pytorch semseg
1.0.0
Этот репозиторий направлен на отражение популярных архитектур семантической сегментации в Pytorch.
pip install -r requirements.txt
config.yamlНастройка файла конфигурации
# Model Configuration
model :
arch : <name> [options: 'fcn[8,16,32]s, unet, segnet, pspnet, icnet, icnetBN, linknet, frrn[A,B]'
<model_keyarg_1>:<value>
# Data Configuration
data :
dataset : <name> [options: 'pascal, camvid, ade20k, mit_sceneparsing_benchmark, cityscapes, nyuv2, sunrgbd, vistas']
train_split : <split_to_train_on>
val_split : <spit_to_validate_on>
img_rows : 512
img_cols : 1024
path : <path/to/data>
<dataset_keyarg1>:<value>
# Training Configuration
training :
n_workers : 64
train_iters : 35000
batch_size : 16
val_interval : 500
print_interval : 25
loss :
name : <loss_type> [options: 'cross_entropy, bootstrapped_cross_entropy, multi_scale_crossentropy']
<loss_keyarg1>:<value>
# Optmizer Configuration
optimizer :
name : <optimizer_name> [options: 'sgd, adam, adamax, asgd, adadelta, adagrad, rmsprop']
lr : 1.0e-3
<optimizer_keyarg1>:<value>
# Warmup LR Configuration
warmup_iters : <iters for lr warmup>
mode : <'constant' or 'linear' for warmup'>
gamma : <gamma for warm up>
# Augmentations Configuration
augmentations :
gamma : x # [gamma varied in 1 to 1+x]
hue : x # [hue varied in -x to x]
brightness : x # [brightness varied in 1-x to 1+x]
saturation : x # [saturation varied in 1-x to 1+x]
contrast : x # [contrast varied in 1-x to 1+x]
rcrop : [h, w] # [crop of size (h,w)]
translate : [dh, dw] # [reflective translation by (dh, dw)]
rotate : d # [rotate -d to d degrees]
scale : [h,w] # [scale to size (h,w)]
ccrop : [h,w] # [center crop of (h,w)]
hflip : p # [flip horizontally with chance p]
vflip : p # [flip vertically with chance p]
# LR Schedule Configuration
lr_schedule :
name : <schedule_type> [options: 'constant_lr, poly_lr, multi_step, cosine_annealing, exp_lr']
<scheduler_keyarg1>:<value>
# Resume from checkpoint
resume : <path_to_checkpoint>Чтобы тренировать модель:
python train.py [-h] [--config [CONFIG]]
--config Configuration file to use
Чтобы подтвердить модель:
usage: validate.py [-h] [--config [CONFIG]] [--model_path [MODEL_PATH]]
[--eval_flip] [--measure_time]
--config Config file to be used
--model_path Path to the saved model
--eval_flip Enable evaluation with flipped image | True by default
--measure_time Enable evaluation with time (fps) measurement | True
by default
Чтобы проверить модель набора данных на пользовательских изображениях:
python test.py [-h] [--model_path [MODEL_PATH]] [--dataset [DATASET]]
[--dcrf [DCRF]] [--img_path [IMG_PATH]] [--out_path [OUT_PATH]]
--model_path Path to the saved model
--dataset Dataset to use ['pascal, camvid, ade20k etc']
--dcrf Enable DenseCRF based post-processing
--img_path Path of the input image
--out_path Path of the output segmap
Если вы найдете этот код полезным в своем исследовании, пожалуйста, рассмотрите возможность цитировать:
@article{mshahsemseg,
Author = {Meet P Shah},
Title = {Semantic Segmentation Architectures Implemented in PyTorch.},
Journal = {https://github.com/meetshah1995/pytorch-semseg},
Year = {2017}
}