Skip to content

GitLab

"plugins/vscode:/vscode.git/clone" did not exist on "8eb6850dba9fb13c8fee94524318f134c9b298af"
Commit 5c10a883 authored by sunxx1's avatar sunxx1
Browse files

Merge branch 'sun_22.10' into 'main' 

Sun 22.10

See merge request dcutoolkit/deeplearing/dlexamples_new!51
parents 267b2e4a dcd2aabd
Hide whitespace changes
Inline Side-by-side
Showing with 1000 additions and 0 deletions
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b3_8xb32_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b3.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=300,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=300,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b4_8xb32-01norm_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b4.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=380,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=380,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b4_8xb32_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b4.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=380,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=380,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b5_8xb32-01norm_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b5.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=456,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=456,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b5_8xb32_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b5.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=456,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=456,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b6_8xb32-01norm_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b6.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=528,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=528,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b6_8xb32_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b6.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=528,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=528,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b7_8xb32-01norm_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b7.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=600,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=600,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b7_8xb32_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b7.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=600,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=600,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b8_8xb32-01norm_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b8.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=672,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=672,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-b8_8xb32_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_b8.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=672,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=672,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-em_8xb32-01norm_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_em.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=240,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=240,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/efficientnet-es_8xb32-01norm_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/efficientnet_es.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py',
'../_base_/default_runtime.py',
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
mean=[127.5, 127.5, 127.5], std=[127.5, 127.5, 127.5], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomResizedCrop',
size=224,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='ToTensor', keys=['gt_label']),
dict(type='Collect', keys=['img', 'gt_label'])
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='CenterCrop',
crop_size=224,
efficientnet_style=True,
interpolation='bicubic'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
train=dict(pipeline=train_pipeline),
val=dict(pipeline=test_pipeline),
test=dict(pipeline=test_pipeline))
openmmlab_test/mmclassification-0.24.1/configs/efficientnet/metafile.yml 0 → 100644
View file @ 5c10a883
Collections:
- Name: EfficientNet
Metadata:
Training Data: ImageNet-1k
Architecture:
- 1x1 Convolution
- Average Pooling
- Convolution
- Dense Connections
- Dropout
- Inverted Residual Block
- RMSProp
- Squeeze-and-Excitation Block
- Swish
Paper:
URL: https://arxiv.org/abs/1905.11946v5
Title: "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks"
README: configs/efficientnet/README.md
Code:
Version: v0.20.1
URL: https://github.com/open-mmlab/mmclassification/blob/v0.20.1/mmcls/models/backbones/efficientnet.py
Models:
- Name: efficientnet-b0_3rdparty_8xb32_in1k
Metadata:
FLOPs: 16481180
Parameters: 5288548
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 76.74
Top 5 Accuracy: 93.17
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b0_3rdparty_8xb32_in1k_20220119-a7e2a0b1.pth
Config: configs/efficientnet/efficientnet-b0_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckpts/efficientnet-b0.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b0_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 16481180
Parameters: 5288548
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 77.26
Top 5 Accuracy: 93.41
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b0_3rdparty_8xb32-aa_in1k_20220119-8d939117.pth
Config: configs/efficientnet/efficientnet-b0_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b0.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b0_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 16481180
Parameters: 5288548
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 77.53
Top 5 Accuracy: 93.61
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b0_3rdparty_8xb32-aa-advprop_in1k_20220119-26434485.pth
Config: configs/efficientnet/efficientnet-b0_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b0.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b1_3rdparty_8xb32_in1k
Metadata:
FLOPs: 27052224
Parameters: 7794184
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 78.68
Top 5 Accuracy: 94.28
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b1_3rdparty_8xb32_in1k_20220119-002556d9.pth
Config: configs/efficientnet/efficientnet-b1_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckpts/efficientnet-b1.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b1_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 27052224
Parameters: 7794184
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 79.20
Top 5 Accuracy: 94.42
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b1_3rdparty_8xb32-aa_in1k_20220119-619d8ae3.pth
Config: configs/efficientnet/efficientnet-b1_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b1.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b1_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 27052224
Parameters: 7794184
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 79.52
Top 5 Accuracy: 94.43
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b1_3rdparty_8xb32-aa-advprop_in1k_20220119-5715267d.pth
Config: configs/efficientnet/efficientnet-b1_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b1.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b2_3rdparty_8xb32_in1k
Metadata:
FLOPs: 34346386
Parameters: 9109994
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 79.64
Top 5 Accuracy: 94.80
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b2_3rdparty_8xb32_in1k_20220119-ea374a30.pth
Config: configs/efficientnet/efficientnet-b2_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckpts/efficientnet-b2.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b2_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 34346386
Parameters: 9109994
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 80.21
Top 5 Accuracy: 94.96
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b2_3rdparty_8xb32-aa_in1k_20220119-dd61e80b.pth
Config: configs/efficientnet/efficientnet-b2_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b2.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b2_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 34346386
Parameters: 9109994
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 80.45
Top 5 Accuracy: 95.07
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b2_3rdparty_8xb32-aa-advprop_in1k_20220119-1655338a.pth
Config: configs/efficientnet/efficientnet-b2_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b2.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b3_3rdparty_8xb32_in1k
Metadata:
FLOPs: 58641904
Parameters: 12233232
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 81.01
Top 5 Accuracy: 95.34
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b3_3rdparty_8xb32_in1k_20220119-4b4d7487.pth
Config: configs/efficientnet/efficientnet-b3_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckpts/efficientnet-b3.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b3_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 58641904
Parameters: 12233232
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 81.58
Top 5 Accuracy: 95.67
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b3_3rdparty_8xb32-aa_in1k_20220119-5b4887a0.pth
Config: configs/efficientnet/efficientnet-b3_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b3.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b3_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 58641904
Parameters: 12233232
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 81.81
Top 5 Accuracy: 95.69
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b3_3rdparty_8xb32-aa-advprop_in1k_20220119-53b41118.pth
Config: configs/efficientnet/efficientnet-b3_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b3.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b4_3rdparty_8xb32_in1k
Metadata:
FLOPs: 121870624
Parameters: 19341616
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.57
Top 5 Accuracy: 96.09
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b4_3rdparty_8xb32_in1k_20220119-81fd4077.pth
Config: configs/efficientnet/efficientnet-b4_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckpts/efficientnet-b4.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b4_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 121870624
Parameters: 19341616
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.95
Top 5 Accuracy: 96.26
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b4_3rdparty_8xb32-aa_in1k_20220119-45b8bd2b.pth
Config: configs/efficientnet/efficientnet-b4_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b4.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b4_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 121870624
Parameters: 19341616
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.25
Top 5 Accuracy: 96.44
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b4_3rdparty_8xb32-aa-advprop_in1k_20220119-38c2238c.pth
Config: configs/efficientnet/efficientnet-b4_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b4.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b5_3rdparty_8xb32_in1k
Metadata:
FLOPs: 243879440
Parameters: 30389784
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.18
Top 5 Accuracy: 96.47
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b5_3rdparty_8xb32_in1k_20220119-e9814430.pth
Config: configs/efficientnet/efficientnet-b5_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckpts/efficientnet-b5.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b5_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 243879440
