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.
95 lines
2.8 KiB
95 lines
2.8 KiB
# Summary
|
|
|
|
**MnasNet** is a type of convolutional neural network optimized for mobile devices that is discovered through mobile neural architecture search, which explicitly incorporates model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. The main building block is an [inverted residual block](https://paperswithcode.com/method/inverted-residual-block) (from [MobileNetV2](https://paperswithcode.com/method/mobilenetv2)).
|
|
|
|
{% include 'code_snippets.md' %}
|
|
|
|
## 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{tan2019mnasnet,
|
|
title={MnasNet: Platform-Aware Neural Architecture Search for Mobile},
|
|
author={Mingxing Tan and Bo Chen and Ruoming Pang and Vijay Vasudevan and Mark Sandler and Andrew Howard and Quoc V. Le},
|
|
year={2019},
|
|
eprint={1807.11626},
|
|
archivePrefix={arXiv},
|
|
primaryClass={cs.CV}
|
|
}
|
|
```
|
|
|
|
<!--
|
|
Models:
|
|
- Name: semnasnet_100
|
|
Metadata:
|
|
FLOPs: 414570766
|
|
Training Data:
|
|
- ImageNet
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Convolution
|
|
- Depthwise Separable Convolution
|
|
- Dropout
|
|
- Global Average Pooling
|
|
- Inverted Residual Block
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Connection
|
|
- Softmax
|
|
- Squeeze-and-Excitation Block
|
|
File Size: 15731489
|
|
Tasks:
|
|
- Image Classification
|
|
ID: semnasnet_100
|
|
Crop Pct: '0.875'
|
|
Image Size: '224'
|
|
Interpolation: bicubic
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/efficientnet.py#L928
|
|
In Collection: MNASNet
|
|
- Name: mnasnet_100
|
|
Metadata:
|
|
FLOPs: 416415488
|
|
Batch Size: 4000
|
|
Training Data:
|
|
- ImageNet
|
|
Training Techniques:
|
|
- RMSProp
|
|
- Weight Decay
|
|
Architecture:
|
|
- 1x1 Convolution
|
|
- Batch Normalization
|
|
- Convolution
|
|
- Depthwise Separable Convolution
|
|
- Dropout
|
|
- Global Average Pooling
|
|
- Inverted Residual Block
|
|
- Max Pooling
|
|
- ReLU
|
|
- Residual Connection
|
|
- Softmax
|
|
File Size: 17731774
|
|
Tasks:
|
|
- Image Classification
|
|
ID: mnasnet_100
|
|
Layers: 100
|
|
Dropout: 0.2
|
|
Crop Pct: '0.875'
|
|
Momentum: 0.9
|
|
Image Size: '224'
|
|
Interpolation: bicubic
|
|
RMSProp Decay: 0.9
|
|
Code: https://github.com/rwightman/pytorch-image-models/blob/9a25fdf3ad0414b4d66da443fe60ae0aa14edc84/timm/models/efficientnet.py#L894
|
|
In Collection: MNASNet
|
|
Collections:
|
|
- Name: MNASNet
|
|
Paper:
|
|
title: 'MnasNet: Platform-Aware Neural Architecture Search for Mobile'
|
|
url: https://papperswithcode.com//paper/mnasnet-platform-aware-neural-architecture
|
|
type: model-index
|
|
Type: model-index
|
|
-->
|