IP Cam Talk Custom Community DeepStack Model

Below are some samples of the images from the original dark model

Person
View attachment 128602

Car
View attachment 128603
Really helpful to see what the original sample images look like. Personally, I'd like to see more bias toward B/W (IR lit) images, but obviously it needs to have both. Are you aiming for a smaller image set this time around? I presume that would help out those of us whose systems struggle a bit with the current dark.pt when running it on a CPU only Deepstack setup.
 
I started training the new dark model. I tried to train it local with my RTX 3060 Ti but I could not get it to work. I think I broken it when I was make DeepStackALPR. So i figured I will give Google Colab a try and train the model on their servers, sofar looks to be going well. I should have the model finished sometime late tomorrow or early the next day.

1653273648208.png
 
Last edited:
Training still going, it should be done in about 16 hours. The training crashed when I was getting ready to go to sleep using the free version of Colab and would not let me restart the training so I bought a one month subscription to Colab Pro, the cost was only $9.99.

With the new model the accuracy should be better than the original dark models and as fast as my other models

1653308216862.png
 
I just uploaded the new dark model in the first post. This new dark model is faster and better object detection then the original dark model also uses less memory, enjoy.
Let me know how the model works.

 
Last edited:
I just uploaded the new dark model in the first post. This new dark model is faster and better object detection then the original dark model also uses less memory, enjoy.
Let me know how the model works.


It's looking good so far on the cams I loaded it one even in this short of time. It appears fast and highly accurate. You have once again outdone yourself!

Thanks, Mike!
 
Thanks yet again Mike! I'll load this and see what happens tonight.
 
  • Like
Reactions: looney2ns
If you are using combined all you need is (objects:0,combined) for daytime and (objects:0,dark,combined) for nightime all of the new animals are in the combined model. In the next several days I am going to add the dark images to the new models so the new models will not need dark any more.
So, if you are using combined, there is no reason to specifically use animal? Or am I misunderstanding (highly likely!)
 
One note for the new dark model I did change some of the labels

Labels:
Bicycle, Bus, Car, Cat, Dog, Motorcycle, & Person

Thank you for this change. That is the one thing that drove me crazy when using the original dark model. I like the "person" or "Person" to differentiate the two running models.
 
  • Like
Reactions: 105437
Next I am going to try making a new General Model V2.0. This model I will merge the general images with the dark images and make one model that would only have one label for each item. So no more person & Person. Also I am going to add cat & dog to the model. This model might take days to train because there are 10x more images than when I trained the dark model and this took about 24 hours to train

Labels for General V2.0:
bicycle, bus, car, cat, dog, motorcycle, person, truck
 
Last edited: