• State TI Thinks Resolved
  • Locked Locked
  • Replies 10 replies
  • Answers 1 answer
  • Subscribers 98 subscribers
  • Views 425 views
  • Users 0 members are here
Support feedback
Options
Options
Related

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: SDK

Makoto Nakamura
Prodigy 50 points
Part Number: TDA4VM
Other Parts Discussed in Thread: 4213

Tool/software:

I am trying the SDK 9.2.

I run the default demo, it is running like this:

root@tda4vm-sk:/opt/edgeai-gst-apps/apps_python# python3 app_edgeai.py ../configs/object_detection.yaml
libtidl_onnxrt_EP loaded 0x39211760
Final number of subgraphs created are : 1, - Offloaded Nodes - 283, Total Nodes - 283
APP: Init ... !!!
MEM: Init ... !!!
MEM: Initialized DMA HEAP (fd=5) !!!
MEM: Init ... Done !!!
IPC: Init ... !!!
IPC: Init ... Done !!!
REMOTE_SERVICE: Init ... !!!
REMOTE_SERVICE: Init ... Done !!!
4212.865192 s: GTC Frequency = 200 MHz
APP: Init ... Done !!!
4212.865268 s: VX_ZONE_INIT:Enabled
4212.865277 s: VX_ZONE_ERROR:Enabled
4212.865282 s: VX_ZONE_WARNING:Enabled
4212.865828 s: VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-0
4212.865924 s: VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-1
4212.866013 s: VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-2
4212.866109 s: VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-3
4212.866119 s: VX_ZONE_INIT:[tivxInitLocal:136] Initialization Done !!!
4212.866584 s: VX_ZONE_INIT:[tivxHostInitLocal:101] Initialization Done for HOST !!!
[ERROR] Could not get allowed GstCaps of device
4213.130218 s: VX_ZONE_ERROR:[vxGetStatus:1020] Reference is NULL
4213.134274 s: VX_ZONE_INIT:[tivxHostDeInitLocal:115] De-Initialization Done for HOST !!!
4213.138731 s: VX_ZONE_INIT:[tivxDeInitLocal:204] De-Initialization Done !!!
APP: Deinit ... !!!
REMOTE_SERVICE: Deinit ... !!!
REMOTE_SERVICE: Deinit ... Done !!!
IPC: Deinit ... !!!
IPC: DeInit ... Done !!!
MEM: Deinit ... !!!
DDR_SHARED_MEM: Alloc's: 15 alloc's of 32899080 bytes
DDR_SHARED_MEM: Free's : 15 free's of 32899080 bytes
DDR_SHARED_MEM: Open's : 0 allocs of 0 bytes
MEM: Deinit ... Done !!!
APP: Deinit ... Done !!!
root@tda4vm-sk:/opt/edgeai-gst-apps/apps_python#

There is an error in the log. If this is a problem of SDK?
And the yaml file is like this:

root@tda4vm-sk:/opt/edgeai-gst-apps/configs# cat object_detection.yaml
title: "Object Detection"
log_level: 2
inputs:
input0:
source: /dev/video-usb-cam0
format: jpeg
width: 1280
height: 720
framerate: 30
input1:
source: /opt/edgeai-test-data/videos/video0_1280_768.h264
format: h264
width: 1280
height: 768
framerate: 30
loop: True
input2:
source: /opt/edgeai-test-data/images/%04d.jpg
width: 1280
height: 720
index: 0
framerate: 1
loop: True
models:
model0:
model_path: /opt/model_zoo/TVM-OD-5120-ssdLite-mobDet-DSP-coco-320x320
viz_threshold: 0.6
model1:
model_path: /opt/model_zoo/TFL-OD-2020-ssdLite-mobDet-DSP-coco-320x320
viz_threshold: 0.6
model2:
model_path: /opt/model_zoo/ONR-OD-8200-yolox-nano-lite-mmdet-coco-416x416
viz_threshold: 0.6
outputs:
output0:
sink: kmssink
width: 1920
height: 1080
overlay-perf-type: graph
output1:
sink: /opt/edgeai-test-data/output/output_video0.mkv
width: 1920
height: 1080
output2:
sink: /opt/edgeai-test-data/output/output_image_%04d.jpg
width: 1920
height: 1080
output3:
sink: remote
width: 1920
height: 1080
port: 8081
host: 127.0.0.1
encoding: jpeg
overlay-perf-type: graph

flows:
flow0: [input1,model2,output0,[320,150,1280,720]]
root@tda4vm-sk:/opt/edgeai-gst-apps/configs#

Regards,
Makoto.

