Skip to content

GitLab

"...git@developer.sourcefind.cn:kecinstone/2024-pra-vllm.git" did not exist on "8efe23f15087222540ec076ed00785544442c02f"
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 1450 additions and 0 deletions
configs/vision_transformer/vit-base-p16_8xb64-lora_in1k-384px.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs64_pil_resize.py',
'../_base_/schedules/imagenet_bs4096_AdamW.py',
'../_base_/default_runtime.py'
]
# model setting
model = dict(
type='ImageClassifier',
backbone=dict(
type='LoRAModel',
module=dict(
type='VisionTransformer',
arch='b',
img_size=384,
patch_size=16,
drop_rate=0.1,
init_cfg=dict(type='Pretrained', checkpoint='',
prefix='backbone')),
alpha=16,
rank=16,
drop_rate=0.1,
targets=[dict(type='qkv')]),
neck=None,
head=dict(
type='VisionTransformerClsHead',
num_classes=1000,
in_channels=768,
loss=dict(
type='LabelSmoothLoss', label_smooth_val=0.1,
mode='classy_vision'),
init_cfg=[dict(type='TruncNormal', layer='Linear', std=2e-5)],
))
# dataset setting
data_preprocessor = dict(
mean=[127.5, 127.5, 127.5],
std=[127.5, 127.5, 127.5],
# convert image from BGR to RGB
to_rgb=True,
)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', scale=384, backend='pillow'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='PackInputs'),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
dict(type='CenterCrop', crop_size=384),
dict(type='PackInputs'),
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
param_scheduler = [
dict(
type='LinearLR',
start_factor=1e-4,
by_epoch=True,
begin=0,
end=5,
convert_to_iter_based=True),
dict(
type='CosineAnnealingLR',
T_max=45,
by_epoch=True,
begin=5,
end=50,
eta_min=1e-6,
convert_to_iter_based=True)
]
train_cfg = dict(by_epoch=True, max_epochs=50)
default_hooks = dict(
# save checkpoint per epoch.
checkpoint=dict(type='CheckpointHook', interval=1, max_keep_ckpts=3))
# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))
configs/vision_transformer/vit-base-p32_64xb64_in1k-384px.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/vit-base-p32.py',
'../_base_/datasets/imagenet_bs64_pil_resize.py',
'../_base_/schedules/imagenet_bs4096_AdamW.py',
'../_base_/default_runtime.py'
]
# model setting
model = dict(backbone=dict(img_size=384))
# dataset setting
data_preprocessor = dict(
mean=[127.5, 127.5, 127.5],
std=[127.5, 127.5, 127.5],
# convert image from BGR to RGB
to_rgb=True,
)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', scale=384, backend='pillow'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='PackInputs'),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
dict(type='CenterCrop', crop_size=384),
dict(type='PackInputs'),
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))
configs/vision_transformer/vit-base-p32_64xb64_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/vit-base-p32.py',
'../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
'../_base_/schedules/imagenet_bs4096_AdamW.py',
'../_base_/default_runtime.py'
]
# model setting
model = dict(
head=dict(hidden_dim=3072),
train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)),
)
# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))
configs/vision_transformer/vit-large-p16_64xb64_in1k-384px.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/vit-large-p16.py',
'../_base_/datasets/imagenet_bs64_pil_resize.py',
'../_base_/schedules/imagenet_bs4096_AdamW.py',
'../_base_/default_runtime.py'
]
# model setting
model = dict(backbone=dict(img_size=384))
# dataset setting
data_preprocessor = dict(
mean=[127.5, 127.5, 127.5],
std=[127.5, 127.5, 127.5],
# convert image from BGR to RGB
to_rgb=True,
)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', scale=384, backend='pillow'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='PackInputs'),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
dict(type='CenterCrop', crop_size=384),
dict(type='PackInputs'),
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))
configs/vision_transformer/vit-large-p16_64xb64_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/vit-large-p16.py',
'../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
'../_base_/schedules/imagenet_bs4096_AdamW.py',
'../_base_/default_runtime.py'
]
# model setting
model = dict(
head=dict(hidden_dim=3072),
train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)),
)
# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))
configs/vision_transformer/vit-large-p32_64xb64_in1k-384px.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/vit-large-p32.py',
'../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
'../_base_/schedules/imagenet_bs4096_AdamW.py',
'../_base_/default_runtime.py'
]
# model setting
model = dict(backbone=dict(img_size=384))
# dataset setting
data_preprocessor = dict(
mean=[127.5, 127.5, 127.5],
std=[127.5, 127.5, 127.5],
# convert image from BGR to RGB
to_rgb=True,
)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='RandomResizedCrop', scale=384, backend='pillow'),
dict(type='RandomFlip', prob=0.5, direction='horizontal'),
dict(type='PackInputs'),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(type='ResizeEdge', scale=384, edge='short', backend='pillow'),
dict(type='CenterCrop', crop_size=384),
dict(type='PackInputs'),
]
train_dataloader = dict(dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = dict(dataset=dict(pipeline=test_pipeline))
# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))
configs/vision_transformer/vit-large-p32_64xb64_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/vit-large-p32.py',
'../_base_/datasets/imagenet_bs64_pil_resize_autoaug.py',
'../_base_/schedules/imagenet_bs4096_AdamW.py',
'../_base_/default_runtime.py'
]
# model setting
model = dict(
head=dict(hidden_dim=3072),
train_cfg=dict(augments=dict(type='Mixup', alpha=0.2)),
)
# schedule setting
optim_wrapper = dict(clip_grad=dict(max_norm=1.0))
configs/wrn/README.md 0 → 100644
View file @ 495d9ed9
# Wide-ResNet
> [Wide Residual Networks](https://arxiv.org/abs/1605.07146)
<!-- [ALGORITHM] -->
## Abstract
Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet.
