ahangchen/ncs_detection

Raspberry Pi NCS Object detection，端上CNN实践

NCS Raspberry Pi Object detection

• Download ncs graph model: https://pan.baidu.com/s/1WI_r6jazYikrcq2E6qklrQ key：4vs5
• run count_for_video_ncs.py with python2

Detail instruction: https://github.com/ahangchen/windy-afternoon/blob/master/linux/raspbian/ncs_detection.md

ncs_detection's Issues

google.protobuf.message.DecodeError: Tag had invalid wire type.

Hi ahangchen,

When i test my graph with my jpg file,it's output "google.protobuf.message.DecodeError: Tag had invalid wire type."
maybe my train step has mistake.how to tackle the problem or which step am i wrong?
Thanks in advance.

I use labelimg to dealwith jpg file.
ImageSets file like this:
########################
markimg39.jpg markimg39.xml
markimg50.jpg markimg50.xml
markimg67.jpg markimg67.xml
timg (18).jpg timg (18).xml
timg (33).jpg timg (33).xml
timg (19).jpg timg (19).xml
#######################

what's the "0.487500 0.320675 0.670000 0.433193" mean?

假设你的打的标签是这样一个文件raw_label.txt，假装我们数据集只有两张图片：
data/strange_animal/1017.jpg 0.487500 0.320675 0.670000 0.433193
data/strange_animal/1018.jpg 0.215000 0.293952 0.617500 0.481013

labelmap_coco.prototxt like this:
######################################
item {
name: "none_of_the_above"
label: 0
display_name: "background"
}
item {
name: "markpoint"
label: 1
display_name: "markpoint"
}

labelmap_coco.pbtxt like this: what's the name: "/m/01g317" mean?can i write this as same as display_name?

###########################
item {
name: "markpoint"
label: 1
display_name: "markpoint"
}
##############################
item {
name: "/m/01g317"
id: 1
display_name: "new"
}
item {
name: "/m/0199g"
id: 2
display_name: "bicycle"
}
#########################

my xml like this:

###########################
<annotation> <folder>train</folder> <filename>markimg2.jpg</filename> <path>H:\Tensorflow_ObjectDetection_MarkLabel\src\research\customized_model\images\pre\train\markimg2.jpg</path> <source> <database>Unknown</database> </source> <size> <width>640</width> <height>480</height> <depth>3</depth> </size> <segmented>0</segmented> <object> <name>markpoint</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>133</xmin> <ymin>225</ymin> <xmax>212</xmax> <ymax>298</ymax> </bndbox> </object> <object> <name>markpoint</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>265</xmin> <ymin>133</ymin> <xmax>338</xmax> <ymax>194</ymax> </bndbox> </object> <object> <name>markpoint</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>388</xmin> <ymin>133</ymin> <xmax>465</xmax> <ymax>196</ymax> </bndbox> </object> <object> <name>markpoint</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>381</xmin> <ymin>238</ymin> <xmax>472</xmax> <ymax>326</ymax> </bndbox> </object> <object> <name>markpoint</name> <pose>Unspecified</pose> <truncated>0</truncated> <difficult>0</difficult> <bndbox> <xmin>252</xmin> <ymin>357</ymin> <xmax>344</xmax> <ymax>462</ymax> </bndbox> </object> </annotation>
##############################
pi@raspberrypi:/workspace/ncs_detection $ python ncs_detection_testmarkpoint.py
mkdir: cannot create directory ‘r10_tmp’: File exists
rm: cannot remove 'r10_tmp/*': No such file or directory
[INFO] finding NCS devices...
[INFO] found 1 devices. device0 will be used. opening device0...
[INFO] loading the graph file into RPi memory...
[INFO] allocating the graph on the NCS...
<mvnc.mvncapi.Graph instance at 0x6cbce260>
('data/labelmap_coco.pbtxt', 1)
Traceback (most recent call last):
File "ncs_detection_testmarkpoint.py", line 172, in
count_for_video_ncs(img_dir, start_index, end_index)
File "ncs_detection_testmarkpoint.py", line 129, in count_for_video_ncs
category_index = label_prepare(PATH_TO_LABELS, NUM_CLASSES)
File "ncs_detection_testmarkpoint.py", line 96, in label_prepare
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
File "/home/pi/workspace/ncs_detection/object_detection/utils/label_map_util.py", line 122, in load_labelmap
label_map.ParseFromString(label_map_string)
File "/usr/local/lib/python2.7/dist-packages/protobuf-3.5.1-py2.7.egg/google/protobuf/message.py", line 185, in ParseFromString
self.MergeFromString(serialized)
File "/usr/local/lib/python2.7/dist-packages/protobuf-3.5.1-py2.7.egg/google/protobuf/internal/python_message.py", line 1083, in MergeFromString
if self._InternalParse(serialized, 0, length) != length:
File "/usr/local/lib/python2.7/dist-packages/protobuf-3.5.1-py2.7.egg/google/protobuf/internal/python_message.py", line 1109, in InternalParse
new_pos = local_SkipField(buffer, new_pos, end, tag_bytes)
File "/usr/local/lib/python2.7/dist-packages/protobuf-3.5.1-py2.7.egg/google/protobuf/internal/decoder.py", line 850, in SkipField
return WIRETYPE_TO_SKIPPER[wire_type](buffer, pos, end)
File "/usr/local/lib/python2.7/dist-packages/protobuf-3.5.1-py2.7.egg/google/protobuf/internal/decoder.py", line 820, in _RaiseInvalidWireType
raise _DecodeError('Tag had invalid wire type.')
google.protobuf.message.DecodeError: Tag had invalid wire type.
pi@raspberrypi:/workspace/ncs_detection $

AttributeError: 'module' object has no attribute 'EnumerateDevices'

你好，我在运行ncs_detection.py时报错：
File "ncs_detection.py", line 64, in ncs_prepare
devices = mvnc.EnumerateDevices()
AttributeError: 'module' object has no attribute 'EnumerateDevices'
请问有什么解决办法呢？