Skip to content

GitLab

Commit 85529f35 authored by unknown's avatar unknown
Browse files

添加openmmlab测试用例

parent b21b0c01
Hide whitespace changes
Inline Side-by-side
Showing with 864 additions and 0 deletions
openmmlab_test/mmclassification-speed-benchmark/configs/lenet/README.md 0 → 100644
View file @ 85529f35
# Backpropagation Applied to Handwritten Zip Code Recognition
## Introduction
<!-- [ALGORITHM] -->
```latex
@ARTICLE{6795724,
author={Y. {LeCun} and B. {Boser} and J. S. {Denker} and D. {Henderson} and R. E. {Howard} and W. {Hubbard} and L. D. {Jackel}},
journal={Neural Computation},
title={Backpropagation Applied to Handwritten Zip Code Recognition},
year={1989},
volume={1},
number={4},
pages={541-551},
doi={10.1162/neco.1989.1.4.541}}
}
```
openmmlab_test/mmclassification-speed-benchmark/configs/lenet/lenet5_mnist.py 0 → 100644
View file @ 85529f35
# model settings
model = dict(
type='ImageClassifier',
backbone=dict(type='LeNet5', num_classes=10),
neck=None,
head=dict(
type='ClsHead',
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
))
# dataset settings
dataset_type = 'MNIST'
img_norm_cfg = dict(mean=[33.46], std=[78.87], to_rgb=True)
train_pipeline = [
dict(type='Resize', size=32),
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='Resize', size=32),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
]
data = dict(
samples_per_gpu=128,
workers_per_gpu=2,
train=dict(
type=dataset_type, data_prefix='data/mnist', pipeline=train_pipeline),
val=dict(
type=dataset_type, data_prefix='data/mnist', pipeline=test_pipeline),
test=dict(
type=dataset_type, data_prefix='data/mnist', pipeline=test_pipeline))
evaluation = dict(
interval=5, metric='accuracy', metric_options={'topk': (1, )})
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(policy='step', step=[15])
# checkpoint saving
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
interval=150,
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook')
])
# yapf:enable
# runtime settings
runner = dict(type='EpochBasedRunner', max_epochs=5)
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/mnist/'
load_from = None
resume_from = None
workflow = [('train', 1)]
openmmlab_test/mmclassification-speed-benchmark/configs/mobilenet_v2/README.md 0 → 100644
View file @ 85529f35
# MobileNetV2: Inverted Residuals and Linear Bottlenecks
## Introduction
<!-- [ALGORITHM] -->
```latex
@INPROCEEDINGS{8578572,
author={M. {Sandler} and A. {Howard} and M. {Zhu} and A. {Zhmoginov} and L. {Chen}},
booktitle={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
title={MobileNetV2: Inverted Residuals and Linear Bottlenecks},
year={2018},
volume={},
number={},
pages={4510-4520},
doi={10.1109/CVPR.2018.00474}}
}
```
## Results and models
### ImageNet
| Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
| MobileNet V2 | 3.5 | 0.319 | 71.86 | 90.42 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/mobilenet_v2/mobilenet_v2_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/mobilenet_v2/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/mobilenet_v2/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.log.json) |
openmmlab_test/mmclassification-speed-benchmark/configs/mobilenet_v2/metafile.yml 0 → 100644
View file @ 85529f35
Collections:
- Name: MobileNet V2
Metadata:
Training Data: ImageNet
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x V100 GPUs
Epochs: 300
Batch Size: 256
Architecture:
- MobileNet V2
Paper: https://arxiv.org/abs/1801.04381
README: configs/mobilenet_v2/README.md
Models:
- Config: configs/mobilenet_v2/mobilenet_v2_b32x8_imagenet.py
In Collection: MobileNet V2
Metadata:
FLOPs: 319000000
Parameters: 3500000
Name: mobilenet_v2_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 71.86
Top 5 Accuracy: 90.42
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/mobilenet_v2/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.pth
openmmlab_test/mmclassification-speed-benchmark/configs/mobilenet_v2/mobilenet_v2_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/mobilenet_v2_1x.py',
'../_base_/datasets/imagenet_bs32_pil_resize.py',
'../_base_/schedules/imagenet_bs256_epochstep.py',
'../_base_/default_runtime.py'
]
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/README.md 0 → 100644
View file @ 85529f35
# Designing Network Design Spaces
## Introduction
<!-- [ALGORITHM] -->
```latex
@article{radosavovic2020designing,
title={Designing Network Design Spaces},
author={Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Dollár},
year={2020},
eprint={2003.13678},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## Pretrain model
The pre-trained modles are converted from [model zoo of pycls](https://github.com/facebookresearch/pycls/blob/master/MODEL_ZOO.md).
