Nanyu

I have problem the same as you.

Could you provide more messages about the line number or somethings?

Try to print out the value of *imagestore.shape*.

### First at all, which platform are you using: #### For Windows install [ffmpeg](https://github.com/BtbN/FFmpeg-Builds/releases) to your system and add [the path of installed **ffmpeg** to system variable PATH](https://www.zerodollartips.com/install-ffmpeg-windows-10/#:~:text=%20Add%20FFmpeg%20to%20Windows%20Path%20using%20Environment,select%20the%20Path%20and%20click%20on...%20More%20) #### For...

---------------------------------------- Oct 29, 2021 10:36:07 wangrui12345678 ***@***.***>: > > *First at all, which platform are you using:* > > *For Windows* > > install ffmpeg[https://github.com/BtbN/FFmpeg-Builds/releases] to your system and add...

That is right, with a wrong result is normal behavior. The actual life view may differ from input photos, which mean the perspective angle, car size may different from one...

See https://github.com/OlafenwaMoses/Traffic-Net/issues/3#issue-548616623

---------------------------------------- Nov 26, 2021 19:32:32 Meinrad Recheis ***@***.***>: > Why don't you check numpy documentation? > > — > You are receiving this because you authored the thread. > Reply...

> I did google it for you (but hey man you really should learn to google yourself). `np.r_[sliced_a, sliced_b]` can probably be replaced by `np.concatenate((sliced_a, sliced_b), axis = 0) `...

---------------------------------------- Nov 27, 2021 19:35:44 Meinrad Recheis ***@***.***>: > Sorry, I forget not everyone has the same freedoms as I do in Austria. I have never heard of using a...