  • 0
    TI__Mastermind 19680 points

    Hello Makoto,

    Try running the following command for object detection:

    root@tda4vm-sk:/opt/edgeai-gst-apps# ./apps_python/app_edgeai.py ./configs/object_detection.yaml

    For more on running the out of box demos: https://software-dl.ti.com/jacinto7/esd/processor-sdk-linux-sk-tda4vm/09_02_00/exports/edgeai-docs/common/sample_apps.html#python-c-apps

    Thank you,

    Fabiana

  • 0 in reply to Fabiana Jaimes
    Prodigy 50 points

    Hi Fabiana,

    I've run that demo.
    I want to confirm that if the log when demo is running like below is a SDK problem or not?

    ---------------------------------log↓--------------------------------------
    [ERROR] Could not get allowed GstCaps of device
    4213.130218 s: VX_ZONE_ERROR:[vxGetStatus:1020] Reference is NULL
    ---------------------------------log↑--------------------------------------

    I am using this input

    --------------------------------object_detection.yaml↓-------------
    input1:
    source: /opt/edgeai-test-data/videos/video0_1280_768.h264
    format: h264
    width: 1280
    height: 768
    framerate: 30
    loop: True
    --------------------------------object_detection.yaml↑-------------

    Regards,
    Makoto.

  • 0 in reply to Makoto Nakamura
    TI__Mastermind 19680 points

    Hi Makoto,

    I have tested this on my end with the same configuration file and was able to run the demo with no issue. Do you have a display connected when running the application?

    Thank you,

    Fabiana

  • 0 in reply to Fabiana Jaimes
    Prodigy 50 points

    Dear Fabiana

    I didn't connect a display when running the application.

    Regards,
    Makoto.

  • 0 in reply to Makoto Nakamura
    TI__Mastermind 19680 points

    Hi Makoto,

    Could you try connecting to a display or changing the ouput0 to output1 in your flow like such:

    flow0: [input1,model2,output1,[320,150,1280,720]]

    Thank you,

    Fabiana

  • 0 in reply to Fabiana Jaimes
    Prodigy 50 points

    Dear Fabiana,
    I tried output1.

    But I got other errors when running.
    I attach the rtsp_src_example.yaml (as rtsp_src_example.yaml.txt)
    and the run.log

    What is going wrong?

    Thank you,

    Makoto

    Fullscreen rtsp_src_example.yaml.txt Download 
    title RTSP stream
log_level 2
inputs
    # httpsgist.github.comSantiago-vdk80c378a315722a1b813ae5da1661f890
    # Steps given in the above url can be used to create an rtsp src in a
    # linux machine
    input0
        source rtsp192.168.11.1118088livestream2 # rtsp stream url
        width 640
        height 480
        framerate 30
        loop False
models
    model0
        model_path optmodel_zooONR-CL-6360-regNetx-200mf
        topN 5
    model1
        model_path optmodel_zooTFL-OD-2020-ssdLite-mobDet-DSP-coco-320x320
        viz_threshold 0.6
    model2
        model_path optmodel_zooONR-SS-8610-deeplabv3lite-mobv2-ade20k32-512x512
        alpha 0.4
outputs
    output0
        sink kmssink
        width 1920
        height 1080
        overlay-perf-type graph
    output1
        sink optedgeai-test-dataoutputoutput_video.mkv
        width 640
        height 480
    output2
        sink optedgeai-test-dataoutputoutput_image_%04d.jpg
        width 640
        height 480
    output3
        sink remote
        width 1920
        height 1080
        port 8081
        host 127.0.0.1
        encoding jpeg
        overlay-perf-type graph