### ImageNet
| Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Download |
|:---------------------:|:---------:|:--------:|:---------:|:---------:|:--------:|
| RegNetX-400MF | 5.16 | 0.41 | 72.55 | 90.91 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-400MF-0db9f35c.pth)|
| RegNetX-800MF | 7.26 | 0.81 | 75.21 | 92.37 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-800MF-4f9d1e8a.pth)|
| RegNetX-1.6GF | 9.19 | 1.63 | 77.04 | 93.51 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-1.6GF-cfb32375.pth)|
| RegNetX-3.2GF | 15.3 | 3.21 | 78.26 | 94.20 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-3.2GF-82c43fd5.pth)|
| RegNetX-4.0GF | 22.12 | 4.0 | 78.72 | 94.22 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-4.0GF-ef8bb32c.pth)|
| RegNetX-6.4GF | 26.21 | 6.51 | 79.22 | 94.61 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-6.4GF-6888c0ea.pth)|
| RegNetX-8.0GF | 39.57 | 8.03 | 79.31 | 94.57 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-8.0GF-cb4c77ec.pth)|
| RegNetX-12GF | 46.11 | 12.15 | 79.91 | 94.78 | [model](https://download.openmmlab.com/mmclassification/v0/regnet/convert/RegNetX-12GF-0574538f.pth)|
## Results and models
Waiting for adding.
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_1.6gf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_1.6gf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_12gf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_12gf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_3.2gf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_3.2gf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_4.0gf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_4.0gf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_400mf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_400mf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_6.4gf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_6.4gf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_8.0gf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_8.0gf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/regnet/regnetx_800mf_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/regnet/regnetx_800mf.py',
'../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
# dataset settings
dataset_type = 'ImageNet'
img_norm_cfg = dict(
# The mean and std are used in PyCls when training RegNets
mean=[103.53, 116.28, 123.675],
std=[57.375, 57.12, 58.395],
to_rgb=False)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', size=224),
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='Resize', size=(256, -1)),
dict(type='CenterCrop', crop_size=224),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img'])
]
data = dict(
samples_per_gpu=32,
workers_per_gpu=2,
train=dict(
type=dataset_type,
data_prefix='data/imagenet/train',
pipeline=train_pipeline),
val=dict(
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline),
test=dict(
# replace `data/val` with `data/test` for standard test
type=dataset_type,
data_prefix='data/imagenet/val',
ann_file='data/imagenet/meta/val.txt',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='accuracy')
openmmlab_test/mmclassification-speed-benchmark/configs/resnet/README.md 0 → 100644
View file @ 85529f35
# Deep Residual Learning for Image Recognition
## Introduction
<!-- [ALGORITHM] -->
```latex
@inproceedings{he2016deep,
title={Deep residual learning for image recognition},
author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
pages={770--778},
year={2016}
}
```
## Results and models
## Cifar10
| Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
| ResNet-18-b16x8 | 11.17 | 0.56 | 94.82 | | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet18_b16x8_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.log.json) |
| ResNet-34-b16x8 | 21.28 | 1.16 | 95.34 | | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet34_b16x8_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20210528-a8aa36a6.log.json) |
| ResNet-50-b16x8 | 23.52 | 1.31 | 95.55 | | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_b16x8_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20210528-f54bfad9.log.json) |
| ResNet-101-b16x8 | 42.51 | 2.52 | 95.58 | | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet101_b16x8_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20210528-2d29e936.log.json) |
