Skip to content

GitLab

"...git@developer.sourcefind.cn:kecinstone/2024-pra-vllm.git" did not exist on "f964493274c3c839b2e27453cb70f179090cd027"
Commit 495d9ed9 authored by limm's avatar limm
Browse files

add part code

parent 59b09903
Pipeline #2799 canceled with stages
Hide whitespace changes
Inline Side-by-side
Showing with 818 additions and 0 deletions
configs/itpn/itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-300e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs256_itpn.py',
'../_base_/default_runtime.py',
]
model = dict(
type='iTPN',
backbone=dict(
type='iTPNHiViT',
arch='base',
drop_path_rate=0.0,
rpe=True,
layer_scale_init_value=0.1,
reconstruction_type='clip'),
neck=dict(
type='iTPNPretrainDecoder',
patch_size=16,
in_chans=3,
embed_dim=512,
mlp_ratio=4.,
reconstruction_type='clip',
# transformer pyramid
fpn_dim=256,
fpn_depth=2,
num_outs=3,
),
head=dict(
type='iTPNClipHead',
embed_dims=512,
num_embed=512,
loss=dict(type='CosineSimilarityLoss')),
target_generator=dict(
type='CLIPGenerator',
tokenizer_path= # noqa
'https://download.openmmlab.com/mmselfsup/1.x/target_generator_ckpt/clip_vit_base_16.pth.tar' # noqa
),
)
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
# betas: (0.9, 0.98) for 300 epochs and (0.9, 0.999) for 1600 epochs.
optimizer=dict(
type='AdamW', lr=1.5e-3, betas=(0.9, 0.98), weight_decay=0.05),
clip_grad=dict(max_norm=3.0),
paramwise_cfg=dict(
custom_keys={
'.norm': dict(decay_mult=0.0),
'.pos_embed': dict(decay_mult=0.0),
'.gamma': dict(decay_mult=0.0),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=10,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
eta_min=1e-5,
by_epoch=True,
begin=10,
end=300,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=300)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=2048)
configs/itpn/itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-800e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs256_itpn.py',
'../_base_/default_runtime.py',
]
model = dict(
type='iTPN',
backbone=dict(
type='iTPNHiViT',
arch='base',
drop_path_rate=0.1,
rpe=True,
layer_scale_init_value=0.1,
reconstruction_type='clip'),
neck=dict(
type='iTPNPretrainDecoder',
patch_size=16,
in_chans=3,
embed_dim=512,
mlp_ratio=4.,
reconstruction_type='clip',
# transformer pyramid
fpn_dim=256,
fpn_depth=2,
num_outs=3,
),
head=dict(
type='iTPNClipHead',
embed_dims=512,
num_embed=512,
loss=dict(type='CrossEntropyLoss')),
target_generator=dict(
type='CLIPGenerator',
tokenizer_path= # noqa
'https://download.openmmlab.com/mmselfsup/1.x/target_generator_ckpt/clip_vit_base_16.pth.tar' # noqa
),
)
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
# betas: (0.9, 0.98) for 300 epochs and (0.9, 0.999) for 800/1600 epochs.
optimizer=dict(
type='AdamW', lr=1.5e-3, betas=(0.9, 0.999), weight_decay=0.05),
clip_grad=dict(max_norm=3.0),
paramwise_cfg=dict(
custom_keys={
'.norm': dict(decay_mult=0.0),
'.pos_embed': dict(decay_mult=0.0),
'.gamma': dict(decay_mult=0.0),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=10,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
eta_min=1e-5,
by_epoch=True,
begin=10,
end=800,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=800)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=2048)
configs/itpn/itpn-pixel_hivit-base-p16_8xb512-amp-coslr-1600e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/itpn_hivit-base-p16.py',
'../_base_/datasets/imagenet_bs512_mae.py',
'../_base_/default_runtime.py',
]
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
optimizer=dict(
type='AdamW',
lr=1.5e-4 * 4096 / 256,
betas=(0.9, 0.95),
weight_decay=0.05),
paramwise_cfg=dict(
custom_keys={
'norm': dict(decay_mult=0.0),
'bias': dict(decay_mult=0.0),
'pos_embed': dict(decay_mult=0.),
'mask_token': dict(decay_mult=0.),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=40,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=1560,
by_epoch=True,
begin=40,
end=1600,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=1600)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
# auto resume
resume = True
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=4096)
configs/itpn/itpn-pixel_hivit-base-p16_8xb512-amp-coslr-400e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/itpn_hivit-base-p16.py',
'../_base_/datasets/imagenet_bs512_mae.py',
'../_base_/default_runtime.py',
]
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
optimizer=dict(
type='AdamW',
lr=1.5e-4 * 4096 / 256,
betas=(0.9, 0.95),
weight_decay=0.05),
paramwise_cfg=dict(
custom_keys={
'norm': dict(decay_mult=0.0),
'bias': dict(decay_mult=0.0),
'pos_embed': dict(decay_mult=0.),
'mask_token': dict(decay_mult=0.),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=40,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=360,
by_epoch=True,
begin=40,
end=400,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=400)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
# auto resume
resume = True
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=4096)
configs/itpn/itpn-pixel_hivit-base-p16_8xb512-amp-coslr-800e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/itpn_hivit-base-p16.py',
'../_base_/datasets/imagenet_bs512_mae.py',
'../_base_/default_runtime.py',
]
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
optimizer=dict(
type='AdamW',
lr=1.5e-4 * 4096 / 256,
betas=(0.9, 0.95),
weight_decay=0.05),
paramwise_cfg=dict(
custom_keys={
'norm': dict(decay_mult=0.0),
'bias': dict(decay_mult=0.0),
'pos_embed': dict(decay_mult=0.),
'mask_token': dict(decay_mult=0.),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=40,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=760,
by_epoch=True,
begin=40,
end=800,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=800)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
# auto resume
resume = True
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=4096)
configs/itpn/itpn-pixel_hivit-large-p16_8xb512-amp-coslr-1600e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/itpn_hivit-base-p16.py',
'../_base_/datasets/imagenet_bs512_mae.py',
'../_base_/default_runtime.py',
]
# model settings
model = dict(
backbone=dict(type='iTPNHiViT', arch='large'),
neck=dict(type='iTPNPretrainDecoder', embed_dim=768))
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
optimizer=dict(
type='AdamW',
lr=1.5e-4 * 4096 / 256,
betas=(0.9, 0.95),
weight_decay=0.05),
paramwise_cfg=dict(
custom_keys={
'ln': dict(decay_mult=0.0),
'bias': dict(decay_mult=0.0),
'pos_embed': dict(decay_mult=0.),
'mask_token': dict(decay_mult=0.),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=40,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=1560,
by_epoch=True,
begin=40,
end=1600,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=1600)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
# auto resume
resume = True
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=4096)
configs/itpn/itpn-pixel_hivit-large-p16_8xb512-amp-coslr-400e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/itpn_hivit-base-p16.py',
'../_base_/datasets/imagenet_bs512_mae.py',
'../_base_/default_runtime.py',
]
# model settings
model = dict(
backbone=dict(type='iTPNHiViT', arch='large'),
neck=dict(type='iTPNPretrainDecoder', embed_dim=768))
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
optimizer=dict(
type='AdamW',
lr=1.5e-4 * 4096 / 256,
betas=(0.9, 0.95),
weight_decay=0.05),
paramwise_cfg=dict(
custom_keys={
'ln': dict(decay_mult=0.0),
'bias': dict(decay_mult=0.0),
'pos_embed': dict(decay_mult=0.),
'mask_token': dict(decay_mult=0.),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=40,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=360,
by_epoch=True,
begin=40,
end=400,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=400)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
# auto resume
resume = True
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=4096)
configs/itpn/itpn-pixel_hivit-large-p16_8xb512-amp-coslr-800e_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/itpn_hivit-base-p16.py',
'../_base_/datasets/imagenet_bs512_mae.py',
'../_base_/default_runtime.py',
]
# model settings
model = dict(
backbone=dict(type='iTPNHiViT', arch='large'),
neck=dict(type='iTPNPretrainDecoder', embed_dim=768))
# optimizer wrapper
optim_wrapper = dict(
type='AmpOptimWrapper',
loss_scale='dynamic',
optimizer=dict(
type='AdamW',
lr=1.5e-4 * 4096 / 256,
betas=(0.9, 0.95),
weight_decay=0.05),
paramwise_cfg=dict(
custom_keys={
'ln': dict(decay_mult=0.0),
'bias': dict(decay_mult=0.0),
'pos_embed': dict(decay_mult=0.),
'mask_token': dict(decay_mult=0.),
}))
# learning rate scheduler
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=40,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=760,
by_epoch=True,
begin=40,
end=800,
convert_to_iter_based=True)
]
# runtime settings
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=800)
default_hooks = dict(
# only keeps the latest 3 checkpoints
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
randomness = dict(seed=0, diff_rank_seed=True)
# auto resume
resume = True
find_unused_parameters = True
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
auto_scale_lr = dict(base_batch_size=4096)
configs/itpn/metafile.yml 0 → 100644
View file @ 495d9ed9
Collections:
- Name: iTPN
Metadata:
Architecture:
- Dense Connections
- GELU
- Layer Normalization