Parameters: 30389784
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.82
Top 5 Accuracy: 96.76
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b5_3rdparty_8xb32-aa_in1k_20220119-2cab8b78.pth
Config: configs/efficientnet/efficientnet-b5_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b5.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b5_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 243879440
Parameters: 30389784
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.21
Top 5 Accuracy: 96.98
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b5_3rdparty_8xb32-aa-advprop_in1k_20220119-f57a895a.pth
Config: configs/efficientnet/efficientnet-b5_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b5.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b6_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 412002408
Parameters: 43040704
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.05
Top 5 Accuracy: 96.82
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b6_3rdparty_8xb32-aa_in1k_20220119-45b03310.pth
Config: configs/efficientnet/efficientnet-b6_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b6.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b6_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 412002408
Parameters: 43040704
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.74
Top 5 Accuracy: 97.14
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b6_3rdparty_8xb32-aa-advprop_in1k_20220119-bfe3485e.pth
Config: configs/efficientnet/efficientnet-b6_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b6.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b7_3rdparty_8xb32-aa_in1k
Metadata:
FLOPs: 715526512
Parameters: 66347960
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.38
Top 5 Accuracy: 96.88
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b7_3rdparty_8xb32-aa_in1k_20220119-bf03951c.pth
Config: configs/efficientnet/efficientnet-b7_8xb32_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/ckptsaug/efficientnet-b7.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b7_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 715526512
Parameters: 66347960
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.14
Top 5 Accuracy: 97.23
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b7_3rdparty_8xb32-aa-advprop_in1k_20220119-c6dbff10.pth
Config: configs/efficientnet/efficientnet-b7_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b7.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
- Name: efficientnet-b8_3rdparty_8xb32-aa-advprop_in1k
Metadata:
FLOPs: 1092755326
Parameters: 87413142
In Collections: EfficientNet
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.38
Top 5 Accuracy: 97.28
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b8_3rdparty_8xb32-aa-advprop_in1k_20220119-297ce1b7.pth
Config: configs/efficientnet/efficientnet-b8_8xb32-01norm_in1k.py
Converted From:
Weights: https://storage.googleapis.com/cloud-tpu-checkpoints/efficientnet/advprop/efficientnet-b8.tar.gz
Code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
openmmlab_test/mmclassification-0.24.1/configs/fp16/resnet50_b32x8_fp16_dynamic_imagenet.py 0 → 100644
View file @ 5c10a883
_base_ = '../resnet/resnet50_8xb32-fp16-dynamic_in1k.py'
_deprecation_ = dict(
expected='../resnet/resnet50_8xb32-fp16-dynamic_in1k.py',
reference='https://github.com/open-mmlab/mmclassification/pull/508',
)
openmmlab_test/mmclassification-0.24.1/configs/fp16/resnet50_b32x8_fp16_imagenet.py 0 → 100644
View file @ 5c10a883
_base_ = '../resnet/resnet50_8xb32-fp16_in1k.py'
_deprecation_ = dict(
expected='../resnet/resnet50_8xb32-fp16_in1k.py',
reference='https://github.com/open-mmlab/mmclassification/pull/508',
)
openmmlab_test/mmclassification-0.24.1/configs/hornet/README.md 0 → 100644
View file @ 5c10a883
# HorNet
> [HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions](https://arxiv.org/pdf/2207.14284v2.pdf)
<!-- [ALGORITHM] -->
## Abstract
Recent progress in vision Transformers exhibits great success in various tasks driven by the new spatial modeling mechanism based on dot-product self-attention. In this paper, we show that the key ingredients behind the vision Transformers, namely input-adaptive, long-range and high-order spatial interactions, can also be efficiently implemented with a convolution-based framework. We present the Recursive Gated Convolution (g nConv) that performs high-order spatial interactions with gated convolutions and recursive designs. The new operation is highly flexible and customizable, which is compatible with various variants of convolution and extends the two-order interactions in self-attention to arbitrary orders without introducing significant extra computation. g nConv can serve as a plug-and-play module to improve various vision Transformers and convolution-based models. Based on the operation, we construct a new family of generic vision backbones named HorNet. Extensive experiments on ImageNet classification, COCO object detection and ADE20K semantic segmentation show HorNet outperform Swin Transformers and ConvNeXt by a significant margin with similar overall architecture and training configurations. HorNet also shows favorable scalability to more training data and a larger model size. Apart from the effectiveness in visual encoders, we also show g nConv can be applied to task-specific decoders and consistently improve dense prediction performance with less computation. Our results demonstrate that g nConv can be a new basic module for visual modeling that effectively combines the merits of both vision Transformers and CNNs. Code is available at https://github.com/raoyongming/HorNet.
<div align=center>
<img src="https://user-images.githubusercontent.com/24734142/188356236-b8e3db94-eaa6-48e9-b323-15e5ba7f2991.png" width="80%"/>
</div>
## Results and models
### ImageNet-1k
| Model | Pretrain | resolution | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
| :-----------: | :----------: | :--------: | :-------: | :------: | :-------: | :-------: | :--------------------------------------------------------------: | :----------------------------------------------------------------: |
| HorNet-T\* | From scratch | 224x224 | 22.41 | 3.98 | 82.84 | 96.24 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hornet/hornet-tiny_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-tiny_3rdparty_in1k_20220915-0e8eedff.pth) |
| HorNet-T-GF\* | From scratch | 224x224 | 22.99 | 3.9 | 82.98 | 96.38 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hornet/hornet-tiny-gf_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-tiny-gf_3rdparty_in1k_20220915-4c35a66b.pth) |
| HorNet-S\* | From scratch | 224x224 | 49.53 | 8.83 | 83.79 | 96.75 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hornet/hornet-small_8xb64_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-small_3rdparty_in1k_20220915-5935f60f.pth) |
| HorNet-S-GF\* | From scratch | 224x224 | 50.4 | 8.71 | 83.98 | 96.77 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hornet/hornet-small-gf_8xb64_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-small-gf_3rdparty_in1k_20220915-649ca492.pth) |
| HorNet-B\* | From scratch | 224x224 | 87.26 | 15.59 | 84.24 | 96.94 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hornet/hornet-base_8xb64_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-base_3rdparty_in1k_20220915-a06176bb.pth) |
| HorNet-B-GF\* | From scratch | 224x224 | 88.42 | 15.42 | 84.32 | 96.95 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/hornet/hornet-base-gf_8xb64_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-base-gf_3rdparty_in1k_20220915-82c06fa7.pth) |
\*Models with * are converted from [the official repo](https://github.com/raoyongming/HorNet). The config files of these models are only for validation. We don't ensure these config files' training accuracy and welcome you to contribute your reproduction results.
### Pre-trained Models
The pre-trained models on ImageNet-21k are used to fine-tune on the downstream tasks.
| Model | Pretrain | resolution | Params(M) | Flops(G) | Download |
| :--------------: | :----------: | :--------: | :-------: | :------: | :------------------------------------------------------------------------------------------------------------------------: |
| HorNet-L\* | ImageNet-21k | 224x224 | 194.54 | 34.83 | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-large_3rdparty_in21k_20220909-9ccef421.pth) |
| HorNet-L-GF\* | ImageNet-21k | 224x224 | 196.29 | 34.58 | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-large-gf_3rdparty_in21k_20220909-3aea3b61.pth) |
| HorNet-L-GF384\* | ImageNet-21k | 384x384 | 201.23 | 101.63 | [model](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-large-gf384_3rdparty_in21k_20220909-80894290.pth) |
\*Models with * are converted from [the official repo](https://github.com/raoyongming/HorNet).
## Citation
```
@article{rao2022hornet,
title={HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions},
author={Rao, Yongming and Zhao, Wenliang and Tang, Yansong and Zhou, Jie and Lim, Ser-Lam and Lu, Jiwen},
journal={arXiv preprint arXiv:2207.14284},
year={2022}
}
```
openmmlab_test/mmclassification-0.24.1/configs/hornet/hornet-base-gf_8xb64_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/hornet/hornet-base-gf.py',
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
data = dict(samples_per_gpu=64)
optimizer = dict(lr=4e-3)
optimizer_config = dict(grad_clip=dict(max_norm=1.0), _delete_=True)
custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]
openmmlab_test/mmclassification-0.24.1/configs/hornet/hornet-base_8xb64_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/hornet/hornet-base.py',
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
data = dict(samples_per_gpu=64)
optimizer = dict(lr=4e-3)
optimizer_config = dict(grad_clip=dict(max_norm=5.0), _delete_=True)
custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]
openmmlab_test/mmclassification-0.24.1/configs/hornet/hornet-small-gf_8xb64_in1k.py 0 → 100644
View file @ 5c10a883
_base_ = [
'../_base_/models/hornet/hornet-small-gf.py',
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
data = dict(samples_per_gpu=64)
optimizer = dict(lr=4e-3)
optimizer_config = dict(grad_clip=dict(max_norm=1.0), _delete_=True)
custom_hooks = [dict(type='EMAHook', momentum=4e-5, priority='ABOVE_NORMAL')]
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment