Skip to content

[CodeCamp2023-543] Adapt new version of Config #2707

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: dev-1.x
Choose a base branch
from
Open

[CodeCamp2023-543] Adapt new version of Config #2707

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
116 changes: 64 additions & 52 deletions ...rv2/uniformerv2-base-p16-res224_clip-kinetics710-kinetics-k400-pre_16xb32-u8_mitv1-rgb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,28 @@
_base_ = ['../../_base_/default_runtime.py']
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.config import read_base

with read_base():
from ..._base_.default_runtime import *

from mmengine.dataset import DefaultSampler
from mmengine.optim import CosineAnnealingLR, LinearLR
from mmengine.runner import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim import AdamW

from mmaction.datasets import (CenterCrop, DecordDecode, DecordInit, Flip,
FormatShape, PackActionInputs,
PytorchVideoWrapper, RandomResizedCrop, Resize,
ThreeCrop, UniformSample, VideoDataset)
from mmaction.evaluation import AccMetric
from mmaction.models import (ActionDataPreprocessor, Recognizer3D,
TimeSformerHead, UniFormerHead, UniFormerV2)

# model settings
num_frames = 8
model = dict(
type='Recognizer3D',
type=Recognizer3D,
backbone=dict(
type='UniFormerV2',
type=UniFormerV2,
input_resolution=224,
patch_size=16,
width=768,
Expand All @@ -31,13 +48,13 @@
'https://download.openmmlab.com/mmaction/v1.0/recognition/uniformerv2/kinetics400/uniformerv2-base-p16-res224_clip-kinetics710-pre_u8_kinetics400-rgb_20221219-203d6aac.pth', # noqa: E501
prefix='backbone.')),
cls_head=dict(
type='TimeSformerHead',
type=TimeSformerHead,
dropout_ratio=0.5,
num_classes=339,
in_channels=768,
average_clips='prob'),
data_preprocessor=dict(
type='ActionDataPreprocessor',
type=ActionDataPreprocessor,
mean=[114.75, 114.75, 114.75],
std=[57.375, 57.375, 57.375],
format_shape='NCTHW'))
Expand All @@ -52,63 +69,56 @@

file_client_args = dict(io_backend='disk')
train_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(type='UniformSample', clip_len=num_frames, num_clips=1),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 256)),
dict(type=DecordInit, **file_client_args),
dict(type=UniformSample, clip_len=num_frames, num_clips=1),
dict(type=DecordDecode),
dict(type=Resize, scale=(-1, 256)),
dict(
type='PytorchVideoWrapper',
op='RandAugment',
magnitude=7,
num_layers=4),
dict(type='RandomResizedCrop'),
dict(type='Resize', scale=(224, 224), keep_ratio=False),
dict(type='Flip', flip_ratio=0.5),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
type=PytorchVideoWrapper, op='RandAugment', magnitude=7, num_layers=4),
dict(type=RandomResizedCrop),
dict(type=Resize, scale=(224, 224), keep_ratio=False),
dict(type=Flip, flip_ratio=0.5),
dict(type=FormatShape, input_format='NCTHW'),
dict(type=PackActionInputs)
]

val_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(
type='UniformSample', clip_len=num_frames, num_clips=1,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 224)),
dict(type='CenterCrop', crop_size=224),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
dict(type=DecordInit, **file_client_args),
dict(type=UniformSample, clip_len=num_frames, num_clips=1, test_mode=True),
dict(type=DecordDecode),
dict(type=Resize, scale=(-1, 224)),
dict(type=CenterCrop, crop_size=224),
dict(type=FormatShape, input_format='NCTHW'),
dict(type=PackActionInputs)
]

test_pipeline = [
dict(type='DecordInit', **file_client_args),
dict(
type='UniformSample', clip_len=num_frames, num_clips=4,
test_mode=True),
dict(type='DecordDecode'),
dict(type='Resize', scale=(-1, 224)),
dict(type='ThreeCrop', crop_size=224),
dict(type='FormatShape', input_format='NCTHW'),
dict(type='PackActionInputs')
dict(type=DecordInit, **file_client_args),
dict(type=UniformSample, clip_len=num_frames, num_clips=4, test_mode=True),
dict(type=DecordDecode),
dict(type=Resize, scale=(-1, 224)),
dict(type=ThreeCrop, crop_size=224),
dict(type=FormatShape, input_format='NCTHW'),
dict(type=PackActionInputs)
]

train_dataloader = dict(
batch_size=8,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
sampler=dict(type=DefaultSampler, shuffle=True),
dataset=dict(
type=dataset_type,
type=VideoDataset,
ann_file=ann_file_train,
data_prefix=dict(video=data_root),
pipeline=train_pipeline))
val_dataloader = dict(
batch_size=8,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
sampler=dict(type=DefaultSampler, shuffle=False),
dataset=dict(
type=dataset_type,
type=VideoDataset,
ann_file=ann_file_val,
data_prefix=dict(video=data_root_val),
pipeline=val_pipeline,
Expand All @@ -117,47 +127,49 @@
batch_size=8,
num_workers=8,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
sampler=dict(type=DefaultSampler, shuffle=False),
dataset=dict(
type=dataset_type,
type=VideoDataset,
ann_file=ann_file_test,
data_prefix=dict(video=data_root_val),
pipeline=test_pipeline,
test_mode=True))

val_evaluator = dict(type='AccMetric')
test_evaluator = dict(type='AccMetric')
val_evaluator = dict(type=AccMetric)
test_evaluator = dict(type=AccMetric)
train_cfg = dict(
type='EpochBasedTrainLoop', max_epochs=24, val_begin=1, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
type=EpochBasedTrainLoop, max_epochs=24, val_begin=1, val_interval=1)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)

base_lr = 2e-5
optim_wrapper = dict(
optimizer=dict(
type='AdamW', lr=base_lr, betas=(0.9, 0.999), weight_decay=0.05),
type=AdamW, lr=base_lr, betas=(0.9, 0.999), weight_decay=0.05),
paramwise_cfg=dict(norm_decay_mult=0.0, bias_decay_mult=0.0),
clip_grad=dict(max_norm=20, norm_type=2))

param_scheduler = [
dict(
type='LinearLR',
type=LinearLR,
start_factor=1 / 20,
by_epoch=True,
begin=0,
end=5,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
type=CosineAnnealingLR,
eta_min_ratio=1 / 20,
by_epoch=True,
begin=5,
end=24,
convert_to_iter_based=True)
]

default_hooks = dict(
checkpoint=dict(interval=3, max_keep_ckpts=5), logger=dict(interval=100))
default_hooks.update(
dict(
checkpoint=dict(interval=3, max_keep_ckpts=5),
logger=dict(interval=100)))

# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
Expand Down
Loading