flows
    flow0 [input0,model0,output1]
    Fullscreen 3716.run.log Download 
    root@tda4vm-sk:/opt/edgeai-gst-apps# cd apps_python/
root@tda4vm-sk:/opt/edgeai-gst-apps/apps_python# python3 app_edgeai.py ../configs/rtsp_src_example.yaml 
libtidl_onnxrt_EP loaded 0x3b973700 
Final number of subgraphs created are : 1, - Offloaded Nodes - 103, Total Nodes - 103 
APP: Init ... !!!
MEM: Init ... !!!
MEM: Initialized DMA HEAP (fd=5) !!!
MEM: Init ... Done !!!
IPC: Init ... !!!
IPC: Init ... Done !!!
REMOTE_SERVICE: Init ... !!!
REMOTE_SERVICE: Init ... Done !!!
   408.833889 s: GTC Frequency = 200 MHz
APP: Init ... Done !!!
   408.837078 s:  VX_ZONE_INIT:Enabled
   408.837092 s:  VX_ZONE_ERROR:Enabled
   408.837101 s:  VX_ZONE_WARNING:Enabled
   408.839354 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-0 
   408.839459 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-1 
   408.839565 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-2 
   408.839663 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-3 
   408.839724 s:  VX_ZONE_INIT:[tivxInitLocal:136] Initialization Done !!!
   408.844267 s:  VX_ZONE_INIT:[tivxHostInitLocal:101] Initialization Done for HOST !!!
==========[INPUT PIPELINE(S)]==========


** (python3:1593): CRITICAL **: 01:25:07.934: gst_v4l2_buffer_pool_orphan: assertion 'bpool' failed
[PIPE-0]

rtspsrc location=rtsp://192.168.11.111:8088/live/stream2 latency=0 proxy-id=None proxy-pw=None ! rtph264depay ! h264parse ! v4l2h264dec capture-io-mode=5 ! tiovxmemalloc pool-size=12 ! capsfilter caps="video/x-raw, format=(string)NV12;" ! tiovxmultiscaler name=split_01
split_01. ! queue ! capsfilter caps="video/x-raw, width=(int)640, height=(int)480;" ! tiovxdlcolorconvert out-pool-size=4 ! capsfilter caps="video/x-raw, format=(string)RGB;" ! appsink max-buffers=2 drop=True name=sen_0
split_01. ! queue ! capsfilter caps="video/x-raw, width=(int)340, height=(int)256;" ! tiovxdlcolorconvert out-pool-size=4 ! capsfilter caps="video/x-raw, format=(string)RGB;" ! videobox qos=True left=58 right=58 top=16 bottom=16 ! tiovxdlpreproc out-pool-size=4 data-type=3 tensor-format=1 ! capsfilter caps="application/x-tensor-tiovx;" ! appsink max-buffers=2 drop=True name=pre_0


==========[OUTPUT PIPELINE]==========

appsrc do-timestamp=True format=3 block=True name=post_0 ! tiovxdlcolorconvert ! capsfilter caps="video/x-raw, format=(string)NV12, width=(int)640, height=(int)480;" ! v4l2h264enc extra-controls="controls, frame_level_rate_control_enable=(int)1, video_bitrate=(int)10000000, video_gop_size=(int)30;" ! h264parse ! matroskamux writing-app=GStreamer Matroska muxer ! filesink sync=False location=/opt/edgeai-test-data/output/output_video.mkv

[ERROR] Error pulling tensor from GST Pipeline
   414.923404 s:  VX_ZONE_INIT:[tivxHostDeInitLocal:115] De-Initialization Done for HOST !!!
   414.927951 s:  VX_ZONE_INIT:[tivxDeInitLocal:204] De-Initialization Done !!!
APP: Deinit ... !!!
REMOTE_SERVICE: Deinit ... !!!
REMOTE_SERVICE: Deinit ... Done !!!
IPC: Deinit ... !!!
IPC: DeInit ... Done !!!
MEM: Deinit ... !!!
DDR_SHARED_MEM: Alloc's: 54 alloc's of 22075056 bytes 
DDR_SHARED_MEM: Free's : 54 free's  of 22075056 bytes 
DDR_SHARED_MEM: Open's : 0 allocs  of 0 bytes 
MEM: Deinit ... Done !!!
APP: Deinit ... Done !!!

