EfficientNet-B0: Image Classification

EfficientNet-B0 is the baseline model in the EfficientNet series introduced by Google in 2019. EfficientNet employs a "compound scaling" method, which jointly optimizes the network's depth, width, and resolution to achieve greater computational efficiency and accuracy. EfficientNet-B0 utilizes the Mobile Inverted Bottleneck Convolution (MBConv) module along with depthwise separable convolutions, significantly reducing parameters and computational cost. Despite being the smallest model in the series, EfficientNet-B0 performs excellently across various computer vision tasks, delivering high accuracy while maintaining low resource requirements, making it ideal for mobile devices and edge computing in resource-constrained environments.

Source model

  • Input shape: 224x224
  • Number of parameters: 5.04M
  • Model size: 20.16M
  • Output shape: 1x1000

Source model repository: EfficientNet-B0

Performance Reference

Please search model by model name in Model Farm

Inference & Model Conversion

Please search model by model name in Model Farm

License

Downloads last month
7
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support