Configuration for training baidu_V2 about ext_portrait_segmentation

[HYOJINPARK]

In my case,

self.data_dir
└── Nukki
    └── baidu_V1
         ├── input
         ├── target
         ├── train.txt
         └── val.txt
   └── baidu_V2
         ├── input
         ├── target
         ├── train.txt
         └── val.txt
└── Portrait

this_additional is " '/Nukki/baidu_V1/'"

And code call additional dataset by
img_file = ((self.data_dir).strip() + this_additoinal+'input/' + line.strip())
label_file = ((self.data_dir).strip() + this_additoinal+'target/' + line.strip())

Finally
self.data_dir/Nukki/baidu_V1/input/ and self.data_dir/Nukki/baidu_V1/target/

The train.txt is also
self.data_dir/Nukki/baidu_V1/train.txt

Could you tell me your definition of additional_data variable???

@HYOJINPARK

I only want to train baidu_V1 & baidu_V2, so from loadData.py I comment-out from line 57 to line 112.
see loadData.py.zip

SINet.json

"data_dir": "./dataset/",

Dataset folder tree

home@home-desktop:~/p10/ext_portrait_segmentation/dataset$ tree -L 3
.
├── Nukki
│   ├── baidu_V1
│   │   ├── input
│   │   ├── target
│   │   ├── train.txt
│   │   └── val.txt
│   └── baidu_V2
│       ├── input
│       ├── target
│       ├── train.txt
│       └── val.txt
└── Portrait

dataloader.py

additional_data = []

Now I am getting error:
see full log
log.txt

Traceback (most recent call last):
  File "main.py", line 251, in <module>
    lossVal, ElossVal, mIOU_val = val_edge(num_gpu, valLoader, model, criteria, Lovasz)
  File "/home/home/p10/ext_portrait_segmentation/etc/help_function.py", line 25, in val_edge
    rand_pick = np.random.randint(0, len(val_loader))
  File "mtrand.pyx", line 992, in mtrand.RandomState.randint
ValueError: Range cannot be empty (low >= high) unless no samples are taken

[HYOJINPARK]

I am sorry for late answer for you.
These days, I leave from my home country for an internship in another country with a long trip.
Still, I need time more to set new experiment environment.
I will check your code this week.
Thanks for your waiting.

I understand, wishing you all the best.

[HYOJINPARK]

I think your problem of "rand_pick = np.random.randint(0, len(val_loader))" is that
you don't use any validation dataset.
if you comment-out everything.

If you want to train with Baidu dataset
please just remove this 2 lines in loadData.py line 89, 90

self.trainImList.append(img_file)
self.trainAnnotList.append(label_file)

You can get this result

 Load public Baidu train dataset
This num of data is 10160
 Load public val dataset
This num of data is 270

Originally,

 Load public Baidu train dataset
This num of data is 11469
 Load public val dataset
This num of data is 270

This means that you train with only Baidu dataset and validate with EG1800 validation set