Command Palette
Search for a command to run...
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Forrest N. Iandola; Song Han; Matthew W. Moskewicz; Khalid Ashraf; William J. Dally; Kurt Keutzer
Abstract
Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). The SqueezeNet architecture is available for download here: https://github.com/DeepScale/SqueezeNet
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| image-classification-on-imagenet-9 | SqueezeNet + Simple Bypass | Top 1 Accuracy: 60.4% |
| image-classification-on-imagenet-p | SqueezeNet + Simple Bypass | Top 5 Accuracy: 82.5% |
| network-pruning-on-imagenet | SqueezeNet (6-bit Deep Compression) | Accuracy: 57.5% MParams: 1.24 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.