  • 0 in reply to Makoto Nakamura
    TI__Mastermind 19680 points

    Hi Makoto,

    Try running the configuration file below, only changing the input source (line 8) to your RTSP stream URL.

    title: "RTSP stream"
log_level: 2
inputs:
    # https://gist.github.com/Santiago-vdk/80c378a315722a1b813ae5da1661f890
    # Steps given in the above url can be used to create an rtsp src in a
    # linux machine
    input0:
        source: rtsp://10.24.51.126:8554/test # rtsp stream url
        width: 1280
        height: 720
        framerate: 30
        loop: True
models:
    model0:
        model_path: /opt/model_zoo/ONR-CL-6360-regNetx-200mf
        topN: 5
    model1:
        model_path: /opt/model_zoo/TFL-OD-2020-ssdLite-mobDet-DSP-coco-320x320
        viz_threshold: 0.6
    model2:
        model_path: /opt/model_zoo/ONR-SS-8610-deeplabv3lite-mobv2-ade20k32-512x512
        alpha: 0.4
outputs:
    output0:
        sink: kmssink
        width: 1920
        height: 1080
        overlay-perf-type: graph
    output1:
        sink: /opt/edgeai-test-data/output/output_video.mkv
        width: 1920
        height: 1080
    output2:
        sink: /opt/edgeai-test-data/output/output_image_%04d.jpg
        width: 1920
        height: 1080
    output3:
        sink: remote
        width: 1920
        height: 1080
        port: 8081
        host: 127.0.0.1
        encoding: jpeg
        overlay-perf-type: graph

flows:
    flow0: [input0,model0,output1,[320,150,1280,720]]

    Thank you,

    Fabiana

  • 0 in reply to Fabiana Jaimes
    Prodigy 50 points

    Dear Fabiana,

    I tried as your reply.
    I attached the log.

    However, my RTSP is 640x480.

    Fullscreen cmd2.txt Download 
    root@tda4vm-sk:/opt/edgeai-gst-apps/apps_python# cat ../configs/tmp.yaml
title: RTSP stream
log_level: 2
inputs:
    # https://gist.github.com/Santiago-vdk/80c378a315722a1b813ae5da1661f890
    # Steps given in the above url can be used to create an rtsp src in a
    # linux machine
    input0:
        source: rtsp://192.168.11.111:8088/live/stream2 # rtsp stream url
        width: 1280
        height: 720
        framerate: 30
        loop: True
models:
    model0:
        model_path: /opt/model_zoo/ONR-CL-6360-regNetx-200mf
        topN: 5
    model1:
        model_path: /opt/model_zoo/TFL-OD-2020-ssdLite-mobDet-DSP-coco-320x320
        viz_threshold: 0.6
    model2:
        model_path: /opt/model_zoo/ONR-SS-8610-deeplabv3lite-mobv2-ade20k32-512x512
        alpha: 0.4
outputs:
    output0:
        sink: kmssink
        width: 1920
        height: 1080
        overlay-perf-type: graph
    output1:
        sink: /opt/edgeai-test-data/output/output_video.mkv
        width: 1920
        height: 1080
    output2:
        sink: /opt/edgeai-test-data/output/output_image_%04d.jpg
        width: 1920
        height: 1080
    output3:
        sink: remote
        width: 1920
        height: 1080
        port: 8081
        host: 127.0.0.1
        encoding: jpeg
        overlay-perf-type: graph

