problem training on master

[YoannRandon]

After I install the last version of the code, I tried to run a training using the following cmd :
"python train.py --dataroot /home/shared/seg_sem_2 --checkpoints_dir /home/shared/checkpoint_model --name oktal2bdd --config_json /home/ubuntu/seg_sem.json --output_display_aim_server 127.0.0.1 --output_display_visdom_port 8501 --gpu_ids 0,1,2,3 --train_semantic_mask --data_relative_paths"
I encounter this problem :

My data is structure as the following :
-seg_sem_2 # name of dataset
-trainA # Synthetic Oktalse
-bbox # boundingbox png format
-imgs # images png format
-paths.txt # link imgs/bbox
-trainB # realistic BDD100K
-bbox # boundingbox png format
-imgs # images jpg format
-paths.txt

[YoannRandon]

furthermore, I don't understand why B domain is related to trainA when the config file I am using is AtoB direction

[pierrot-lc]

Hi,

This error could be due to your images being not found. From what you wrote, you should have a dataroot that follows this structure :

seg_sem_2/
├── trainA
│   ├── bbox
│   ├── imgs
│   └── paths.txt
└── trainB
    ├── bbox
    ├── imgs
    └── paths.txt

Since the error arises when you're trying to read images from domain B, it could be that your seg_seq_2/trainB/paths.txt file is wrong. It looks like it tries to search for images in the trainA/imgs directory, maybe paths are should point to the trainB/imgs directory ? (you should check if the files exists in this directory).

Hope this helps.

[YoannRandon]

yes i missed this. Thanks