Tappas Error: No tensor with name yolov5m_wo_spp_60p/yolov5_nms_postprocess

General
1

I installed Tappas from GitHub by running the setup_env.sh and install.sh scripts. However, I encountered an error when attempting to execute the detection.sh script located in the /tappas/apps/h8/gstreamer/raspberrypi/detection/ directory.

Since I have the Hailo8L, the earlier error indicated that the board was Hailo8L, but the model used was for Hailo8 and was not supported. To resolve this, I downloaded the yolov5m_wo_spp.hef model specifically for Hailo8L.

Error
Error1148×429 72.2 KB

File:

Running yolov5
gst-launch-1.0 filesrc location=/home/sandlogic/tappas/apps/h8/gstreamer/resources/mp4/detection.mp4 name=src_0 ! qtdemux ! h264parse ! avdec_h264 max_threads=2 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! videoscale n-threads=2 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! videoconvert n-threads=3 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! hailonet hef-path=/home/sandlogic/hailo-rpi5-examples/resources/yolov8s_h8l.hef batch-size=1 output-format-type=HAILO_FORMAT_TYPE_FLOAT32 nms-score-threshold=0.3 nms-iou-threshold=0.45 output-format-type=HAILO_FORMAT_TYPE_FLOAT32 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! hailofilter function-name=yolov5 so-path=/home/sandlogic/tappas/apps/h8/gstreamer/libs/post_processes/libyolo_hailortpp_post.so qos=false ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! hailooverlay ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! videoconvert n-threads=3 ! fpsdisplaysink video-sink=ximagesink name=hailo_display sync=false text-overlay=false
Setting pipeline to PAUSED ...
Pipeline is PREROLLING ...
Redistribute latency...
Redistribute latency...
Redistribute latency...
Redistribute latency...
terminate called after throwing an instance of 'std::invalid_argument'
  what():  No tensor with name yolov5m_wo_spp_60p/yolov5_nms_postprocess
./detection.sh: line 164:  3422 Aborted                 gst-launch-1.0 filesrc location=/home/sandlogic/tappas/apps/h8/gstreamer/resources/mp4/detection.mp4 name=src_0 ! qtdemux ! h264parse ! avdec_h264 max_threads=2 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! videoscale n-threads=2 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! videoconvert n-threads=3 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! hailonet hef-path=/home/sandlogic/hailo-rpi5-examples/resources/yolov8s_h8l.hef batch-size=1 output-format-type=HAILO_FORMAT_TYPE_FLOAT32 nms-score-threshold=0.3 nms-iou-threshold=0.45 output-format-type=HAILO_FORMAT_TYPE_FLOAT32 ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! hailofilter function-name=yolov5 so-path=/home/sandlogic/tappas/apps/h8/gstreamer/libs/post_processes/libyolo_hailortpp_post.so qos=false ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! hailooverlay ! queue max-size-buffers=5 max-size-bytes=0 max-size-time=0 ! videoconvert n-threads=3 ! fpsdisplaysink video-sink=ximagesink name=hailo_display sync=false text-overlay=false
2

Welcome to the Hailo Community!

The screenshot shows you are using a yolov8 model HEF file in the hailonet element but specify yolov5 in the hailofilter element.