<div align=center>
<img src="https://user-images.githubusercontent.com/26739999/156701329-2c7ec7bc-23da-401b-86bf-dea8567ccee8.png" width="90%"/>
</div>
## How to use it?
<!-- [TABS-BEGIN] -->
**Predict image**
```python
from mmpretrain import inference_model
predict = inference_model('wide-resnet50_3rdparty_8xb32_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('wide-resnet50_3rdparty_8xb32_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/wrn/wide-resnet50_8xb32_in1k.py https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty_8xb32_in1k_20220304-66678344.pth
```
<!-- [TABS-END] -->
## Models and results
### Image Classification on ImageNet-1k
| Model | Pretrain | Params (M) | Flops (G) | Top-1 (%) | Top-5 (%) | Config | Download |
| :----------------------------------------- | :----------: | :--------: | :-------: | :-------: | :-------: | :----------------------------------------: | :-----------------------------------------------------------------: |
| `wide-resnet50_3rdparty_8xb32_in1k`\* | From scratch | 68.88 | 11.44 | 78.48 | 94.08 | [config](wide-resnet50_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty_8xb32_in1k_20220304-66678344.pth) |
| `wide-resnet101_3rdparty_8xb32_in1k`\* | From scratch | 126.89 | 22.81 | 78.84 | 94.28 | [config](wide-resnet101_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet101_3rdparty_8xb32_in1k_20220304-8d5f9d61.pth) |
| `wide-resnet50_3rdparty-timm_8xb32_in1k`\* | From scratch | 68.88 | 11.44 | 81.45 | 95.53 | [config](wide-resnet50_timm_8xb32_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty-timm_8xb32_in1k_20220304-83ae4399.pth) |
*Models with * are converted from the [timm](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/resnet.py). The config files of these models are only for inference. We haven't reproduce the training results.*
## Citation
```bibtex
@INPROCEEDINGS{Zagoruyko2016WRN,
author = {Sergey Zagoruyko and Nikos Komodakis},
title = {Wide Residual Networks},
booktitle = {BMVC},
year = {2016}}
```
configs/wrn/metafile.yml 0 → 100644
View file @ 495d9ed9
Collections:
- Name: Wide-ResNet
Metadata:
Training Data: ImageNet-1k
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x V100 GPUs
Epochs: 100
Batch Size: 256
Architecture:
- 1x1 Convolution
- Batch Normalization
- Convolution
- Global Average Pooling
- Max Pooling
- ReLU
- Residual Connection
- Softmax
- Wide Residual Block
Paper:
URL: https://arxiv.org/abs/1605.07146
Title: "Wide Residual Networks"
README: configs/wrn/README.md
Code:
URL: https://github.com/open-mmlab/mmpretrain/blob/v0.20.1/mmcls/models/backbones/resnet.py#L383
Version: v0.20.1
Models:
- Name: wide-resnet50_3rdparty_8xb32_in1k
Metadata:
FLOPs: 11440000000 # 11.44G
Parameters: 68880000 # 68.88M
In Collection: Wide-ResNet
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 78.48
Top 5 Accuracy: 94.08
Weights: https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty_8xb32_in1k_20220304-66678344.pth
Config: configs/wrn/wide-resnet50_8xb32_in1k.py
Converted From:
Weights: https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth
Code: https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py
- Name: wide-resnet101_3rdparty_8xb32_in1k
Metadata:
FLOPs: 22810000000 # 22.81G
Parameters: 126890000 # 126.89M
In Collection: Wide-ResNet
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 78.84
Top 5 Accuracy: 94.28
Weights: https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet101_3rdparty_8xb32_in1k_20220304-8d5f9d61.pth
Config: configs/wrn/wide-resnet101_8xb32_in1k.py
Converted From:
Weights: https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth
Code: https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py
- Name: wide-resnet50_3rdparty-timm_8xb32_in1k
Metadata:
FLOPs: 11440000000 # 11.44G
Parameters: 68880000 # 68.88M
In Collection: Wide-ResNet
Results:
- Task: Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 81.45
Top 5 Accuracy: 95.53
Weights: https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty-timm_8xb32_in1k_20220304-83ae4399.pth
Config: configs/wrn/wide-resnet50_timm_8xb32_in1k.py
Converted From:
Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/wide_resnet50_racm-8234f177.pth
Code: https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/resnet.py
configs/wrn/wide-resnet101_8xb32_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/wide-resnet50.py',
'../_base_/datasets/imagenet_bs32_pil_resize.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
model = dict(backbone=dict(depth=101))
configs/wrn/wide-resnet50_8xb32_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/wide-resnet50.py',
'../_base_/datasets/imagenet_bs32_pil_resize.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
configs/wrn/wide-resnet50_timm_8xb32_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/models/wide-resnet50.py',
