, xmax, ymax, label, score, label_name])
109 | return result
110 |
111 | def main(args):
112 | '''main '''
113 | detection = CaffeDetection(args.gpu_id,
114 | args.model_def, args.model_weights,
115 | args.image_resize, args.labelmap_file)
116 | result = detection.detect(args.image_file)
117 | print result
118 |
119 | img = Image.open(args.image_file)
120 | draw = ImageDraw.Draw(img)
121 | width, height = img.size
122 | print width, height
123 | for item in result:
124 | xmin = int(round(item[0] * width))
125 | ymin = int(round(item[1] * height))
126 | xmax = int(round(item[2] * width))
127 | ymax = int(round(item[3] * height))
128 | draw.rectangle([xmin, ymin, xmax, ymax], outline=(255, 0, 0))
129 | draw.text([xmin, ymin], item[-1] + str(item[-2]), (0, 0, 255))
130 | print item
131 | print [xmin, ymin, xmax, ymax]
132 | print [xmin, ymin], item[-1]
133 | img.save('detect_result.jpg')
134 |
135 |
136 | def parse_args():
137 | '''parse args'''
138 | parser = argparse.ArgumentParser()
139 | parser.add_argument('--gpu_id', type=int, default=0, help='gpu id')
140 | parser.add_argument('--labelmap_file',
141 | default='/home/s05/caffe_ssd/caffe/data/VOC0712/labelmap_voc.prototxt')
142 | parser.add_argument('--model_def',
143 | default='/home/s05/caffe_ssd/caffe/models/VGGNet/VOC0712/SSD_300x300/deploy.prototxt')
144 | parser.add_argument('--image_resize', default=300, type=int)
145 | parser.add_argument('--model_weights',
146 | default='/home/s05/caffe_ssd/caffe/models/VGGNet/VOC0712/SSD_300x300/'
147 | 'VGG_VOC0712_SSD_300x300_iter_6000.caffemodel')
148 | # parser.add_argument('--image_file', default='/home/s05/caffe_ssd/caffe/examples/images/plane (25).jpg')
149 | return parser.parse_args()
150 | def load_net():
151 | args = parse_args()
152 | detection = CaffeDetection(args.gpu_id,
153 | args.model_def, args.model_weights,
154 | args.image_resize, args.labelmap_file)
155 | return detection
156 | def detect(net,image_file):
157 | result = net.detect(image_file)
158 | return result
159 | if __name__ == '__main__':
160 | main(parse_args())
--------------------------------------------------------------------------------
/static/js/template.js:
--------------------------------------------------------------------------------
1 | function require(script) {
2 | $.ajax({
3 | url: script,
4 | dataType: "script",
5 | async: false, // <-- This is the key, however this has been deprecated, for more solutions, see https://stackoverflow.com/questions/950087/how-do-i-include-a-javascript-file-in-another-javascript-file
6 | success: function () {
7 | // all good...
8 | },
9 | error: function () {
10 | throw new Error("Could not load script " + script);
11 | }
12 | });
13 | }
14 | // load the script of decompressing tiff image, for tiff/tif is not normal images supported by browser
15 | //require("/static/js/tiff.min.js");
16 | // load the script of dropzone(drag and drop file utils).
17 | //require("/static/js/dropzone.js");
18 |
19 | var currentFile = null;
20 | var resizeRatio = 1;
21 | var dx = 0;
22 | var dy = 0;
23 | Dropzone.autoDiscover = false;
24 | var myDropzone = new Dropzone("#dropz", { //url: "/upload-det-rsi"});
25 | url: "/upload-det-rsi",
26 | timeout: 600000, /*milliseconds, default is 30 sec*/
27 | maxFiles: 100,
28 | maxFilesize: 1024,
29 | // acceptedFiles: ".jpg,.jpeg,.doc,.docx,.ppt,.pptx,.txt,.avi,.pdf,.mp3,.zip",
30 | // autoProcessQueue: false,
31 | // paramName: "file",
32 | createImageThumbnails: false,//不显示缩略图
33 | previewsContainer: false,//不显示preview
34 | // dictDefaultMessage: "拖入需要上传的文件",
35 | init: function () {
36 | var myDropzone = this;//, submitButton = document.querySelector("#qr"),
37 | //cancelButton = document.querySelector("#cancel");
38 | var picshow = document.querySelector("#dropz");
39 | myDropzone.on('addedfile', function (file) {
40 | //添加上传文件的过程
41 | if (currentFile) {
42 | this.removeFile(currentFile);
43 | }
44 | currentFile = file;
45 | picshow.setAttribute('plus_sign', 'none');
46 | $(".dz-message").html(null);
47 | var subregions = document.getElementById('rightpic');
48 | $(subregions).empty();
49 | subregions.setAttribute("class", "rightpic_hide");
50 | var FR= new FileReader();
51 | // handle special type of images
52 | if (file.type != "image/tif" && file.type != "image/tiff") {
53 | FR.onload = function(e) {
54 | // console.log( e.target.result); //This is the base64 data of file(gif) dropped
55 | //if you want to display it somewhere in your previewTemplate
56 | // var temp = file.previewTemplate;
57 | // picshow.innerHTML = "54 | 55 | 56 | 康行天下 57 | 58 |
59 |耗时 {{ result[3] }} 秒.
126 |