- Multi-Head Attention
- Scaled Dot-Product Attention
Paper:
Title: 'Integrally Pre-Trained Transformer Pyramid Networks'
URL: https://arxiv.org/abs/2211.12735
README: configs/itpn/README.md
Code:
URL: null
Version: null
Models:
- Name: itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-800e_in1k
Metadata:
FLOPs: 18474000000
Parameters: 233000000
Training Data:
- ImageNet-1k
In Collection: iTPN
Results: null
Weights:
Config: configs/itpn/itpn-clip-b_hivit-base-p16_8xb256-amp-coslr-800e_in1k.py
- Name: itpn-pixel_hivit-base-p16_8xb512-amp-coslr-800e_in1k
Metadata:
FLOPs: 18474000000
Parameters: 103000000
Training Data:
- ImageNet-1k
In Collection: iTPN
Results: null
Weights:
Config: configs/itpn/itpn-pixel_hivit-base-p16_8xb512-amp-coslr-800e_in1k.py
- Name: itpn-pixel_hivit-large-p16_8xb512-amp-coslr-800e_in1k
Metadata:
FLOPs: 63977000000
Parameters: 314000000
Training Data:
- ImageNet-1k
In Collection: iTPN
Results: null
Weights:
Config: configs/itpn/itpn-pixel_hivit-large-p16_8xb512-amp-coslr-800e_in1k.py
configs/lenet/README.md 0 → 100644
View file @ 495d9ed9
# LeNet
> [Backpropagation Applied to Handwritten Zip Code Recognition](https://ieeexplore.ieee.org/document/6795724)
<!-- [ALGORITHM] -->
## Abstract
The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.
<div align=center>
<img src="https://user-images.githubusercontent.com/26739999/142561080-cd1c4bdc-8739-46ca-bc32-76d462a32901.png" width="50%"/>
</div>
## Citation
```
@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}}
}
```
configs/lenet/lenet5_mnist.py 0 → 100644
View file @ 495d9ed9
# 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'
data_preprocessor = dict(mean=[33.46], std=[78.87], num_classes=10)
pipeline = [dict(type='Resize', scale=32), dict(type='PackInputs')]
common_data_cfg = dict(
type=dataset_type, data_prefix='data/mnist', pipeline=pipeline)
train_dataloader = dict(
batch_size=128,
num_workers=2,
dataset=dict(**common_data_cfg, test_mode=False),
sampler=dict(type='DefaultSampler', shuffle=True),
)
val_dataloader = dict(
batch_size=128,
num_workers=2,
dataset=dict(**common_data_cfg, test_mode=True),
sampler=dict(type='DefaultSampler', shuffle=False),
)
val_evaluator = dict(type='Accuracy', topk=(1, ))
test_dataloader = val_dataloader
test_evaluator = val_evaluator
# schedule settings
optim_wrapper = dict(
optimizer=dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001))
param_scheduler = dict(
type='MultiStepLR', # learning policy, decay on several milestones.
by_epoch=True, # update based on epoch.
milestones=[15], # decay at the 15th epochs.
gamma=0.1, # decay to 0.1 times.
)
train_cfg = dict(by_epoch=True, max_epochs=5, val_interval=1) # train 5 epochs
val_cfg = dict()
test_cfg = dict()
# runtime settings
default_scope = 'mmpretrain'
default_hooks = dict(
# record the time of every iteration.
timer=dict(type='IterTimerHook'),
# print log every 150 iterations.
logger=dict(type='LoggerHook', interval=150),
# enable the parameter scheduler.
param_scheduler=dict(type='ParamSchedulerHook'),
# save checkpoint per epoch.
checkpoint=dict(type='CheckpointHook', interval=1),
# set sampler seed in distributed evrionment.
sampler_seed=dict(type='DistSamplerSeedHook'),
)
env_cfg = dict(
# disable cudnn benchmark
cudnn_benchmark=False,
# set multi process parameters
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
# set distributed parameters
dist_cfg=dict(backend='nccl'),
)
log_level = 'INFO'
# load from which checkpoint
load_from = None
# whether to resume the training of the checkpoint
resume_from = None
# NOTE: `auto_scale_lr` is for automatically scaling LR
# based on the actual training batch size.
# base_batch_size = (1 GPUs) x (128 samples per GPU)
auto_scale_lr = dict(base_batch_size=128)
configs/levit/README.md 0 → 100644
View file @ 495d9ed9
# LeViT
> [LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference](https://arxiv.org/abs/2104.01136)
<!-- [ALGORITHM] -->
## Abstract
We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps with decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers. As a result, we propose LeVIT: a hybrid neural network for fast inference image classification. We consider different measures of efficiency on different hardware platforms, so as to best reflect a wide range of application scenarios. Our extensive experiments empirically validate our technical choices and show they are suitable to most architectures. Overall, LeViT significantly outperforms existing convnets and vision transformers with respect to the speed/accuracy tradeoff. For example, at 80% ImageNet top-1 accuracy, LeViT is 5 times faster than EfficientNet on CPU.