'../_base_/datasets/imagenet_bs32_pil_bicubic.py',
'../_base_/schedules/imagenet_bs256.py', '../_base_/default_runtime.py'
]
configs/xcit/README.md 0 → 100644
View file @ 495d9ed9
# XCiT
> [XCiT: Cross-Covariance Image Transformers](https://arxiv.org/abs/2106.09681)
<!-- [ALGORITHM] -->
## Abstract
Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images. Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.
<div align=center>
<img src="https://user-images.githubusercontent.com/26739999/218900814-64a44606-150b-4757-aec8-7015c77a9fd1.png" width="60%"/>
</div>
## How to use it?
<!-- [TABS-BEGIN] -->
**Use the model**
```python
import torch
from mmpretrain import get_model
model = get_model('xcit-nano-12-p16_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/xcit/xcit-nano-12-p16_8xb128_in1k.py https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty_in1k_20230213-ed776c38.pth
```
<!-- [TABS-END] -->
## Models and results
### Pretrained models
| Model | Params (M) | Flops (G) | Config | Download |
| :---------------------------------------------- | :--------: | :-------: | :-----------------------------------------------: | :-----------------------------------------------------------------------------------: |
| `xcit-nano-12-p16_3rdparty_in1k`\* | 3.05 | 0.56 | [config](xcit-nano-12-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty_in1k_20230213-ed776c38.pth) |
| `xcit-nano-12-p16_3rdparty-dist_in1k`\* | 3.05 | 0.56 | [config](xcit-nano-12-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k_20230213-fb247f7b.pth) |
| `xcit-tiny-12-p16_3rdparty_in1k`\* | 6.72 | 1.24 | [config](xcit-tiny-12-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty_in1k_20230213-82c547ca.pth) |
| `xcit-tiny-12-p16_3rdparty-dist_in1k`\* | 6.72 | 1.24 | [config](xcit-tiny-12-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k_20230213-d5fde0a3.pth) |
| `xcit-nano-12-p16_3rdparty-dist_in1k-384px`\* | 3.05 | 1.64 | [config](xcit-nano-12-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k-384px_20230213-712db4d4.pth) |
| `xcit-nano-12-p8_3rdparty_in1k`\* | 3.05 | 2.16 | [config](xcit-nano-12-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty_in1k_20230213-3370c293.pth) |
| `xcit-nano-12-p8_3rdparty-dist_in1k`\* | 3.05 | 2.16 | [config](xcit-nano-12-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k_20230213-2f87d2b3.pth) |
| `xcit-tiny-24-p16_3rdparty_in1k`\* | 12.12 | 2.34 | [config](xcit-tiny-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty_in1k_20230213-366c1cd0.pth) |
| `xcit-tiny-24-p16_3rdparty-dist_in1k`\* | 12.12 | 2.34 | [config](xcit-tiny-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k_20230213-b472e80a.pth) |
| `xcit-tiny-12-p16_3rdparty-dist_in1k-384px`\* | 6.72 | 3.64 | [config](xcit-tiny-12-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k-384px_20230213-00a20023.pth) |
| `xcit-tiny-12-p8_3rdparty_in1k`\* | 6.71 | 4.81 | [config](xcit-tiny-12-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty_in1k_20230213-8b02f8f5.pth) |
| `xcit-tiny-12-p8_3rdparty-dist_in1k`\* | 6.71 | 4.81 | [config](xcit-tiny-12-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k_20230213-f3f9b44f.pth) |
| `xcit-small-12-p16_3rdparty_in1k`\* | 26.25 | 4.81 | [config](xcit-small-12-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty_in1k_20230213-d36779d2.pth) |
| `xcit-small-12-p16_3rdparty-dist_in1k`\* | 26.25 | 4.81 | [config](xcit-small-12-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k_20230213-c95bbae1.pth) |
| `xcit-nano-12-p8_3rdparty-dist_in1k-384px`\* | 3.05 | 6.34 | [config](xcit-nano-12-p8_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k-384px_20230213-09d925ef.pth) |
| `xcit-tiny-24-p16_3rdparty-dist_in1k-384px`\* | 12.12 | 6.87 | [config](xcit-tiny-24-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k-384px_20230213-20e13917.pth) |
| `xcit-small-24-p16_3rdparty_in1k`\* | 47.67 | 9.10 | [config](xcit-small-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty_in1k_20230213-40febe38.pth) |
| `xcit-small-24-p16_3rdparty-dist_in1k`\* | 47.67 | 9.10 | [config](xcit-small-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k_20230213-130d7262.pth) |
| `xcit-tiny-24-p8_3rdparty_in1k`\* | 12.11 | 9.21 | [config](xcit-tiny-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty_in1k_20230213-4b9ba392.pth) |
| `xcit-tiny-24-p8_3rdparty-dist_in1k`\* | 12.11 | 9.21 | [config](xcit-tiny-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k_20230213-ad9c44b0.pth) |
| `xcit-tiny-12-p8_3rdparty-dist_in1k-384px`\* | 6.71 | 14.13 | [config](xcit-tiny-12-p8_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k-384px_20230213-a072174a.pth) |
| `xcit-small-12-p16_3rdparty-dist_in1k-384px`\* | 26.25 | 14.14 | [config](xcit-small-12-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k-384px_20230213-ba36c982.pth) |
