Zhijie Wang
Zhijie Wang
Hi, Could you share your training settings in detail? To reproduce the result in pascal voc leader board, you need to follow these steps: 1. Pretrain on COCO 2. Train...
OK, I see, the pretrained weights provided in this report is for validation set, not for test set, you need use different training methods if you want to get better...
@ymli39 Could you give more details about your training settings? Like data set split, batch size, input size, crop size and inference strategy (flip or multi scale etc.)?
@ymli39 You training steps are incomplete, as I said, the whole training process to reproduce the best performance on test set including 3 stages: 1. Train the model on coco....
@tyeah not yet, I still can not get a reasonable performance of pspnet, beside the network structure, there are some other ticks in pspnet which make it hard to train...
@rohitgajawada make sure your pytorch version == 0.2.0
@andreasrobinson @lzj322 Have you fix this problems? I also met the same problem
I find it! This error is caused by some training data, maybe there are some error when preprocess data, so I just delete them and my training code can run....
I can train the network after delete training data I mentioned above, but there are still some errors in validate process, so I just give it up and use caffe...
Hi, @luhc15 , I'm also trying to use these codes in voc dataset, could you please share your test codes? Thanks a lot!