Migrations
/
pytorch-image-models
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '7419e9835f'
${ noResults }
pytorch-image-models/data/__init__.py

7 lines
228 B
Raw Normal View History Unescape

Some transform/data/loader refactoring, hopefully didn't break things * factor out data related constants to own file * move data related config helpers to own file * add a variant of RandomResizeCrop that randomizes interpolation method * remove old Numpy version of RandomErasing * cleanup torch version of RandomErasing and use it in either GPU loader batch mode or single image cpu Transform
5 years ago
from data.constants import *
from data.config import resolve_data_config
Add some Nvidia performance enhancements (prefetch loader, fast collate), and refactor some of training and model fact/transforms
5 years ago
from data.dataset import Dataset
Uniform pretrained model handling. * All models have 'default_cfgs' dict * load/resume/pretrained helpers factored out * pretrained load operates on state_dict based on default_cfg * test all models in validate * schedule, optim factor factored out * test time pool wrapper applied based on default_cfg
5 years ago
from data.transforms import *
from data.loader import create_loader
Mixup and prefetcher improvements * Do mixup in custom collate fn if prefetcher enabled, reduces performance impact * Move mixup code to own file * Add arg to disable prefetcher * Fix no cuda transfer when prefetcher off * Random erasing when prefetcher off wasn't changed to match new args, fixed * Default random erasing to off (prob = 0.) for train
5 years ago
from data.mixup import mixup_target, FastCollateMixup