| `xcit-medium-24-p16_3rdparty_in1k`\* | 84.40 | 16.13 | [config](xcit-medium-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty_in1k_20230213-ad0aa92e.pth) |
| `xcit-medium-24-p16_3rdparty-dist_in1k`\* | 84.40 | 16.13 | [config](xcit-medium-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k_20230213-aca5cd0c.pth) |
| `xcit-small-12-p8_3rdparty_in1k`\* | 26.21 | 18.69 | [config](xcit-small-12-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty_in1k_20230213-9e364ce3.pth) |
| `xcit-small-12-p8_3rdparty-dist_in1k`\* | 26.21 | 18.69 | [config](xcit-small-12-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k_20230213-71886580.pth) |
| `xcit-small-24-p16_3rdparty-dist_in1k-384px`\* | 47.67 | 26.72 | [config](xcit-small-24-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k-384px_20230213-28fa2d0e.pth) |
| `xcit-tiny-24-p8_3rdparty-dist_in1k-384px`\* | 12.11 | 27.05 | [config](xcit-tiny-24-p8_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k-384px_20230213-30d5e5ec.pth) |
| `xcit-small-24-p8_3rdparty_in1k`\* | 47.63 | 35.81 | [config](xcit-small-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty_in1k_20230213-280ebcc7.pth) |
| `xcit-small-24-p8_3rdparty-dist_in1k`\* | 47.63 | 35.81 | [config](xcit-small-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k_20230213-f2773c78.pth) |
| `xcit-large-24-p16_3rdparty_in1k`\* | 189.10 | 35.86 | [config](xcit-large-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty_in1k_20230214-d29d2529.pth) |
| `xcit-large-24-p16_3rdparty-dist_in1k`\* | 189.10 | 35.86 | [config](xcit-large-24-p16_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k_20230214-4fea599c.pth) |
| `xcit-medium-24-p16_3rdparty-dist_in1k-384px`\* | 84.40 | 47.39 | [config](xcit-medium-24-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k-384px_20230214-6c23a201.pth) |
| `xcit-small-12-p8_3rdparty-dist_in1k-384px`\* | 26.21 | 54.92 | [config](xcit-small-12-p8_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k-384px_20230214-9f2178bc.pth) |
| `xcit-medium-24-p8_3rdparty_in1k`\* | 84.32 | 63.52 | [config](xcit-medium-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty_in1k_20230214-c362850b.pth) |
| `xcit-medium-24-p8_3rdparty-dist_in1k`\* | 84.32 | 63.52 | [config](xcit-medium-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k_20230214-625c953b.pth) |
| `xcit-small-24-p8_3rdparty-dist_in1k-384px`\* | 47.63 | 105.24 | [config](xcit-small-24-p8_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k-384px_20230214-57298eca.pth) |
| `xcit-large-24-p16_3rdparty-dist_in1k-384px`\* | 189.10 | 105.35 | [config](xcit-large-24-p16_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k-384px_20230214-bd515a34.pth) |
| `xcit-large-24-p8_3rdparty_in1k`\* | 188.93 | 141.23 | [config](xcit-large-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty_in1k_20230214-08f2f664.pth) |
| `xcit-large-24-p8_3rdparty-dist_in1k`\* | 188.93 | 141.23 | [config](xcit-large-24-p8_8xb128_in1k.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k_20230214-8c092b34.pth) |
| `xcit-medium-24-p8_3rdparty-dist_in1k-384px`\* | 84.32 | 186.67 | [config](xcit-medium-24-p8_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k-384px_20230214-5db925e0.pth) |
| `xcit-large-24-p8_3rdparty-dist_in1k-384px`\* | 188.93 | 415.00 | [config](xcit-large-24-p8_8xb128_in1k-384px.py) | [model](https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k-384px_20230214-9f718b1a.pth) |
*Models with * are converted from the [official repo](https://github.com/facebookresearch/xcit). The config files of these models are only for inference. We haven't reproduce the training results.*
## Citation
```bibtex
@article{el2021xcit,
title={XCiT: Cross-Covariance Image Transformers},
author={El-Nouby, Alaaeldin and Touvron, Hugo and Caron, Mathilde and Bojanowski, Piotr and Douze, Matthijs and Joulin, Armand and Laptev, Ivan and Neverova, Natalia and Synnaeve, Gabriel and Verbeek, Jakob and others},
journal={arXiv preprint arXiv:2106.09681},
year={2021}
}
```
configs/xcit/metafile.yml 0 → 100644
View file @ 495d9ed9
Collections:
- Name: XCiT
Metadata:
Architecture:
- Class Attention
- Local Patch Interaction
- Cross-Covariance Attention
Paper:
Title: 'XCiT: Cross-Covariance Image Transformers'
URL: https://arxiv.org/abs/2106.09681
README: configs/xcit/README.md
Models:
- Name: xcit-nano-12-p16_3rdparty_in1k
Metadata:
FLOPs: 557074560
Parameters: 3053224
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 70.35
Top 5 Accuracy: 89.98
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty_in1k_20230213-ed776c38.pth
Config: configs/xcit/xcit-nano-12-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p16_224.pth
- Name: xcit-nano-12-p16_3rdparty-dist_in1k
Metadata:
FLOPs: 557074560
Parameters: 3053224
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 72.36
Top 5 Accuracy: 91.02
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k_20230213-fb247f7b.pth
Config: configs/xcit/xcit-nano-12-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p16_224_dist.pth
- Name: xcit-tiny-12-p16_3rdparty_in1k
Metadata:
FLOPs: 1239698112
Parameters: 6716272
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 77.21
Top 5 Accuracy: 93.62
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty_in1k_20230213-82c547ca.pth
Config: configs/xcit/xcit-tiny-12-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p16_224.pth
- Name: xcit-tiny-12-p16_3rdparty-dist_in1k
Metadata:
FLOPs: 1239698112
Parameters: 6716272
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 78.7
Top 5 Accuracy: 94.12
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k_20230213-d5fde0a3.pth
Config: configs/xcit/xcit-tiny-12-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p16_224_dist.pth
- Name: xcit-nano-12-p16_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 1636347520
Parameters: 3053224
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 74.93
Top 5 Accuracy: 92.42
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p16_3rdparty-dist_in1k-384px_20230213-712db4d4.pth
Config: configs/xcit/xcit-nano-12-p16_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p16_384_dist.pth
- Name: xcit-nano-12-p8_3rdparty_in1k
Metadata:
FLOPs: 2156861056
Parameters: 3049016
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 73.8
Top 5 Accuracy: 92.08
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty_in1k_20230213-3370c293.pth
Config: configs/xcit/xcit-nano-12-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p8_224.pth
- Name: xcit-nano-12-p8_3rdparty-dist_in1k
Metadata:
FLOPs: 2156861056
Parameters: 3049016
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 76.17
Top 5 Accuracy: 93.08
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k_20230213-2f87d2b3.pth
Config: configs/xcit/xcit-nano-12-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p8_224_dist.pth
- Name: xcit-tiny-24-p16_3rdparty_in1k
Metadata:
FLOPs: 2339305152
Parameters: 12116896
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 79.47
Top 5 Accuracy: 94.85
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty_in1k_20230213-366c1cd0.pth
Config: configs/xcit/xcit-tiny-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p16_224.pth
- Name: xcit-tiny-24-p16_3rdparty-dist_in1k
Metadata:
FLOPs: 2339305152
Parameters: 12116896
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 80.51
Top 5 Accuracy: 95.17
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k_20230213-b472e80a.pth
Config: configs/xcit/xcit-tiny-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p16_224_dist.pth
- Name: xcit-tiny-12-p16_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 3641468352
Parameters: 6716272
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 80.58
Top 5 Accuracy: 95.38
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p16_3rdparty-dist_in1k-384px_20230213-00a20023.pth
Config: configs/xcit/xcit-tiny-12-p16_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p16_384_dist.pth
- Name: xcit-tiny-12-p8_3rdparty_in1k
Metadata:
FLOPs: 4807399872
Parameters: 6706504
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 79.75
Top 5 Accuracy: 94.88
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty_in1k_20230213-8b02f8f5.pth
Config: configs/xcit/xcit-tiny-12-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p8_224.pth
- Name: xcit-tiny-12-p8_3rdparty-dist_in1k
Metadata:
FLOPs: 4807399872
Parameters: 6706504
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 81.26
Top 5 Accuracy: 95.46
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k_20230213-f3f9b44f.pth
Config: configs/xcit/xcit-tiny-12-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p8_224_dist.pth
- Name: xcit-small-12-p16_3rdparty_in1k
Metadata:
FLOPs: 4814951808
Parameters: 26253304
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 81.87
Top 5 Accuracy: 95.77
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty_in1k_20230213-d36779d2.pth
Config: configs/xcit/xcit-small-12-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p16_224.pth
- Name: xcit-small-12-p16_3rdparty-dist_in1k
Metadata:
FLOPs: 4814951808
Parameters: 26253304
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.12
Top 5 Accuracy: 96.41
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k_20230213-c95bbae1.pth
Config: configs/xcit/xcit-small-12-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p16_224_dist.pth
- Name: xcit-nano-12-p8_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 6337760896
Parameters: 3049016
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 77.69
Top 5 Accuracy: 94.09
