mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-05-31 11:25:27 +00:00
* Add gradient accumulation, fix lr scheduler * fix FP16 optimizer and adapted torch amp with tensor parallel (#18) * fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes * fixed trainer * Revert "fixed trainer" This reverts commit2e0b0b7699
. * improved consistency between trainer, engine and schedule (#23) Co-authored-by: 1SAA <c2h214748@gmail.com> * Split conv2d, class token, positional embedding in 2d, Fix random number in ddp Fix convergence in cifar10, Imagenet1000 * Integrate 1d tensor parallel in Colossal-AI (#39) * fixed 1D and 2D convergence (#38) * optimized 2D operations * fixed 1D ViT convergence problem * Feature/ddp (#49) * remove redundancy func in setup (#19) (#20) * use env to control the language of doc (#24) (#25) * Support TP-compatible Torch AMP and Update trainer API (#27) * Add gradient accumulation, fix lr scheduler * fix FP16 optimizer and adapted torch amp with tensor parallel (#18) * fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes * fixed trainer * Revert "fixed trainer" This reverts commit2e0b0b7699
. * improved consistency between trainer, engine and schedule (#23) Co-authored-by: 1SAA <c2h214748@gmail.com> Co-authored-by: 1SAA <c2h214748@gmail.com> Co-authored-by: ver217 <lhx0217@gmail.com> * add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29) * add explanation for ViT example (#35) (#36) * support torch ddp * fix loss accumulation * add log for ddp * change seed * modify timing hook Co-authored-by: Frank Lee <somerlee.9@gmail.com> Co-authored-by: 1SAA <c2h214748@gmail.com> Co-authored-by: binmakeswell <binmakeswell@gmail.com> * Feature/pipeline (#40) * remove redundancy func in setup (#19) (#20) * use env to control the language of doc (#24) (#25) * Support TP-compatible Torch AMP and Update trainer API (#27) * Add gradient accumulation, fix lr scheduler * fix FP16 optimizer and adapted torch amp with tensor parallel (#18) * fixed bugs in compatibility between torch amp and tensor parallel and performed some minor fixes * fixed trainer * Revert "fixed trainer" This reverts commit2e0b0b7699
. * improved consistency between trainer, engine and schedule (#23) Co-authored-by: 1SAA <c2h214748@gmail.com> Co-authored-by: 1SAA <c2h214748@gmail.com> Co-authored-by: ver217 <lhx0217@gmail.com> * add an example of ViT-B/16 and remove w_norm clipping in LAMB (#29) * add explanation for ViT example (#35) (#36) * optimize communication of pipeline parallel * fix grad clip for pipeline Co-authored-by: Frank Lee <somerlee.9@gmail.com> Co-authored-by: 1SAA <c2h214748@gmail.com> Co-authored-by: binmakeswell <binmakeswell@gmail.com> * optimized 3d layer to fix slow computation ; tested imagenet performance with 3d; reworked lr_scheduler config definition; fixed launch args; fixed some printing issues; simplified apis of 3d layers (#51) * Update 2.5d layer code to get a similar accuracy on imagenet-1k dataset * update api for better usability (#58) update api for better usability Co-authored-by: 1SAA <c2h214748@gmail.com> Co-authored-by: ver217 <lhx0217@gmail.com> Co-authored-by: puck_WCR <46049915+WANG-CR@users.noreply.github.com> Co-authored-by: binmakeswell <binmakeswell@gmail.com> Co-authored-by: アマデウス <kurisusnowdeng@users.noreply.github.com> Co-authored-by: BoxiangW <45734921+BoxiangW@users.noreply.github.com>
55 lines
1.3 KiB
Python
55 lines
1.3 KiB
Python
#!/usr/bin/env python
|
|
# -*- encoding: utf-8 -*-
|
|
|
|
import os
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from torchvision import transforms
|
|
from torch.utils.data import DataLoader
|
|
|
|
from colossalai.builder import build_dataset, build_transform
|
|
from colossalai.context import Config
|
|
|
|
TRAIN_DATA = dict(
|
|
dataset=dict(
|
|
type='CIFAR10',
|
|
root=Path(os.environ['DATA']),
|
|
train=True,
|
|
download=True
|
|
),
|
|
dataloader=dict(batch_size=4, shuffle=True, num_workers=2),
|
|
transform_pipeline=[
|
|
dict(type='ToTensor'),
|
|
dict(type='Normalize',
|
|
mean=(0.5, 0.5, 0.5),
|
|
std=(0.5, 0.5, 0.5)
|
|
)
|
|
]
|
|
)
|
|
|
|
|
|
@pytest.mark.cpu
|
|
def test_cifar10_dataset():
|
|
config = Config(TRAIN_DATA)
|
|
dataset_cfg = config.dataset
|
|
dataloader_cfg = config.dataloader
|
|
transform_cfg = config.transform_pipeline
|
|
|
|
# build transform
|
|
transform_pipeline = [build_transform(cfg) for cfg in transform_cfg]
|
|
transform_pipeline = transforms.Compose(transform_pipeline)
|
|
dataset_cfg['transform'] = transform_pipeline
|
|
|
|
# build dataset
|
|
dataset = build_dataset(dataset_cfg)
|
|
|
|
# build dataloader
|
|
dataloader = DataLoader(dataset=dataset, **dataloader_cfg)
|
|
data_iter = iter(dataloader)
|
|
img, label = data_iter.next()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
test_cifar10_dataset()
|