YOLOv5/YOLOv3 cannot find output tensor name: layer82-conv_dequant

[piotr-defendeye]

When trying to run sample_vi_od with yolov5 / yolov3 prepared according to:
https://milkv.io/docs/duo/application-development/tpu/tpu-yolov5
https://milkv.io/docs/duo/application-development/tdl-sdk/tdl-sdk-yolov5

This error happens. Can you provide YOLO models that work with sample_vi_od or any other way to detect/identify objects with yolo and stream over RTSP?

[root@milkv-duo]~# ./sample_vi_od yolov3 yolov3-tiny_int8_fuse.cvimodel
[SAMPLE_COMM_SNS_ParseIni]-1950: Parse /mnt/data/sensor_cfg.ini
[parse_source_devnum]-1605: devNum =  1
[parse_sensor_name]-1686: sensor =  GCORE_GC2083_MIPI_2M_30FPS_10BIT
[parse_sensor_busid]-1714: bus_id =  2
[parse_sensor_i2caddr]-1725: sns_i2c_addr =  37
[parse_sensor_mipidev]-1736: mipi_dev =  0
[parse_sensor_laneid]-1747: Lane_id =  1, 0, 2, -1, -1
[parse_sensor_pnswap]-1758: pn_swap =  0, 0, 0, 0, 0
MMF Version:7e0cc6a08-musl_riscv64
Create VBPool[0], size: (3110400 * 3) = 9331200 bytes
Create VBPool[1], size: (3110400 * 3) = 9331200 bytes
Create VBPool[2], size: (2359296 * 1) = 2359296 bytes
Total memory of VB pool: 21021696 bytes
Initialize SYS and VB
Initialize VI
ISP Vipipe(0) Allocate pa(0x8c70e000) va(0x0x3fc924d000) size(291120)
stSnsrMode.u16Width 1920 stSnsrMode.u16Height 1080 25.000000 wdrMode 0 pstSnsObj 0x3fca09f860
[SAMPLE_COMM_VI_StartMIPI]-483: sensor 0 stDevAttr.devno 0
awbInit ver 6.8@2021500
0 R:1400 B:3100 CT:2850
1 R:1500 B:2500 CT:3900
2 R:2300 B:1600 CT:6500
Golden 1024 1024 1024
WB Quadratic:0
isWdr:0
ViPipe:0,===GC2083 1080P 30fps 10bit LINE Init OK!===
********************************************************************************
cvi_bin_isp message
gerritId:      36403          commitId:      c69c5863e
md5:           cab880835a2ad5184de5ed7762404b84
sensorNum      1
sensorName0    2083

PQBIN message
gerritId:      80171          commitId:      5c9d8fc5d
md5:           ba5a510e093ad42db6788e6c2d13169e
sensorNum      3
sensorName0    2053

author:        wanqiang.he    desc:          思博慧CV1812H_GC2083_RGB_mode_V1.0.0
createTime:    2023-08-04 16:48:08version:       V1.1
tool Version:       v3.0.5.24           mode:
********************************************************************************
sensorName(0) mismatch, mwSns:2083 != pqBinSns:2053
[SAMPLE_COMM_ISP_Thread]-95: ISP Dev 0 running!
Initialize VPSS
---------VPSS[0]---------
Input size: (1920x1080)
Input format: (19)
VPSS physical device number: 1
Src Frame Rate: -1
Dst Frame Rate: -1
    --------CHN[0]-------
    Output size: (1920x1080)
    Depth: 1
    Do normalization: 0
        Src Frame Rate: -1
        Dst Frame Rate: -1
    ----------------------
    --------CHN[1]-------
    Output size: (1920x1080)
    Depth: 1
    Do normalization: 0
        Src Frame Rate: -1
        Dst Frame Rate: -1
    ----------------------
------------------------
Bind VI with VPSS Grp(0), Chn(0)
Attach VBPool(0) to VPSS Grp(0) Chn(0)
Attach VBPool(1) to VPSS Grp(0) Chn(1)
Initialize VENC
venc codec: h264
venc frame size: 1920x1080
Initialize RTSP
rtsp://169.254.115.188/h264
prio:0
version: 1.4.0
yolov3-tiny Build at 2024-04-24 21:21:09 For platform cv181x
Max SharedMem size:7782400
Enter TDL thread
Enter encoder thread
0 R:1165 B:3087 CT:2688
1 R:1464 B:2327 CT:3937
2 R:1974 B:1613 CT:7225
Golden 1464 1024 2327
wdrLEOnly:1
terminate called after throwing an instance of 'std::invalid_argument'
  what():  cannot find output tensor name: layer82-conv_dequant
Aborted