You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
278 lines
8.6 KiB
278 lines
8.6 KiB
# SSL ResNeXT
|
|
|
|
A **ResNeXt** repeats a [building block](https://paperswithcode.com/method/resnext-block) that aggregates a set of transformations with the same topology. Compared to a [ResNet](https://paperswithcode.com/method/resnet), it exposes a new dimension, *cardinality* (the size of the set of transformations) $C$, as an essential factor in addition to the dimensions of depth and width.
|
|
|
|
The model in this collection utilises semi-supervised learning to improve the performance of the model. The approach brings important gains to standard architectures for image, video and fine-grained classification.
|
|
|
|
Please note the CC-BY-NC 4.0 license on theses weights, non-commercial use only.
|
|
|
|
## How do I use this model on an image?
|
|
To load a pretrained model:
|
|
|
|
```python
|
|
import timm
|
|
model = timm.create_model('ssl_resnext101_32x16d', pretrained=True)
|
|
model.eval()
|
|
```
|
|
|
|
To load and preprocess the image:
|
|
```python
|
|
import urllib
|
|
from PIL import Image
|
|
from timm.data import resolve_data_config
|
|
from timm.data.transforms_factory import create_transform
|
|
|
|
config = resolve_data_config({}, model=model)
|
|
transform = create_transform(**config)
|
|
|
|
url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
|
|
urllib.request.urlretrieve(url, filename)
|
|
img = Image.open(filename).convert('RGB')
|
|
tensor = transform(img).unsqueeze(0) # transform and add batch dimension
|
|
```
|
|
|
|
To get the model predictions:
|
|
```python
|
|
import torch
|
|
with torch.no_grad():
|
|
out = model(tensor)
|
|
probabilities = torch.nn.functional.softmax(out[0], dim=0)
|
|
print(probabilities.shape)
|
|
# prints: torch.Size([1000])
|
|
```
|
|
|
|
To get the top-5 predictions class names:
|
|
```python
|
|
# Get imagenet class mappings
|
|
url, filename = ("https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt", "imagenet_classes.txt")
|
|
urllib.request.urlretrieve(url, filename)
|
|
with open("imagenet_classes.txt", "r") as f:
|
|
categories = [s.strip() for s in f.readlines()]
|
|
|
|
# Print top categories per image
|
|
top5_prob, top5_catid = torch.topk(probabilities, 5)
|
|
for i in range(top5_prob.size(0)):
|
|
print(categories[top5_catid[i]], top5_prob[i].item())
|
|
# prints class names and probabilities like:
|
|
# [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]
|
|
```
|
|
|
|
Replace the model name with the variant you want to use, e.g. `ssl_resnext101_32x16d`. You can find the IDs in the model summaries at the top of this page.
|
|
|
|
To extract image features with this model, follow the [timm feature extraction examples](https://rwightman.github.io/pytorch-image-models/feature_extraction/), just change the name of the model you want to use.
|
|
|
|
## How do I finetune this model?
|
|
You can finetune any of the pre-trained models just by changing the classifier (the last layer).
|
|
```python
|
|
model = timm.create_model('ssl_resnext101_32x16d', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)
|
|
```
|
|
To finetune on your own dataset, you have to write a training loop or adapt [timm's training
|
|
script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.
|
|
|
|
## How do I train this model?
|
|
|
|
You can follow the [timm recipe scripts](https://rwightman.github.io/pytorch-image-models/scripts/) for training a new model afresh.