flows:
    flow0: [input0,model0,output1,[320,150,1280,720]]
root@tda4vm-sk:/opt/edgeai-gst-apps/apps_python# python3 app_edgeai.py ../configs/tmp.yaml 
libtidl_onnxrt_EP loaded 0x228f28f0 
Final number of subgraphs created are : 1, - Offloaded Nodes - 103, Total Nodes - 103 
APP: Init ... !!!
MEM: Init ... !!!
MEM: Initialized DMA HEAP (fd=5) !!!
MEM: Init ... Done !!!
IPC: Init ... !!!
IPC: Init ... Done !!!
REMOTE_SERVICE: Init ... !!!
REMOTE_SERVICE: Init ... Done !!!
  8626.899167 s: GTC Frequency = 200 MHz
APP: Init ... Done !!!
  8626.899371 s:  VX_ZONE_INIT:Enabled
  8626.899416 s:  VX_ZONE_ERROR:Enabled
  8626.899455 s:  VX_ZONE_WARNING:Enabled
  8626.900268 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-0 
  8626.900505 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-1 
  8626.900655 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-2 
  8626.900790 s:  VX_ZONE_INIT:[tivxPlatformCreateTargetId:116] Added target MPU-3 
  8626.900841 s:  VX_ZONE_INIT:[tivxInitLocal:136] Initialization Done !!!
  8626.901277 s:  VX_ZONE_INIT:[tivxHostInitLocal:101] Initialization Done for HOST !!!
==========[INPUT PIPELINE(S)]==========

[ERROR] Error pulling tensor from GST Pipeline
[PIPE-0]

rtspsrc location=rtsp://192.168.11.111:8088/live/stream2 latency=0 proxy-id=None proxy-pw=None name=source0


==========[OUTPUT PIPELINE]==========

appsrc do-timestamp=True format=3 block=True name=post_0 ! tiovxdlcolorconvert ! capsfilter caps="video/x-raw, format=(string)NV12, width=(int)1280, height=(int)720;" ! queue ! mosaic_0.sink_0

tiovxmosaic target=1 background=/tmp/background_0 name=mosaic_0 src::pool-size=2
sink_0::startx="<320>" sink_0::starty="<150>" sink_0::widths="<1280>" sink_0::heights="<720>"
! capsfilter caps="video/x-raw, format=(string)NV12, width=(int)1920, height=(int)1080;" ! v4l2h264enc extra-controls="controls, frame_level_rate_control_enable=(int)1, video_bitrate=(int)10000000, video_gop_size=(int)30;" ! h264parse ! matroskamux writing-app=GStreamer Matroska muxer ! filesink sync=False location=/opt/edgeai-test-data/output/output_video.mkv

  8632.311488 s:  VX_ZONE_INIT:[tivxHostDeInitLocal:115] De-Initialization Done for HOST !!!
  8632.315985 s:  VX_ZONE_INIT:[tivxDeInitLocal:204] De-Initialization Done !!!
APP: Deinit ... !!!
REMOTE_SERVICE: Deinit ... !!!
REMOTE_SERVICE: Deinit ... Done !!!
IPC: Deinit ... !!!
IPC: DeInit ... Done !!!
MEM: Deinit ... !!!
DDR_SHARED_MEM: Alloc's: 24 alloc's of 53919024 bytes 
DDR_SHARED_MEM: Free's : 24 free's  of 53919024 bytes 
DDR_SHARED_MEM: Open's : 0 allocs  of 0 bytes 
MEM: Deinit ... Done !!!
APP: Deinit ... Done !!!

    Thank you,

    Makoto

  • 0 in reply to Makoto Nakamura
    TI__Mastermind 19680 points

    Hi Makoto,

    Responses will be delayed this week due to on-site training. Thank you for understanding.

    -Fabiana

  • 0 in reply to Fabiana Jaimes
    TI__Mastermind 19680 points

    Hi Makto,

    Could you try running the cpp application instead? Instructions on how to do so can be found here: https://software-dl.ti.com/jacinto7/esd/processor-sdk-linux-sk-tda4vm/09_02_00/exports/edgeai-docs/common/sample_apps.html#python-c-apps

    Thank you,

    Fabiana