Dataset folder format for PASACAL VOC dataset

[mprabhakarece]

Hi, I have downloaded VOCtrainval_11-May-2012 dataset. Is there any pre-process for above data to run code available in this repo. What is the folder format should be provided. Available code is only for training or can do inference also. I am a C++ guy. Not aware of python coding. Kindly do help.

Thank You.

[mprabhakarece]

i am getting below error with given command below

python3 train.py data=data/VOCdevkit/VOC2012 --dataset=voc --model-dir=models --batch-size=4 --epochs=30 download=True pytorch-segmentation/datasets/init.py usage: train.py [-h] [--dataset DATASET] [-a ARCH] [--classes C] [--aux-loss] [--resolution N] [--width X] [--height Y] [--device DEVICE] [-b BATCH_SIZE] [--epochs N] [-j N] [--lr LR] [--momentum M] [--wd W] [--print-freq PRINT_FREQ] [--model-dir MODEL_DIR] [--resume RESUME] [--test-only] [--pretrained] [--world-size WORLD_SIZE] [--dist-url DIST_URL] DIR train.py: error: unrecognized arguments: download=True I want get clarified whether it is possible to train without pre-trained weight or it is mandatory. else we can start fresh also? Also kindly provide link to download pre-trained weight need to be downloaded for segmentation.

Note I didn't do any changes or pre-process to the downloaded datasets