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.
pytorch-image-models/hfdocs/source/models/fbnet.mdx

143 lines
4.8 KiB

# FBNet
**FBNet** is a type of convolutional neural architectures discovered through [DNAS](https://paperswithcode.com/method/dnas) neural architecture search. It utilises a basic type of image model block inspired by [MobileNetv2](https://paperswithcode.com/method/mobilenetv2) that utilises depthwise convolutions and an inverted residual structure (see components).
The principal building block is the [FBNet Block](https://paperswithcode.com/method/fbnet-block).
## How do I use this model on an image?
To load a pretrained model:
```py
>>> import timm
>>> model = timm.create_model('fbnetc_100', pretrained=True)
>>> model.eval()
```
To load and preprocess the image:
```py
>>> 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:
```py
>>> 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:
```py
>>> # 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. `fbnetc_100`. 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).
```py
>>> model = timm.create_model('fbnetc_100', 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](scripts) for training a new model afresh.
## Citation
```BibTeX
@misc{wu2019fbnet,
title={FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search},
author={Bichen Wu and Xiaoliang Dai and Peizhao Zhang and Yanghan Wang and Fei Sun and Yiming Wu and Yuandong Tian and Peter Vajda and Yangqing Jia and Kurt Keutzer},
year={2019},
eprint={1812.03443},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
<!--
Type: model-index
Collections:
- Name: FBNet
Paper:
Title: 'FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural
Architecture Search'
URL: https://paperswithcode.com/paper/fbnet-hardware-aware-efficient-convnet-design
Models:
- Name: fbnetc_100
In Collection: FBNet
Metadata:
FLOPs: 508940064
Parameters: 5570000
File Size: 22525094
Architecture:
- 1x1 Convolution
- Convolution
- Dense Connections
- Dropout
- FBNet Block
- Global Average Pooling
- Softmax
Tasks:
- Image Classification
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Data:
- ImageNet
Training Resources: 8x GPUs
ID: fbnetc_100
LR: 0.1
Epochs: 360
Layers: 22
Dropout: 0.2
Crop Pct: '0.875'
Momentum: 0.9
Batch Size: 256
Image Size: '224'
Weight Decay: 0.0005
Interpolation: bilinear
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/efficientnet.py#L985
Weights: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/fbnetc_100-c345b898.pth
Results:
- Task: Image Classification
Dataset: ImageNet
Metrics:
Top 1 Accuracy: 75.12%
Top 5 Accuracy: 92.37%
-->