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-nano-12-p8_3rdparty-dist_in1k-384px_20230213-09d925ef.pth
Config: configs/xcit/xcit-nano-12-p8_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_nano_12_p8_384_dist.pth
- Name: xcit-tiny-24-p16_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 6872966592
Parameters: 12116896
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.43
Top 5 Accuracy: 96.2
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p16_3rdparty-dist_in1k-384px_20230213-20e13917.pth
Config: configs/xcit/xcit-tiny-24-p16_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p16_384_dist.pth
- Name: xcit-small-24-p16_3rdparty_in1k
Metadata:
FLOPs: 9095064960
Parameters: 47671384
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.38
Top 5 Accuracy: 95.93
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty_in1k_20230213-40febe38.pth
Config: configs/xcit/xcit-small-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p16_224.pth
- Name: xcit-small-24-p16_3rdparty-dist_in1k
Metadata:
FLOPs: 9095064960
Parameters: 47671384
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.7
Top 5 Accuracy: 96.61
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k_20230213-130d7262.pth
Config: configs/xcit/xcit-small-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p16_224_dist.pth
- Name: xcit-tiny-24-p8_3rdparty_in1k
Metadata:
FLOPs: 9205828032
Parameters: 12107128
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 81.7
Top 5 Accuracy: 95.9
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty_in1k_20230213-4b9ba392.pth
Config: configs/xcit/xcit-tiny-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p8_224.pth
- Name: xcit-tiny-24-p8_3rdparty-dist_in1k
Metadata:
FLOPs: 9205828032
Parameters: 12107128
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.62
Top 5 Accuracy: 96.16
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k_20230213-ad9c44b0.pth
Config: configs/xcit/xcit-tiny-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p8_224_dist.pth
- Name: xcit-tiny-12-p8_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 14126142912
Parameters: 6706504
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.46
Top 5 Accuracy: 96.22
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-12-p8_3rdparty-dist_in1k-384px_20230213-a072174a.pth
Config: configs/xcit/xcit-tiny-12-p8_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_12_p8_384_dist.pth
- Name: xcit-small-12-p16_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 14143179648
Parameters: 26253304
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.74
Top 5 Accuracy: 97.19
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p16_3rdparty-dist_in1k-384px_20230213-ba36c982.pth
Config: configs/xcit/xcit-small-12-p16_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p16_384_dist.pth
- Name: xcit-medium-24-p16_3rdparty_in1k
Metadata:
FLOPs: 16129561088
Parameters: 84395752
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.56
Top 5 Accuracy: 95.82
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty_in1k_20230213-ad0aa92e.pth
Config: configs/xcit/xcit-medium-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p16_224.pth
- Name: xcit-medium-24-p16_3rdparty-dist_in1k
Metadata:
FLOPs: 16129561088
Parameters: 84395752
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.15
Top 5 Accuracy: 96.82
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k_20230213-aca5cd0c.pth
Config: configs/xcit/xcit-medium-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p16_224_dist.pth
- Name: xcit-small-12-p8_3rdparty_in1k
Metadata:
FLOPs: 18691601280
Parameters: 26213032
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.21
Top 5 Accuracy: 96.41
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty_in1k_20230213-9e364ce3.pth
Config: configs/xcit/xcit-small-12-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p8_224.pth
- Name: xcit-small-12-p8_3rdparty-dist_in1k
Metadata:
FLOPs: 18691601280
Parameters: 26213032
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.97
Top 5 Accuracy: 96.81
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k_20230213-71886580.pth
Config: configs/xcit/xcit-small-12-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p8_224_dist.pth
- Name: xcit-small-24-p16_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 26721471360
Parameters: 47671384
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.1
Top 5 Accuracy: 97.32
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p16_3rdparty-dist_in1k-384px_20230213-28fa2d0e.pth
Config: configs/xcit/xcit-small-24-p16_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p16_384_dist.pth
- Name: xcit-tiny-24-p8_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 27052135872
Parameters: 12107128
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.77
Top 5 Accuracy: 96.72
