edge-connect
edge-connect copied to clipboard
knazeri
Convergency of edge model
Hello @knazeri Thanks for your opening source code. I have used your implementation to train from scratch. I stay all your settings unchanged, but only use another remote sensing dataset, which contains only 800 training images with size 256x256.
At the beginning, I trained a edge model with "MODEL=1". It is observed that after 1000 epoches training, the edge model does learn something, but very slow and far from convergency.
The above images are the samples during training after 1 and 67000 iterations respectively. It shows that the edge model was learning throughout the whole training procedure, but could you tell me why does the estimated results so bad?
Beyond that, I have also trained a inpainting model alone with "MODEL=2", but I get a very different results from the results above, as I list below. It is clear that the inpainting model convergenced successfully, which proves the correctness of the training strategy. So Why I get a results above?
Looking for your replys.
Hello @knazeri Thanks for your opening source code. I have used your implementation to train from scratch. I stay all your settings unchanged, but only use another remote sensing dataset, which contains only 800 training images with size 256x256.
At the beginning, I trained a edge model with "MODEL=1". It is observed that after 1000 epoches training, the edge model does learn something, but very slow and far from convergency.
The above images are the samples during training after 1 and 67000 iterations respectively. It shows that the edge model was learning throughout the whole training procedure, but could you tell me why does the estimated results so bad?
Beyond that, I have also trained a inpainting model alone with "MODEL=2", but I get a very different results from the results above, as I list below. It is clear that the inpainting model convergenced successfully, which proves the correctness of the training strategy. So Why I get a results above?
Looking for your replys.
Hello @knazeri Thanks for your opening source code. I have used your implementation to train from scratch. I stay all your settings unchanged, but only use another remote sensing dataset, which contains only 800 training images with size 256x256.
At the beginning, I trained a edge model with "MODEL=1". It is observed that after 1000 epoches training, the edge model does learn something, but very slow and far from convergency.
The above images are the samples during training after 1 and 67000 iterations respectively. It shows that the edge model was learning throughout the whole training procedure, but could you tell me why does the estimated results so bad?
Beyond that, I have also trained a inpainting model alone with "MODEL=2", but I get a very different results from the results above, as I list below. It is clear that the inpainting model convergenced successfully, which proves the correctness of the training strategy. So Why I get a results above?
Looking for your replys.
Hello, I also encountered the same problem as you when training the edge model, the repaired edge is very bad. Have you solved the problem? If you solved the problem can you tell me how you did it? It means a lot to me. Thank you!
Hi, have you solved this problem yet?
Hello, I have been reproducing this code recently, and the edge repair results were poor when training MODEL=1. Have you solved the problem?
Hi, have you solved this problem yet?
Hello, I have been reproducing this code recently, and the edge repair results were poor when training MODEL=1. Have you solved the problem?
Hello, I also encountered this problem, did you solve it?