Unable to reproduce results about dexined

[xavysp]

Hi, according to the images the model is not training, it's strange. Your result looks like they are just in the first two epochs. When we train with BIPED, we augment the data 200 by 280. This mean that in one epoch you used 56000 images. If you just used 1000 images this means that your 40 epochs used just 40000 images.

[Rong-Tao]

Ok, my original Image is 1024*768, I will do random cropping and run it for 56*20 epochs, which should be equivalent to your 20 epochs. I've uploaded the code to the server I will let you know once I get the results

[Rong-Tao]

This is my tensorboard result, I will just cancel the training since it plateaued for 2 hours right now(I do added a lr.scheduler) . And the provided images are very similar to the images provided last time

[xavysp]

Ok, my original Image is 1024*768, I will do random cropping and run it for 56*20 epochs, which should be equivalent to your 20 epochs. I've uploaded the code to the server I will let you know once I get the results

I think you need to use the augmentation methods of BIPED, check the BIPED repo and let me know. Maybe we can have a chat by zoom, I'm interested how ends your proyect.

[xavysp]

This is my tensorboard result, I will just cancel the training since it plateaued for 2 hours right now(I do added a lr.scheduler) . And the provided images are very similar to the images provided last time

Can you tell me which kind of machine are you using for training? With dexined 2 hours is a short time.

[Rong-Tao]

Hey, I am using GPU equivalent to Nvidia V100 with 16GB Vram but it is neither Nvidia nor Amd. I will check the augmentation some time. I would be happy to have a zoom call some day with you once the new computation result is out. I guess you are in Spain? so we can probably do around 18:00 Beijing Time, basically +7 for EU time zone.

[xavysp]

Hey, I am using GPU equivalent to Nvidia V100 with 16GB Vram but it is neither Nvidia nor Amd. I will check the augmentation some time. I would be happy to have a zoom call some day with you once the new computation result is out. I guess you are in Spain? so we can probably do around 18:00 Beijing Time, basically +7 for EU time zone.

Ok, let me know when you get the result. Actually, I'm in Ecuador, You may write me by my email in the github profile.

Have a good day.