thuangb
thuangb
Hi, how can we add class name above the bounding box for visualization ? Because tracking the color of the class hurts my eyes so much 😂
Just change ImageDataManager to VideoDataManager. And you have to prepare the dataset yourseld also
The easy answer is always using better GPU 🤣. However, you can try to splits the data to smaller subsets and test one by one
HI @akanimax, can you check this PR. I think this PR is more correct than #35
As answered in #40, the D loss should be near zero. What matter most in training GAN is not the loss but the visual quality, if you see it is...
This is not a bug, the loss used in the paper is Hinge GAN loss, which can have negative values for g_loss. If trained stably and correctly, the loss won't...
memory issues, try better GPU and CPU
Sorry I send wrong file, this is the correct one [yolor_tiny.txt](https://github.com/WongKinYiu/yolor/files/7559713/yolor_tiny.txt)
> @thuangb @thunanguyen Tried running your yolor_tiny cfg file on my custom dataset- after changing number of classes and filters. > > classes - line 247 & 304 filters -...
I also tried all existing gumbel quantizer but they all perform worse than normal quantizer. But I've recently notice from OpenAI's code for DALL-E, the encoder outputs the probability and...