mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-06-14 09:48:07 +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>
77 lines
1.7 KiB
Python
77 lines
1.7 KiB
Python
|
|
import sys
|
|
from pathlib import Path
|
|
repo_path = Path(__file__).absolute().parents[2]
|
|
sys.path.append(str(repo_path))
|
|
|
|
try:
|
|
import model_zoo.vit.vision_transformer_from_config
|
|
except ImportError:
|
|
raise ImportError("model_zoo is not found, please check your path")
|
|
|
|
BATCH_SIZE = 8
|
|
IMG_SIZE = 32
|
|
PATCH_SIZE = 4
|
|
DIM = 512
|
|
NUM_ATTENTION_HEADS = 8
|
|
SUMMA_DIM = 2
|
|
NUM_CLASSES = 10
|
|
DEPTH = 6
|
|
|
|
model_cfg = dict(
|
|
type='VisionTransformerFromConfig',
|
|
tensor_splitting_cfg=dict(
|
|
type='ViTInputSplitter2D',
|
|
),
|
|
embedding_cfg=dict(
|
|
type='ViTPatchEmbedding2D',
|
|
img_size=IMG_SIZE,
|
|
patch_size=PATCH_SIZE,
|
|
embed_dim=DIM,
|
|
),
|
|
token_fusion_cfg=dict(
|
|
type='ViTTokenFuser2D',
|
|
img_size=IMG_SIZE,
|
|
patch_size=PATCH_SIZE,
|
|
embed_dim=DIM,
|
|
drop_rate=0.1
|
|
),
|
|
norm_cfg=dict(
|
|
type='LayerNorm2D',
|
|
normalized_shape=DIM,
|
|
eps=1e-6,
|
|
),
|
|
block_cfg=dict(
|
|
type='ViTBlock',
|
|
attention_cfg=dict(
|
|
type='ViTSelfAttention2D',
|
|
hidden_size=DIM,
|
|
num_attention_heads=NUM_ATTENTION_HEADS,
|
|
attention_dropout_prob=0.,
|
|
hidden_dropout_prob=0.1,
|
|
),
|
|
droppath_cfg=dict(
|
|
type='VanillaViTDropPath',
|
|
),
|
|
mlp_cfg=dict(
|
|
type='ViTMLP2D',
|
|
in_features=DIM,
|
|
dropout_prob=0.1,
|
|
mlp_ratio=1
|
|
),
|
|
norm_cfg=dict(
|
|
type='LayerNorm2D',
|
|
normalized_shape=DIM,
|
|
eps=1e-6,
|
|
),
|
|
),
|
|
head_cfg=dict(
|
|
type='ViTHead2D',
|
|
hidden_size=DIM,
|
|
num_classes=NUM_CLASSES,
|
|
),
|
|
embed_dim=DIM,
|
|
depth=DEPTH,
|
|
drop_path_rate=0.,
|
|
)
|