Not able to get demonstrated output

[wowgic]

Hi Bhadresh,

Using the "detector.py" for inference only with same image files as yours, I could not able to get the desired out like yours. I get below error message. It works only if the class file has one class name. But out is not desired. Please help

ValueError: Dimension 0 in both shapes must be equal, but are 1 and 18. Shapes are [1,1,1024,30] and [18,1024,1,1]. for 'Assign_360' (op: 'Assign') with input shapes: [1,1,1024,30], [18,1024,1,1].
Detected Cat Faces in 14.0 seconds

[bhadreshpsavani]

Hi @wowgic ,
I am able to reproduce it, I will work on it this week and try to fix it.
Thanks for letting me know

[bhadreshpsavani]

Hi @wowgic
I have fixed the issue,
Let me know if it still persists

[wowgic]

Great.Thanks bhadresh for the update .

…

On Sat, Aug 8, 2020, 2:08 PM Bhadresh Savani ***@***.***> wrote: Closed #6 <#6>. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#6 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AMX4OAOX2NVXPH73D25MTLTR7UFHFANCNFSM4OXFMP4A> .

[b0unc3]

Hi,

I'm getting the same error as reported before.

ValueError: Dimension 0 in both shapes must be equal, but are 1 and 18. Shapes are [1,1,1024,30] and [18,1024,1,1]. for 'Assign_360' (op: 'Assign') with input shapes: [1,1,1024,30], [18,1024,1,1].

Any hint on how to fix this?
Thanks.

[bhadreshpsavani]

Hi @b0unc3,
The issue has been fixed! It was coming because pre-trained model weights were not available in the Github repository due to size limit.
Model weights are downloadable using the download script.
The weights can be also downloaded directly from this drive link.
Please let me know if it works for you.