pytorch-image-models/modelindex/models/dpn.md

# Summary

A **Dual Path Network (DPN)** is a convolutional neural network which presents a new topology of connection paths internally. The intuition is that [ResNets](https://paperswithcode.com/method/resnet) enables feature re-usage while DenseNet enables new feature exploration, and both are important for learning good representations. To enjoy the benefits from both path topologies, Dual Path Networks share common features while maintaining the flexibility to explore new features through dual path architectures. 

The principal building block is an [DPN Block](https://paperswithcode.com/method/dpn-block).

## How do I use this model on an image?
To load a pretrained model:

```python
import timm
model = timm.create_model('dpn68', 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. `dpn68`. 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('dpn68', pretrained=True).reset_classifier(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
@misc{chen2017dual,
      title={Dual Path Networks}, 
      author={Yunpeng Chen and Jianan Li and Huaxin Xiao and Xiaojie Jin and Shuicheng Yan and Jiashi Feng},
      year={2017},
      eprint={1707.01629},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
```

<!--
Models:
- Name: dpn68
  Metadata:
    FLOPs: 2990567880
    Batch Size: 1280
    Training Data:
    - ImageNet
    Training Techniques:
    - SGD with Momentum
    - Weight Decay
    Training Resources: 40x K80 GPUs
    Architecture:
    - Batch Normalization
    - Convolution
    - DPN Block
    - Dense Connections
    - Global Average Pooling
    - Max Pooling
    - Softmax
    File Size: 50761994
    Tasks:
    - Image Classification
    ID: dpn68
    LR: 0.316
    Layers: 68
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/dpn.py#L270
  In Collection: DPN
- Name: dpn68b
  Metadata:
    FLOPs: 2990567880
    Batch Size: 1280
    Training Data:
    - ImageNet
    Training Techniques:
    - SGD with Momentum
    - Weight Decay
    Training Resources: 40x K80 GPUs
    Architecture:
    - Batch Normalization
    - Convolution
    - DPN Block
    - Dense Connections
    - Global Average Pooling
    - Max Pooling
    - Softmax
    File Size: 50781025
    Tasks:
    - Image Classification
    ID: dpn68b
    LR: 0.316
    Layers: 68
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/dpn.py#L278
  In Collection: DPN
- Name: dpn92
  Metadata:
    FLOPs: 8357659624
    Batch Size: 1280
    Training Data:
    - ImageNet
    Training Techniques:
    - SGD with Momentum
    - Weight Decay
    Training Resources: 40x K80 GPUs
    Architecture:
    - Batch Normalization
    - Convolution
    - DPN Block
    - Dense Connections
    - Global Average Pooling
    - Max Pooling
    - Softmax
    File Size: 151248422
    Tasks:
    - Image Classification
    ID: dpn92
    LR: 0.316
    Layers: 92
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/dpn.py#L286
  In Collection: DPN
- Name: dpn131
  Metadata:
    FLOPs: 20586274792
    Batch Size: 960
    Training Data:
    - ImageNet
    Training Techniques:
    - SGD with Momentum
    - Weight Decay
    Training Resources: 40x K80 GPUs
    Architecture:
    - Batch Normalization
    - Convolution
    - DPN Block
    - Dense Connections
    - Global Average Pooling
    - Max Pooling
    - Softmax
    File Size: 318016207
    Tasks:
    - Image Classification
    ID: dpn131
    LR: 0.316
    Layers: 131
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/dpn.py#L302
  In Collection: DPN
- Name: dpn107
  Metadata:
    FLOPs: 23524280296
    Batch Size: 1280
    Training Data:
    - ImageNet
    Training Techniques:
    - SGD with Momentum
    - Weight Decay
    Training Resources: 40x K80 GPUs
    Architecture:
    - Batch Normalization
    - Convolution
    - DPN Block
    - Dense Connections
    - Global Average Pooling
    - Max Pooling
    - Softmax
    File Size: 348612331
    Tasks:
    - Image Classification
    ID: dpn107
    LR: 0.316
    Layers: 107
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/dpn.py#L310
  In Collection: DPN
- Name: dpn98
  Metadata:
    FLOPs: 15003675112
    Batch Size: 1280
    Training Data:
    - ImageNet
    Training Techniques:
    - SGD with Momentum
    - Weight Decay
    Training Resources: 40x K80 GPUs
    Architecture:
    - Batch Normalization
    - Convolution
    - DPN Block
    - Dense Connections
    - Global Average Pooling
    - Max Pooling
    - Softmax
    File Size: 247021307
    Tasks:
    - Image Classification
    ID: dpn98
    LR: 0.4
    Layers: 98
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/d8e69206be253892b2956341fea09fdebfaae4e3/timm/models/dpn.py#L294
  In Collection: DPN
Collections:
- Name: DPN
  Paper:
    title: Dual Path Networks
    url: https://papperswithcode.com//paper/dual-path-networks
  type: model-index
Type: model-index
-->