pip install -U cloths_segmentation
Jupyter notebook with the example:
https://clothssegmentation.herokuapp.com/
Download the dataset from https://www.kaggle.com/c/imaterialist-fashion-2019-FGVC6
Process the data using script
The script will create process the data and store images to folder images and binary masks to folder labels.
Example at cloths_segmentation/configs
You can enable / disable datasets that are used for training and validation.
Example:
export IMAGE_PATH=<path to the the folder with images>Example:
export MASK_PATH=<path to the folder with masks>python -m cloths_segmentation.train -c <path to config>
python -m torch.distributed.launch --nproc_per_node=<num_gpu> cloths_segmentation/inference.py \
-i <path to images> \
-c <path to config> \
-w <path to weights> \
-o <output-path> \
--fp16