| ResNet-152-b16x8 | 58.16 | 3.74 | 95.76 | | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet152_b16x8_cifar10.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20210528-3e8e9178.log.json) |
## Cifar100
| Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
| ResNet-50-b16x8 | 23.71 | 1.31 | 79.9 | 95.19 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_b16x8_cifar100.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar100_20210528-67b58a1b.log.json) |
### ImageNet
| Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download |
|:---------------------:|:---------:|:--------:|:---------:|:---------:|:---------:|:--------:|
| ResNet-18 | 11.69 | 1.82 | 70.07 | 89.44 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet18_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_batch256_imagenet_20200708-34ab8f90.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_batch256_imagenet_20200708-34ab8f90.log.json) |
| ResNet-34 | 21.8 | 3.68 | 73.85 | 91.53 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet34_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_batch256_imagenet_20200708-32ffb4f7.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_batch256_imagenet_20200708-32ffb4f7.log.json) |
| ResNet-50 | 25.56 | 4.12 | 76.55 | 93.15 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet50_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.log.json) |
| ResNet-101 | 44.55 | 7.85 | 78.18 | 94.03 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet101_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_batch256_imagenet_20200708-753f3608.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_batch256_imagenet_20200708-753f3608.log.json) |
| ResNet-152 | 60.19 | 11.58 | 78.63 | 94.16 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnet152_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_batch256_imagenet_20200708-ec25b1f9.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_batch256_imagenet_20200708-ec25b1f9.log.json) |
| ResNetV1D-50 | 25.58 | 4.36 | 77.54 | 93.57 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d50_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.log.json) |
| ResNetV1D-101 | 44.57 | 8.09 | 78.93 | 94.48 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d101_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.log.json) |
| ResNetV1D-152 | 60.21 | 11.82 | 79.41 | 94.7 | [config](https://github.com/open-mmlab/mmclassification/blob/master/configs/resnet/resnetv1d152_b32x8_imagenet.py) | [model](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth) &#124; [log](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.log.json) |
openmmlab_test/mmclassification-speed-benchmark/configs/resnet/metafile.yml 0 → 100644
View file @ 85529f35
Collections:
- Name: ResNet
Metadata:
Training Data: ImageNet
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x V100 GPUs
Epochs: 100
Batch Size: 256
Architecture:
- ResNet
Paper: https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html
README: configs/resnet/README.md
Models:
- Config: configs/resnet/resnet18_b16x8_cifar10.py
In Collection: ResNet
Metadata:
FLOPs: 560000000
Parameters: 11170000
Training Data: CIFAR-10
Training Resources: 8x 1080 GPUs
Epochs: 200
Batch Size: 128
Name: resnet18_b16x8_cifar10
Results:
- Dataset: CIFAR-10
Metrics:
Top 1 Accuracy: 94.72
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20200823-f906fa4e.pth
- Config: configs/resnet/resnet34_b16x8_cifar10.py
In Collection: ResNet
Metadata:
FLOPs: 1160000000
Parameters: 21280000
Training Data: CIFAR-10
Training Resources: 8x 1080 GPUs
Epochs: 200
Batch Size: 128
Name: resnet34_b16x8_cifar10
Results:
- Dataset: CIFAR-10
Metrics:
Top 1 Accuracy: 95.34
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_b16x8_cifar10_20200823-52d5d832.pth
- Config: configs/resnet/resnet50_b16x8_cifar10.py
In Collection: ResNet
Metadata:
FLOPs: 1310000000
Parameters: 23520000
Training Data: CIFAR-10
Training Resources: 8x 1080 GPUs
Epochs: 200
Batch Size: 128
Name: resnet50_b16x8_cifar10
Results:
- Dataset: CIFAR-10
Metrics:
Top 1 Accuracy: 95.36
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_b16x8_cifar10_20200823-882aa7b1.pth
- Config: configs/resnet/resnet101_b16x8_cifar10.py
In Collection: ResNet
Metadata:
FLOPs: 2520000000
Parameters: 42510000
Training Data: CIFAR-10
Training Resources: 8x 1080 GPUs
Epochs: 200
Batch Size: 128
Name: resnet101_b16x8_cifar10
Results:
