- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
I'm trying to compile a MobileNetSSD that is working find with OpenCV 3.3.0.
name: "MobileNet-SSD"
input: "data"
input_shape {
dim: 1
dim: 3
dim: 300
dim: 300
}
layer {
name: "conv0"
type: "Convolution"
bottom: "data"
top: "conv0"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 32
pad: 1
kernel_size: 3
stride: 2
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
.......
layer {
name: "conv13_mbox_loc_perm"
type: "Permute"
bottom: "conv13_mbox_loc"
top: "conv13_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv13_mbox_loc_flat"
type: "Flatten"
bottom: "conv13_mbox_loc_perm"
top: "conv13_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv13_mbox_conf"
type: "Convolution"
bottom: "conv13"
top: "conv13_mbox_conf"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 126
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
...................
layer {
name: "conv17_2_mbox_loc"
type: "Convolution"
bottom: "conv17_2"
top: "conv17_2_mbox_loc"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 24
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv17_2_mbox_loc_perm"
type: "Permute"
bottom: "conv17_2_mbox_loc"
top: "conv17_2_mbox_loc_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv17_2_mbox_loc_flat"
type: "Flatten"
bottom: "conv17_2_mbox_loc_perm"
top: "conv17_2_mbox_loc_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv17_2_mbox_conf"
type: "Convolution"
bottom: "conv17_2"
top: "conv17_2_mbox_conf"
param {
lr_mult: 1.0
decay_mult: 1.0
}
param {
lr_mult: 2.0
decay_mult: 0.0
}
convolution_param {
num_output: 126
kernel_size: 1
weight_filler {
type: "msra"
}
bias_filler {
type: "constant"
value: 0.0
}
}
}
layer {
name: "conv17_2_mbox_conf_perm"
type: "Permute"
bottom: "conv17_2_mbox_conf"
top: "conv17_2_mbox_conf_perm"
permute_param {
order: 0
order: 2
order: 3
order: 1
}
}
layer {
name: "conv17_2_mbox_conf_flat"
type: "Flatten"
bottom: "conv17_2_mbox_conf_perm"
top: "conv17_2_mbox_conf_flat"
flatten_param {
axis: 1
}
}
layer {
name: "conv17_2_mbox_priorbox"
type: "PriorBox"
bottom: "conv17_2"
bottom: "data"
top: "conv17_2_mbox_priorbox"
prior_box_param {
min_size: 285.0
max_size: 300.0
aspect_ratio: 2.0
aspect_ratio: 3.0
flip: true
clip: false
variance: 0.1
variance: 0.1
variance: 0.2
variance: 0.2
offset: 0.5
}
}
layer {
name: "mbox_loc"
type: "Concat"
bottom: "conv11_mbox_loc_flat"
bottom: "conv13_mbox_loc_flat"
bottom: "conv14_2_mbox_loc_flat"
bottom: "conv15_2_mbox_loc_flat"
bottom: "conv16_2_mbox_loc_flat"
bottom: "conv17_2_mbox_loc_flat"
top: "mbox_loc"
concat_param {
axis: 1
}
}
layer {
name: "mbox_conf"
type: "Concat"
bottom: "conv11_mbox_conf_flat"
bottom: "conv13_mbox_conf_flat"
bottom: "conv14_2_mbox_conf_flat"
bottom: "conv15_2_mbox_conf_flat"
bottom: "conv16_2_mbox_conf_flat"
bottom: "conv17_2_mbox_conf_flat"
top: "mbox_conf"
concat_param {
axis: 1
}
}
layer {
name: "mbox_priorbox"
type: "Concat"
bottom: "conv11_mbox_priorbox"
bottom: "conv13_mbox_priorbox"
bottom: "conv14_2_mbox_priorbox"
bottom: "conv15_2_mbox_priorbox"
bottom: "conv16_2_mbox_priorbox"
bottom: "conv17_2_mbox_priorbox"
top: "mbox_priorbox"
concat_param {
axis: 2
}
}
layer {
name: "mbox_conf_reshape"
type: "Reshape"
bottom: "mbox_conf"
top: "mbox_conf_reshape"
reshape_param {
shape {
dim: 0
dim: -1
dim: 21
}
}
}
layer {
name: "mbox_conf_softmax"
type: "Softmax"
bottom: "mbox_conf_reshape"
top: "mbox_conf_softmax"
softmax_param {
axis: 2
}
}
layer {
name: "mbox_conf_flatten"
type: "Flatten"
bottom: "mbox_conf_softmax"
top: "mbox_conf_flatten"
flatten_param {
axis: 1
}
}
layer {
name: "detection_out"
type: "DetectionOutput"
bottom: "mbox_loc"
bottom: "mbox_conf_flatten"
bottom: "mbox_priorbox"
top: "detection_out"
include {
phase: TEST
}
detection_output_param {
num_classes: 21
share_location: true
background_label_id: 0
nms_param {
nms_threshold: 0.45
top_k: 100
}
code_type: CENTER_SIZE
keep_top_k: 100
confidence_threshold: 0.25
}
}
and I'm getting this error:
vladi@vladi:~/workspace/ncsdk/examples/caffe/real-time-object-detection$ mvNCCompile MobileNetSSD_deploy.prototxt -s 12
mvNCCompile v02.00, Copyright @ Movidius Ltd 2016
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format caffe.NetParameter: 1177:17: Message type "caffe.LayerParameter" has no field named "permute_param".
WARNING: Logging before InitGoogleLogging() is written to STDERR
F1026 17:50:53.770750 32253 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: MobileNetSSD_deploy.prototxt
*** Check failure stack trace: ***
Aborted (core dumped)
I'm using latest SDK updated and compiled today.
vladi@vladi:~/workspace/ncsdk$ git pull
Already up-to-date.
my PYTHONPATH and version
vladi@vladi:~/workspace/ncsdk$ python --version
Python 2.7.13
vladi@vladi:~/workspace/ncsdk$ echo $PYTHONPATH
:/opt/movidius/caffe/python
vladi@vladi:~/workspace/ncsdk$
I'm running Ubuntu Desktop 17.04
Linux vladi 4.10.0-37-generic #41-Ubuntu SMP Fri Oct 6 20:20:37 UTC 2017 x86_64 x86_64 x86_64 GNU/Linux
Could you help me to understand what I'm doing wrong?
Sebastian
Link Copied
6 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@ssalomo1 You aren't doing anything wrong. The current SDK (1.09.00) doesn't support some of the layers required by this network (permute, priorbox, detectionoutput, flatten). Support for these layers is something we are looking into for a future release.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Tome,
Thanks for your answer, I'll wait for future releases to use this network.
In meantime, what is the supported network you can recommend me to do object detection?
Regards,
Sebastian.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@ssalomo1 In regards to object detection, you can check out the recently released Tiny Yolo example on the app zoo by visiting: https://ncsforum.movidius.com/discussion/345/tinyyolo-object-detection-example-is-now-in-the-ncappzoo-repository#latest . Also @dagoff has his version working at https://ncsforum.movidius.com/discussion/218/tiny-yolo-on-ncs. He has the project hosted on his github: https://github.com/gudovskiy/yoloNCS
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thank you very much.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Waiting for a future release to solve this problem.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
So I am having the same issue that you guys experienced around 8 months ago… I am using the NCSDK 2… I watched Ashwin's last webinar and pretty sure he showed MobileNet SSD…
pls advise!
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page