training and validation

[basbaba]

I downloaded the source code and nuscene data(mini version, provided by the Author) as README.txt told, after training 1000 epochs:

1. if set data_size = 0.2, the val_loss.txt will always be around 35
2. if set data_size - 0.7 the val_loss.txt will always be around 20

whatever the value of data_size is, any input image will get an nonsense output. I tried several different images(from nuscene or mine) but the result images look similar. I have no ideal where is the problem.

So have anyone succeeded in training a model to get a good result?

[basbaba]

Update:

Now I'm moving to full nuscenes dataset instead of mini, the result looks better, the edges of generated area are sharpen and solid than mono-semeantic-maps. But the speed of training is touching: 200 epoch will cost 330 days with my nvidia T4. I'll try to improve it.