Timo-hab

Results 19 comments of Timo-hab

@fyu thank you for your answer. test_batch wasnt set to 0. Now i can start the training, but dont see test results of course. Is it possible to test the...

Not really. Have you tried it with caffe-segnet-cudnn5? https://github.com/TimoSaemann/caffe-segnet-cudnn5

Are you progressed? Could you successfully train and test SegNet on Cityscapes database?

Did you check: https://github.com/alexgkendall/caffe-segnet/issues/62 https://github.com/alexgkendall/caffe-segnet/issues/32

I was able to train it on a GTX980, 4GB. However, I had to change the batch size to 2. Unfortunately the results are not really well.

I must correct myself. The results are after 40,000 iterations quite well. Before that I only tested with 10,000 iterations.

I am surprising, that some have problems with 4 GB. I have only changed the batch size. Somewhere I read that cudnn version 2 is required. Actually I use version...

You have to change the padding in prototxt file with: upsample_w: upsample_h:

I could compile caffe-segnet using CUDA 8. You need to build it without CUDNN.