Closed alanmcivor1959 closed 1 year ago
Can you try doing 'sudo make install' and then running the program without specifying a path (i.e. just detectnet-console
From: alanmcivor1959 notifications@github.com Sent: Saturday, September 28, 2019 5:59:33 AM To: dusty-nv/jetson-inference jetson-inference@noreply.github.com Cc: Subscribed subscribed@noreply.github.com Subject: [dusty-nv/jetson-inference] detectnet-console --network (#418)
If you run detectnet-console in the jetson-inference/build/aarch64/bin/ with a --network argument it works fine. If you run it in another directory it fails with errors like this
[TRT] binding to output 1 bboxes dims (b=1 c=4 h=28 w=28) size=12544 device GPU, /home/alan/hello_ai_world/jetson-inference/build/aarch64/bin/networks/facenet-120/snapshot_iter_24000.caffemodel initialized. detectNet -- number object classes: 1 detectNet -- maximum bounding boxes: 784 detectNet -- loaded 1 class info entries detectNet -- number of object classes: 1 [image] failed to find file 'facenet' failed to load image 'facenet'
The above is on a Jetson TX2
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/dusty-nv/jetson-inference/issues/418?email_source=notifications&email_token=ADVEGKYDMFKV3OPPTGTNOIDQL4TILA5CNFSM4I3NREAKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HOJTNGQ, or mute the threadhttps://github.com/notifications/unsubscribe-auth/ADVEGKZIZXBXXSTGPL3GYELQL4TILANCNFSM4I3NREAA.
I did a 'make install' and tried again without the path. The result was exactly the same.
Can you provide the command line you are using?
From: alanmcivor1959 notifications@github.com Sent: Sunday, September 29, 2019 4:55:21 AM To: dusty-nv/jetson-inference jetson-inference@noreply.github.com Cc: Dustin Franklin dustinf@nvidia.com; Comment comment@noreply.github.com Subject: Re: [dusty-nv/jetson-inference] detectnet-console --network (#418)
I did a 'make install' and tried again without the path. The result was exactly the same.
— You are receiving this because you commented. Reply to this email directly, view it on GitHubhttps://github.com/dusty-nv/jetson-inference/issues/418?email_source=notifications&email_token=ADVEGK376LXRHF3AP7YZWPTQMB3QTA5CNFSM4I3NREAKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD73NWGA#issuecomment-536271640, or mute the threadhttps://github.com/notifications/unsubscribe-auth/ADVEGK3IJW42INGPTCU2263QMB3QTANCNFSM4I3NREAA.
Hi,
Here is my command line, plus all the output.
Alan
alan@jetson:~/signage_20140731-1212$ detectnet-console --network pednet signage_20140731-1212_001_00744.ppm out.png
detectNet -- loading detection network model from: -- prototxt networks/ped-100/deploy.prototxt -- model networks/ped-100/snapshot_iter_70800.caffemodel -- input_blob 'data' -- output_cvg 'coverage' -- output_bbox 'bboxes' -- mean_pixel 0.000000 -- mean_binary NULL -- class_labels networks/ped-100/class_labels.txt -- threshold 0.500000 -- batch_size 1
[TRT] TensorRT version 5.1.6 [TRT] loading NVIDIA plugins... [TRT] Plugin Creator registration succeeded - GridAnchor_TRT [TRT] Plugin Creator registration succeeded - NMS_TRT [TRT] Plugin Creator registration succeeded - Reorg_TRT [TRT] Plugin Creator registration succeeded - Region_TRT [TRT] Plugin Creator registration succeeded - Clip_TRT [TRT] Plugin Creator registration succeeded - LReLU_TRT [TRT] Plugin Creator registration succeeded - PriorBox_TRT [TRT] Plugin Creator registration succeeded - Normalize_TRT [TRT] Plugin Creator registration succeeded - RPROI_TRT [TRT] Plugin Creator registration succeeded - BatchedNMS_TRT [TRT] completed loading NVIDIA plugins. [TRT] detected model format - caffe (extension '.caffemodel') [TRT] desired precision specified for GPU: FASTEST [TRT] requested fasted precision for device GPU without providing valid calibrator, disabling INT8 [TRT] native precisions detected for GPU: FP32, FP16 [TRT] selecting fastest native precision for GPU: FP16 [TRT] attempting to open engine cache file /usr/local/bin/networks/ped-100/snapshot_iter_70800.caffemodel.1.1.GPU.FP16.engine [TRT] loading network profile from engine cache... /usr/local/bin/networks/ped-100/snapshot_iter_70800.caffemodel.1.1.GPU.FP16.engine [TRT] device GPU, /usr/local/bin/networks/ped-100/snapshot_iter_70800.caffemodel loaded [TRT] device GPU, CUDA engine context initialized with 3 bindings [TRT] binding -- index 0 -- name 'data' -- type FP32 -- in/out INPUT -- # dims 3 -- dim #0 3 (CHANNEL) -- dim #1 512 (SPATIAL) -- dim #2 1024 (SPATIAL) [TRT] binding -- index 1 -- name 'coverage' -- type FP32 -- in/out OUTPUT -- # dims 3 -- dim #0 1 (CHANNEL) -- dim #1 32 (SPATIAL) -- dim #2 64 (SPATIAL) [TRT] binding -- index 2 -- name 'bboxes' -- type FP32 -- in/out OUTPUT -- # dims 3 -- dim #0 4 (CHANNEL) -- dim #1 32 (SPATIAL) -- dim #2 64 (SPATIAL) [TRT] binding to input 0 data binding index: 0 [TRT] binding to input 0 data dims (b=1 c=3 h=512 w=1024) size=6291456 [TRT] binding to output 0 coverage binding index: 1 [TRT] binding to output 0 coverage dims (b=1 c=1 h=32 w=64) size=8192 [TRT] binding to output 1 bboxes binding index: 2 [TRT] binding to output 1 bboxes dims (b=1 c=4 h=32 w=64) size=32768 device GPU, /usr/local/bin/networks/ped-100/snapshot_iter_70800.caffemodel initialized. detectNet -- number object classes: 1 detectNet -- maximum bounding boxes: 2048 detectNet -- loaded 1 class info entries detectNet -- number of object classes: 1 [image] failed to find file 'pednet' failed to load image 'pednet' alan@jetson:~/signage_20140731-1212$
Hi - this never worked, no matter which directory you used. The problem is in CommandLine::getPosition The loop doesn't increment 'i' again when removing the first (--network) argument (or any argument..) - but it should. With that change, it stops trying to load the network as a jpeg instead the image, and has the right image filename.
Can you try using --network=pednet
instead of --network pednet
?
That works.
The issue is then that the --help flag of it, fed via the imageNet class says:
imageNet arguments: --network NETWORK pre-trained model to load, one of the following:
whereas actually it wants to see "--network=NETWORK" - this is true of every arg that this class takes, they all want a second arg provided with an '=' not a space.
Changing the output of imageNet::usage would be a simple/clean solution.
I just hit the same issue, and the same fix works. I'm not sure why it makes a difference, as I've used argparse many times and never used '=' signs with it...
If you run detectnet-console in the jetson-inference/build/aarch64/bin/ with a --network argument it works fine. If you run it in another directory it fails with errors like this
[TRT] binding to output 1 bboxes dims (b=1 c=4 h=28 w=28) size=12544 device GPU, /home/alan/hello_ai_world/jetson-inference/build/aarch64/bin/networks/facenet-120/snapshot_iter_24000.caffemodel initialized. detectNet -- number object classes: 1 detectNet -- maximum bounding boxes: 784 detectNet -- loaded 1 class info entries detectNet -- number of object classes: 1 [image] failed to find file 'facenet' failed to load image 'facenet'
The above is on a Jetson TX2