|
|
|
|
## Citation
|
|
|
|
```BibTeX
|
|
@article{DBLP:journals/corr/abs-1905-00546,
|
|
author = {I. Zeki Yalniz and
|
|
Herv{\'{e}} J{\'{e}}gou and
|
|
Kan Chen and
|
|
Manohar Paluri and
|
|
Dhruv Mahajan},
|
|
title = {Billion-scale semi-supervised learning for image classification},
|
|
journal = {CoRR},
|
|
volume = {abs/1905.00546},
|
|
year = {2019},
|
|
url = {http://arxiv.org/abs/1905.00546},
|
|
archivePrefix = {arXiv},
|
|
eprint = {1905.00546},
|
|
timestamp = {Mon, 28 Sep 2020 08:19:37 +0200},
|
|
biburl = {https://dblp.org/rec/journals/corr/abs-1905-00546.bib},
|
|
bibsource = {dblp computer science bibliography, https://dblp.org}
|
|
}
|
|
```
|
|
|
|
<!--
|
|
Type: model-index
|
|
Collections:
|
|
- Name: SSL ResNext
|
|
Paper:
|
|
Title: Billion-scale semi-supervised learning for image classification
|
|
URL: https://paperswithcode.com/paper/billion-scale-semi-supervised-learning-for
|
|
Models:
|
|
- Name: ssl_resnext101_32x16d
|
|
In Collection: SSL ResNext
|
|
Metadata:
|
|
FLOPs: 46623691776
|
|
Parameters: 194030000
|
|
File Size: 777518664
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Grouped Convolution
|
|
- Max Pooling
|
|
- ReLU
|
|
- ResNeXt Block
|
|
- Residual Connection
|
|
- Softmax
|
|
Tasks:
|
|
- Image Classification
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Training Data:
|
|
- ImageNet
|
|
- YFCC-100M
|
|
Training Resources: 64x GPUs
|
|
ID: ssl_resnext101_32x16d
|
|
LR: 0.0015
|
|
Epochs: 30
|
|
Layers: 101
|
|
Crop Pct: '0.875'
|
|
Batch Size: 1536
|
|
Image Size: '224'
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L944
|
|
Weights: https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext101_32x16-15fffa57.pth
|
|
Results:
|
|
- Task: Image Classification
|
|
Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 81.84%
|
|
Top 5 Accuracy: 96.09%
|
|
- Name: ssl_resnext101_32x4d
|
|
In Collection: SSL ResNext
|
|
Metadata:
|
|
FLOPs: 10298145792
|
|
Parameters: 44180000
|
|
File Size: 177341913
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Grouped Convolution
|
|
- Max Pooling
|
|
- ReLU
|
|
- ResNeXt Block
|
|
- Residual Connection
|
|
- Softmax
|
|
Tasks:
|
|
- Image Classification
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Training Data:
|
|
- ImageNet
|
|
- YFCC-100M
|
|
Training Resources: 64x GPUs
|
|
ID: ssl_resnext101_32x4d
|
|
LR: 0.0015
|
|
Epochs: 30
|
|
Layers: 101
|
|
Crop Pct: '0.875'
|
|
Batch Size: 1536
|
|
Image Size: '224'
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L924
|
|
Weights: https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext101_32x4-dc43570a.pth
|
|
Results:
|
|
- Task: Image Classification
|
|
Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 80.91%
|
|
Top 5 Accuracy: 95.73%
|
|
- Name: ssl_resnext101_32x8d
|
|
In Collection: SSL ResNext
|
|
Metadata:
|
|
FLOPs: 21180417024
|
|
Parameters: 88790000
|
|
File Size: 356056638
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Grouped Convolution
|
|
- Max Pooling
|
|
- ReLU
|
|
- ResNeXt Block
|
|
- Residual Connection
|
|
- Softmax
|
|
Tasks:
|
|
- Image Classification
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Training Data:
|
|
- ImageNet
|
|
- YFCC-100M
|
|
Training Resources: 64x GPUs
|
|
ID: ssl_resnext101_32x8d
|
|
LR: 0.0015
|
|
Epochs: 30
|
|
Layers: 101
|
|
Crop Pct: '0.875'
|
|
Batch Size: 1536
|
|
Image Size: '224'
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L934
|
|
Weights: https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext101_32x8-2cfe2f8b.pth
|
|
Results:
|
|
- Task: Image Classification
|
|
Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 81.61%
|
|
Top 5 Accuracy: 96.04%
|
|
- Name: ssl_resnext50_32x4d
|
|
In Collection: SSL ResNext
|
|
Metadata:
|
|
FLOPs: 5472648192
|
|
Parameters: 25030000
|
|
File Size: 100428550
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Convolution
|
|
- Global Average Pooling
|
|
- Grouped Convolution
|
|
- Max Pooling
|
|
- ReLU
|
|
- ResNeXt Block
|
|
- Residual Connection
|
|
- Softmax
|
|
Tasks:
|
|
- Image Classification
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Training Data:
|
|
- ImageNet
|
|
- YFCC-100M
|
|
Training Resources: 64x GPUs
|
|
ID: ssl_resnext50_32x4d
|
|
LR: 0.0015
|
|
Epochs: 30
|
|
Layers: 50
|
|
Crop Pct: '0.875'
|
|
Batch Size: 1536
|
|
Image Size: '224'
|
|
Weight Decay: 0.0001
|
|
Interpolation: bilinear
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/resnet.py#L914
|
|
Weights: https://dl.fbaipublicfiles.com/semiweaksupervision/model_files/semi_supervised_resnext50_32x4-ddb3e555.pth
|
|
Results:
|
|
- Task: Image Classification
|
|
Dataset: ImageNet
|
|
Metrics:
|
|
Top 1 Accuracy: 80.3%
|
|
Top 5 Accuracy: 95.41%
|
|
--> |