test.py error: unregonized arguments about deepsegmentor HOT 8 CLOSED

Thanks, @jonahduncan . I revised the codes and uploaded the repo again.

If you have any other problems, please let me know.

from deepsegmentor.

Hi, did you change anything in test_roadnet.sh? It seems that there was an unrecognized arguments 0, which I used for setting the gpu id. @jonahduncan

from deepsegmentor.

The only modification that I made was to change python3 to python as that's what points to the python version for my set-up.

from deepsegmentor.

Do you solve the problem? I close this issue first, if you still have problem, I can reopen it later.

from deepsegmentor.

@yhlleo I have not yet been able to solve this issue

from deepsegmentor.

If you revised GPU_IDS=$1 to something like GPU_IDS=0, you don't need to call the script in this way: sh ./scripts/test_roadnet.sh 0. In this case, please call sh ./scripts/test_roadnet.sh directly.

from deepsegmentor.

If you revised GPU_IDS=$1 to something like GPU_IDS=0, you don't need to call the script in this way: sh ./scripts/test_roadnet.sh 0. In this case, please call sh ./scripts/test_roadnet.sh directly.

I've tried this before and didn't have any success. I still get the same error. I get the error even if I remove the gpu_id argument when calling test.py and relying on the default. It appears to be related to the the use_augment argument, which isn't recognizing 0, which make sense when I look at the argument in base_options.py:

parser.add_argument('--use_augment', action='store_true', help='using data augmentation for training') #parser.add_argument('--use_augment', type=int, default=1, help='using data augmentation for training')

From my understanding of your code, this argument is used in both deepcrack_dataset.py and roadnet_dataset.py to apply affine transforms with if self.opt.use_augment: .... I assume that your intent is to set this to false. I was able to run test_roadnet.sh by removing --use augment 0 from the script, which I saw from the resulting options list sets it to False.

The only other thing I had to do was to modify pretrained_net_G.pth to be latest_net_G.pth

from deepsegmentor.

Hi @jonahduncan ,

I checked again, it's an error of the released codes. I revised the use_augment type from int to action (see details here). So, you're right to simply delete the line --use augment 0 from the script to keep the parameter value to false.

To test the pre-trained model, you're right to rename the file.

from deepsegmentor.