- Dataset: CIFAR-10
Metrics:
Top 1 Accuracy: 95.66
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_b16x8_cifar10_20200823-d9501bbc.pth
- Config: configs/resnet/resnet152_b16x8_cifar10.py
In Collection: ResNet
Metadata:
FLOPs: 3740000000
Parameters: 58160000
Training Data: CIFAR-10
Training Resources: 8x 1080 GPUs
Epochs: 200
Batch Size: 128
Name: resnet152_b16x8_cifar10
Results:
- Dataset: CIFAR-10
Metrics:
Top 1 Accuracy: 95.96
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_b16x8_cifar10_20200823-ad4d5d0c.pth
- Config: configs/resnet/resnet50_b16x8_cifar100.py
In Collection: ResNet
Metadata:
FLOPs: 1310000000
Parameters: 23710000
Training Data: CIFAR-100
Training Resources: 8x 1080 GPUs
Epochs: 200
Batch Size: 128
Name: resnet50_b16x8_cifar100
Results:
- Dataset: CIFAR-100
Metrics:
Top 1 Accuracy: 80.51
Top 5 Accuracy: 95.27
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_cifar100_20210410-37f13c16.pth
- Config: configs/resnet/resnet18_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 1820000000
Parameters: 11690000
Name: resnet18_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 70.07
Top 5 Accuracy: 89.44
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_batch256_imagenet_20200708-34ab8f90.pth
- Config: configs/resnet/resnet34_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 3680000000
Parameters: 2180000
Name: resnet34_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 73.85
Top 5 Accuracy: 91.53
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_batch256_imagenet_20200708-32ffb4f7.pth
- Config: configs/resnet/resnet50_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 4120000000
Parameters: 25560000
Name: resnet50_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 76.55
Top 5 Accuracy: 93.15
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.pth
- Config: configs/resnet/resnet101_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 7850000000
Parameters: 44550000
Name: resnet101_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 78.18
Top 5 Accuracy: 94.03
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_batch256_imagenet_20200708-753f3608.pth
- Config: configs/resnet/resnet152_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 11580000000
Parameters: 60190000
Name: resnet152_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 78.63
Top 5 Accuracy: 94.16
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_batch256_imagenet_20200708-ec25b1f9.pth
- Config: configs/resnet/resnetv1d50_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 4360000000
Parameters: 25580000
Name: resnetv1d50_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 77.4
Top 5 Accuracy: 93.66
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_batch256_imagenet_20200708-1ad0ce94.pth
- Config: configs/resnet/resnetv1d101_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 8090000000
Parameters: 44570000
Name: resnetv1d101_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 78.85
Top 5 Accuracy: 94.38
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_batch256_imagenet_20200708-9cb302ef.pth
- Config: configs/resnet/resnetv1d152_b32x8_imagenet.py
In Collection: ResNet
Metadata:
FLOPs: 11820000000
Parameters: 60210000
Name: resnetv1d152_b32x8_imagenet
Results:
- Dataset: ImageNet
Metrics:
Top 1 Accuracy: 79.35
Top 5 Accuracy: 94.61
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_batch256_imagenet_20200708-e79cb6a2.pth
openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet101_b16x8_cifar10.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/resnet101_cifar.py',
'../_base_/datasets/cifar10_bs16.py',
'../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
]
openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet101_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/resnet101.py', '../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet152_b16x8_cifar10.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/resnet152_cifar.py',
'../_base_/datasets/cifar10_bs16.py',
'../_base_/schedules/cifar10_bs128.py', '../_base_/default_runtime.py'
]
openmmlab_test/mmclassification-speed-benchmark/configs/resnet/resnet152_b32x8_imagenet.py 0 → 100644
View file @ 85529f35
_base_ = [
'../_base_/models/resnet152.py', '../_base_/datasets/imagenet_bs32.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
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