Mnasnet: Image Classification
MNASNet is a lightweight neural network architecture developed by Google, specifically designed for efficient image classification on mobile devices. MnasNet leverages automated machine learning (AutoML) with reinforcement learning to search for a network architecture that achieves an optimal balance between accuracy and latency. The MnasNet architecture builds on MobileNet’s depthwise separable convolutions, further optimizing computational efficiency. Compared to manually designed models, MnasNet offers excellent accuracy at lower computational costs, making it ideal for resource-constrained environments, such as mobile and embedded systems. This model is widely used in tasks like image classification and object detection, providing an efficient solution for mobile vision applications.
Source model
- Input shape: 224x224
- Number of parameters: 2.12M
- Model size: 8.45M
- Output shape: 1x1000
Source model repository: MNASNet
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm
License
Source Model: BSD-3-CLAUSE
Deployable Model: APLUX-MODEL-FARM-LICENSE
- Downloads last month
- 5