<div align=center>
<img src="https://raw.githubusercontent.com/facebookresearch/LeViT/main/.github/levit.png" width="90%"/>
</div>
## How to use it?
<!-- [TABS-BEGIN] -->
**Predict image**
```python
from mmpretrain import inference_model
predict = inference_model('levit-128s_3rdparty_in1k', 'demo/bird.JPEG')
print(predict['pred_class'])
print(predict['pred_score'])
```
**Use the model**
```python
import torch
from mmpretrain import get_model
model = get_model('levit-128s_3rdparty_in1k', pretrained=True)
inputs = torch.rand(1, 3, 224, 224)
out = model(inputs)
print(type(out))
# To extract features.
feats = model.extract_feat(inputs)
print(type(feats))
```
**Test Command**
Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
Test:
```shell
python tools/test.py configs/levit/levit-128s_8xb256_in1k.py https://download.openmmlab.com/mmclassification/v0/levit/levit-128s_3rdparty_in1k_20230117-e9fbd209.pth
```
<!-- [TABS-END] -->
## Models and results
### Image Classification on ImageNet-1k
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) | Config | Download |
| :--------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :---------------------------------: | :--------------------------------------------------------------------------------------: |
| `levit-128s_3rdparty_in1k`\* | From scratch | 7.39 | 0.31 | 76.51 | 92.90 | [config](levit-128s_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/levit/levit-128s_3rdparty_in1k_20230117-e9fbd209.pth) |
| `levit-128_3rdparty_in1k`\* | From scratch | 8.83 | 0.41 | 78.58 | 93.95 | [config](levit-128_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/levit/levit-128_3rdparty_in1k_20230117-3be02a02.pth) |
| `levit-192_3rdparty_in1k`\* | From scratch | 10.56 | 0.67 | 79.86 | 94.75 | [config](levit-192_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/levit/levit-192_3rdparty_in1k_20230117-8217a0f9.pth) |
| `levit-256_3rdparty_in1k`\* | From scratch | 18.38 | 1.14 | 81.59 | 95.46 | [config](levit-256_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/levit/levit-256_3rdparty_in1k_20230117-5ae2ce7d.pth) |
| `levit-384_3rdparty_in1k`\* | From scratch | 38.36 | 2.37 | 82.59 | 95.95 | [config](levit-384_8xb256_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/levit/levit-384_3rdparty_in1k_20230117-f3539cce.pth) |
*Models with * are converted from the [official repo](https://github.com/facebookresearch/LeViT). The config files of these models are only for inference. We haven't reproduce the training results.*
## Citation
```bibtex
@InProceedings{Graham_2021_ICCV,
author = {Graham, Benjamin and El-Nouby, Alaaeldin and Touvron, Hugo and Stock, Pierre and Joulin, Armand and Jegou, Herve and Douze, Matthijs},
title = {LeViT: A Vision Transformer in ConvNet's Clothing for Faster Inference},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2021},
pages = {12259-12269}
}
```
configs/levit/deploy/levit-128_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = '../levit-128_8xb256_in1k.py'
model = dict(backbone=dict(deploy=True), head=dict(deploy=True))
configs/levit/deploy/levit-128s_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = '../levit-128s_8xb256_in1k.py'
model = dict(backbone=dict(deploy=True), head=dict(deploy=True))
configs/levit/deploy/levit-192_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = '../levit-192_8xb256_in1k.py'
model = dict(backbone=dict(deploy=True), head=dict(deploy=True))
configs/levit/deploy/levit-256_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = '../levit-256_8xb256_in1k.py'
model = dict(backbone=dict(deploy=True), head=dict(deploy=True))
configs/levit/deploy/levit-384_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = '../levit-384_8xb256_in1k.py'
model = dict(backbone=dict(deploy=True), head=dict(deploy=True))
configs/levit/levit-128_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/levit-256-p16.py',
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs2048_adamw_levit.py',
'../_base_/default_runtime.py',
]
# model settings
model = dict(backbone=dict(arch='128'), head=dict(in_channels=384))
# dataset settings
train_dataloader = dict(batch_size=256)
configs/levit/levit-128s_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/levit-256-p16.py',
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs2048_adamw_levit.py',
'../_base_/default_runtime.py',
]
# model settings
model = dict(backbone=dict(arch='128s'), head=dict(in_channels=384))
# dataset settings
train_dataloader = dict(batch_size=256)
configs/levit/levit-192_8xb256_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/levit-256-p16.py',
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs2048_adamw_levit.py',
'../_base_/default_runtime.py',
]
# model settings
model = dict(backbone=dict(arch='192'), head=dict(in_channels=384))
# dataset settings
train_dataloader = dict(batch_size=256)
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