NPU documentation and tools

VIM3
61

thank you …

62

thanks…

63

(venv) root@Khadas:/npu/darknet# pip3 install opencv-python
ERROR: Could not find a version that satisfies the requirement opencv-python (from versions: none)
ERROR: No matching distribution found for opencv-python

64

@RichardG

You can try this:

$ sudo apt-get update
$ sudo apt-get install opencv3
66

Just finished our first test of the VIM3’s NPU! @Frank did most of the heavy lifting. I just videoed everything with my iPhone.

7 Likes
68

Can we download this demo?

69

@RichardG yes you can, refer to the instructions inside the video. The part where Frank goes to this forum to download it: NPU Demo and source code

70

thanks …

1 Like
71

@blitzfr1
Hello , I have push a yolo tiny model to my gitlab . You can clone it .


the source code I have push to my gitlab too.

It should be noted that this is a fairly primitive model. I haven’t optimized the parameters yet, so the recognition effect is not very good,FPS is between 40 and 45, I will do more optimization later. This is just for users to try

72

Hi all,
I’m looking for a guideline on how to create a dataset.txt file which contains my 200 sample image filenames. This dataset.txt file is supposed to be input of option --source-file of the Acuity ‘tensorzonex’ quantization tool.
Thank in advance

73

@thanhhc just need to add you image file path to dataset.txt . Only one path per line.

1 Like
74

Thank for your reply

75

Is 40-45 FPS with a 1080p stream…?

76

@Archangel1235 Which one model ? yolo_v3 can’t . just yolo_tiny can be 40 to 45 fps

77

@Frank Thanks,

What’s the inference time for Yolo_v3 and yolo_tiny…?

78

@Archangel1235 I don’t test it . You can try

79

In my case, Yolov3-608x608 200ms and yolov3-tiny-416x416 10ms spend in vsi_nn_runGraph.

2 Likes
80

@khs971 Thanks for the reply!!

81

Hi Khadas Team,
I recently encountered a strange problem when running my NPU converted model. This mode was running fine for our several testing. we then moved on to a different OS version (on different SD card) and came back to the original sd card last days. We then ran our NPU model testing code again and got this error (which has never happened before we changed to another sd card of another OS)
Verify…
E [vnn_VerifyGraph:85]CHECK STATUS 85
E [main:218]CHECK STATUS 218

The error didn’t tell us much detail about what’s going on. Is there any advise on how to debug this issue?
Thank in advance
Thannh

82

@thanhhc In the process of switching the system, what changes have been made to the converted code ?

This tool is not open source tools, and we don’t know what these status information represents… I’m sorry for that .