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-tiny-24-p8_3rdparty-dist_in1k-384px_20230213-30d5e5ec.pth
Config: configs/xcit/xcit-tiny-24-p8_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_tiny_24_p8_384_dist.pth
- Name: xcit-small-24-p8_3rdparty_in1k
Metadata:
FLOPs: 35812053888
Parameters: 47631112
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.62
Top 5 Accuracy: 96.51
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty_in1k_20230213-280ebcc7.pth
Config: configs/xcit/xcit-small-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p8_224.pth
- Name: xcit-small-24-p8_3rdparty-dist_in1k
Metadata:
FLOPs: 35812053888
Parameters: 47631112
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.68
Top 5 Accuracy: 97.07
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k_20230213-f2773c78.pth
Config: configs/xcit/xcit-small-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p8_224_dist.pth
- Name: xcit-large-24-p16_3rdparty_in1k
Metadata:
FLOPs: 35855948544
Parameters: 189096136
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.97
Top 5 Accuracy: 95.86
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty_in1k_20230214-d29d2529.pth
Config: configs/xcit/xcit-large-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p16_224.pth
- Name: xcit-large-24-p16_3rdparty-dist_in1k
Metadata:
FLOPs: 35855948544
Parameters: 189096136
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.61
Top 5 Accuracy: 97.07
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k_20230214-4fea599c.pth
Config: configs/xcit/xcit-large-24-p16_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p16_224_dist.pth
- Name: xcit-medium-24-p16_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 47388932608
Parameters: 84395752
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.47
Top 5 Accuracy: 97.49
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p16_3rdparty-dist_in1k-384px_20230214-6c23a201.pth
Config: configs/xcit/xcit-medium-24-p16_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p16_384_dist.pth
- Name: xcit-small-12-p8_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 54923537280
Parameters: 26213032
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.12
Top 5 Accuracy: 97.31
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-12-p8_3rdparty-dist_in1k-384px_20230214-9f2178bc.pth
Config: configs/xcit/xcit-small-12-p8_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_12_p8_384_dist.pth
- Name: xcit-medium-24-p8_3rdparty_in1k
Metadata:
FLOPs: 63524706816
Parameters: 84323624
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.61
Top 5 Accuracy: 96.23
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty_in1k_20230214-c362850b.pth
Config: configs/xcit/xcit-medium-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p8_224.pth
- Name: xcit-medium-24-p8_3rdparty-dist_in1k
Metadata:
FLOPs: 63524706816
Parameters: 84323624
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.0
Top 5 Accuracy: 97.16
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k_20230214-625c953b.pth
Config: configs/xcit/xcit-medium-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p8_224_dist.pth
- Name: xcit-small-24-p8_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 105236704128
Parameters: 47631112
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.57
Top 5 Accuracy: 97.6
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-small-24-p8_3rdparty-dist_in1k-384px_20230214-57298eca.pth
Config: configs/xcit/xcit-small-24-p8_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_small_24_p8_384_dist.pth
- Name: xcit-large-24-p16_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 105345095424
Parameters: 189096136
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.78
Top 5 Accuracy: 97.6
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p16_3rdparty-dist_in1k-384px_20230214-bd515a34.pth
Config: configs/xcit/xcit-large-24-p16_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p16_384_dist.pth
- Name: xcit-large-24-p8_3rdparty_in1k
Metadata:
FLOPs: 141225699072
Parameters: 188932648
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.23
Top 5 Accuracy: 96.58
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty_in1k_20230214-08f2f664.pth
Config: configs/xcit/xcit-large-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p8_224.pth
- Name: xcit-large-24-p8_3rdparty-dist_in1k
Metadata:
FLOPs: 141225699072
Parameters: 188932648
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.14
Top 5 Accuracy: 97.32
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k_20230214-8c092b34.pth
Config: configs/xcit/xcit-large-24-p8_8xb128_in1k.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p8_224_dist.pth
- Name: xcit-medium-24-p8_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 186672626176
Parameters: 84323624
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.87
Top 5 Accuracy: 97.61
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-medium-24-p8_3rdparty-dist_in1k-384px_20230214-5db925e0.pth
Config: configs/xcit/xcit-medium-24-p8_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_medium_24_p8_384_dist.pth
- Name: xcit-large-24-p8_3rdparty-dist_in1k-384px
Metadata:
FLOPs: 415003137792
Parameters: 188932648
Training Data: ImageNet-1k
In Collection: XCiT
Results:
- Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 86.13
Top 5 Accuracy: 97.75
Task: Image Classification
Weights: https://download.openmmlab.com/mmclassification/v0/xcit/xcit-large-24-p8_3rdparty-dist_in1k-384px_20230214-9f718b1a.pth
Config: configs/xcit/xcit-large-24-p8_8xb128_in1k-384px.py
Converted From:
Code: https://github.com/facebookresearch/xcit
Weights: https://dl.fbaipublicfiles.com/xcit/xcit_large_24_p8_384_dist.pth
configs/xcit/xcit-large-24-p16_8xb128_in1k-384px.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs64_swin_384.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
model = dict(
type='ImageClassifier',
backbone=dict(
type='XCiT',
patch_size=16,
embed_dims=768,
depth=24,
num_heads=16,
mlp_ratio=4,
qkv_bias=True,
layer_scale_init_value=1e-5,
tokens_norm=True,
out_type='cls_token',
),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=768,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
),
train_cfg=dict(augments=[
dict(type='Mixup', alpha=0.8),
dict(type='CutMix', alpha=1.0),
]),
)
# dataset settings
train_dataloader = dict(batch_size=128)
configs/xcit/xcit-large-24-p16_8xb128_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
model = dict(
type='ImageClassifier',
backbone=dict(
type='XCiT',
patch_size=16,
embed_dims=768,
depth=24,
num_heads=16,
mlp_ratio=4,
qkv_bias=True,
layer_scale_init_value=1e-5,
tokens_norm=True,
out_type='cls_token',
),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=768,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
),
train_cfg=dict(augments=[
dict(type='Mixup', alpha=0.8),
dict(type='CutMix', alpha=1.0),
]),
)
# dataset settings
train_dataloader = dict(batch_size=128)
configs/xcit/xcit-large-24-p8_8xb128_in1k-384px.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs64_swin_384.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
model = dict(
type='ImageClassifier',
backbone=dict(
type='XCiT',
patch_size=8,
embed_dims=768,
depth=24,
num_heads=16,
mlp_ratio=4,
qkv_bias=True,
layer_scale_init_value=1e-5,
tokens_norm=True,
out_type='cls_token',
),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=768,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
),
train_cfg=dict(augments=[
dict(type='Mixup', alpha=0.8),
dict(type='CutMix', alpha=1.0),
]),
)
# dataset settings
train_dataloader = dict(batch_size=128)
configs/xcit/xcit-large-24-p8_8xb128_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
model = dict(
type='ImageClassifier',
backbone=dict(
type='XCiT',
patch_size=8,
embed_dims=768,
depth=24,
num_heads=16,
mlp_ratio=4,
qkv_bias=True,
layer_scale_init_value=1e-5,
tokens_norm=True,
out_type='cls_token',
),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=768,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
),
train_cfg=dict(augments=[
dict(type='Mixup', alpha=0.8),
dict(type='CutMix', alpha=1.0),
]),
)
# dataset settings
train_dataloader = dict(batch_size=128)
configs/xcit/xcit-medium-24-p16_8xb128_in1k-384px.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs64_swin_384.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
model = dict(
type='ImageClassifier',
backbone=dict(
type='XCiT',
patch_size=16,
embed_dims=512,
depth=24,
num_heads=8,
mlp_ratio=4,
qkv_bias=True,
layer_scale_init_value=1e-5,
tokens_norm=True,
out_type='cls_token',
),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=512,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
),
train_cfg=dict(augments=[
dict(type='Mixup', alpha=0.8),
dict(type='CutMix', alpha=1.0),
]),
)
# dataset settings
train_dataloader = dict(batch_size=128)
configs/xcit/xcit-medium-24-p16_8xb128_in1k.py 0 → 100644
View file @ 495d9ed9
_base_ = [
'../_base_/datasets/imagenet_bs64_swin_224.py',
'../_base_/schedules/imagenet_bs1024_adamw_swin.py',
'../_base_/default_runtime.py',
]
model = dict(
type='ImageClassifier',
backbone=dict(
type='XCiT',
patch_size=16,
embed_dims=512,
depth=24,
num_heads=8,
mlp_ratio=4,
qkv_bias=True,
layer_scale_init_value=1e-5,
tokens_norm=True,
out_type='cls_token',
),
head=dict(
type='LinearClsHead',
num_classes=1000,
in_channels=512,
loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
),
train_cfg=dict(augments=[
dict(type='Mixup', alpha=0.8),
dict(type='CutMix', alpha=1.0),
]),
)
# dataset settings
train_dataloader = dict(batch_size=128)
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